[{"content":"We are excited to share the release of a specialized Gemini Gem designed specifically for Computational Medical Physicists. This AI agent acts as a knowledgeable co-pilot for research, computational modeling, dosimetry, and medical image computing.\nWhat is the Computational Medical Physicist Gem? The Computational Medical Physicist Gem is a custom-tuned assistant tailored to the complex, multidisciplinary domain of medical physics. It bridges the gap between physics modeling, coding, and clinical guidelines.\nWhether you are debugging particle transport simulations, building deep learning pipelines for image segmentation, or checking AAPM protocols, this Gem is pre-conditioned to provide expert-level technical feedback.\nKey Capabilities The Gem is trained to assist in four primary pillars of computational medical physics:\n1. Medical Image Processing \u0026amp; Deep Learning Speed up your imaging workflows using popular Python packages such as SimpleITK, Pydicom, and PyTorch.\nExample Ask: \u0026ldquo;Write a robust SimpleITK script to perform rigid registration between CT and MR images, including resampling.\u0026rdquo; 2. Dosimetry \u0026amp; Quantitative Radiomics Validate dose distribution algorithms, biological modeling equations (TCP/NTCP), and quantitative radiomics feature extraction parameters.\nExample Ask: \u0026ldquo;Draft a Python function to extract First-Order and GLCM radiomics features from an NRRD volume and RTSTRUCT mask.\u0026rdquo; 3. Clinical Guidelines \u0026amp; Protocol QA Quickly lookup reference standards and math details based on AAPM (American Association of Physicists in Medicine) Task Group reports such as TG-51 (reference dosimetry) and TG-142 (linear accelerator QA).\nExample Ask: \u0026ldquo;Summarize the TG-51 water calibration procedure and explain the temperature-pressure correction factor $P_{TP}$ equation.\u0026rdquo; 4. Monte Carlo \u0026amp; Radiation Transport Simulations Get assistance with writing, configuring, and debugging simulation scripts in Geant4, MCNP, and EGSnrc.\nExample Ask: \u0026ldquo;Help me configure a physics list in Geant4 for simulating a clinical 6 MV photon beam and calculating the Bragg peak.\u0026rdquo; Seamless Synergy with qradiomics This Gem is a perfect companion for researchers utilizing the newly released qradiomics CLI. When you are writing Nextflow pipelines or integrating new Radiomics feature extractors, you can use this Gem to rapidly draft scripts, debug PyRadiomics configuration files, or write custom clinical merge code.\nTry It Now The Gem is completely free to use. Click the link below to add it to your Google Gemini account and start boosting your medical physics research today:\n👉 Launch the Computational Medical Physicist Gem\nWe would love to hear your feedback on how it performs in your daily research tasks!\n","permalink":"https://qradiomics.com/posts/2026-05-24-announcing-gemini-gem-for-computational-medical-physics/","summary":"\u003cp\u003eWe are excited to share the release of a specialized \u003cstrong\u003eGemini Gem\u003c/strong\u003e designed specifically for \u003cstrong\u003eComputational Medical Physicists\u003c/strong\u003e. This AI agent acts as a knowledgeable co-pilot for research, computational modeling, dosimetry, and medical image computing.\u003c/p\u003e\n\u003ch2 id=\"what-is-the-computational-medical-physicist-gem\"\u003eWhat is the Computational Medical Physicist Gem?\u003c/h2\u003e\n\u003cp\u003eThe \u003ca href=\"https://gemini.google.com/gem/17j3telEOpOnpU01FDvGLAcLEu1mOxrtG?usp=sharing\"\u003eComputational Medical Physicist Gem\u003c/a\u003e is a custom-tuned assistant tailored to the complex, multidisciplinary domain of medical physics. It bridges the gap between physics modeling, coding, and clinical guidelines.\u003c/p\u003e","title":"Announcing Gemini Gem for Computational Medical Physics — Your Specialized AI Research Assistant"},{"content":"This page summarizes active and legacy open-source projects from Choi Lab.\nActive qradiomics Unified Python radiomics CLI and library for end-to-end workflows (DICOM conversion, feature extraction, modeling, and reproducible orchestration).\nRepo: github.com/choilab-jefferson/qradiomics License: MIT Status: actively maintained Legacy (superseded by qradiomics) Lung Cancer Screening Radiomics Earlier end-to-end screening workflow on LIDC-IDRI and LUNGx with AutoML components.\nRepo: github.com/choilab-jefferson/LungCancerScreeningRadiomics Status: no longer maintained Radiomics Tools C++/Python (ITK, Ruffus) radiomics pipeline including DICOM/RT handling and feature extraction.\nRepo: github.com/taznux/radiomics-tools Status: no longer maintained Lung Image Analysis Framwork MATLAB framework for pulmonary nodule detection and characterization on CT.\nRepo: github.com/taznux/lung-image-analysis Status: no longer maintained Related PathCNN Interpretable CNN for survival prediction and pathway analysis in glioblastoma.\nRepo: github.com/mskspi/PathCNN ","permalink":"https://qradiomics.com/projects/2016-08-27-open-source-projects/","summary":"\u003cp\u003eThis page summarizes active and legacy open-source projects from Choi Lab.\u003c/p\u003e\n\u003ch2 id=\"active\"\u003eActive\u003c/h2\u003e\n\u003ch3 id=\"qradiomics\"\u003e\u003ca href=\"../2026-05-17-qradiomics/\"\u003eqradiomics\u003c/a\u003e\u003c/h3\u003e\n\u003cp\u003eUnified Python radiomics CLI and library for end-to-end workflows (DICOM conversion, feature extraction, modeling, and reproducible orchestration).\u003c/p\u003e\n\u003cul\u003e\n\u003cli\u003eRepo: \u003ca href=\"https://github.com/choilab-jefferson/qradiomics\"\u003egithub.com/choilab-jefferson/qradiomics\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003eLicense: MIT\u003c/li\u003e\n\u003cli\u003eStatus: actively maintained\u003c/li\u003e\n\u003c/ul\u003e\n\u003ch2 id=\"legacy-superseded-by-qradiomics\"\u003eLegacy (superseded by qradiomics)\u003c/h2\u003e\n\u003ch3 id=\"lung-cancer-screening-radiomics\"\u003e\u003ca href=\"../2022-06-10-lung-cancer-screening-radiomics/\"\u003eLung Cancer Screening Radiomics\u003c/a\u003e\u003c/h3\u003e\n\u003cp\u003eEarlier end-to-end screening workflow on LIDC-IDRI and LUNGx with AutoML components.\u003c/p\u003e\n\u003cul\u003e\n\u003cli\u003eRepo: \u003ca href=\"https://github.com/choilab-jefferson/LungCancerScreeningRadiomics\"\u003egithub.com/choilab-jefferson/LungCancerScreeningRadiomics\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003eStatus: no longer maintained\u003c/li\u003e\n\u003c/ul\u003e\n\u003ch3 id=\"radiomics-tools\"\u003e\u003ca href=\"../2016-07-23-radiomics-tools/\"\u003eRadiomics Tools\u003c/a\u003e\u003c/h3\u003e\n\u003cp\u003eC++/Python (ITK, Ruffus) radiomics pipeline including DICOM/RT handling and feature extraction.\u003c/p\u003e","title":"Open source projects"},{"content":"We are releasing qradiomics — an open-source Python CLI that unifies more than a decade of Choi Lab radiomics work into a single, reproducible, pip-installable toolkit.\nWhat is qradiomics? qradiomics (command: qr) is a radiomics research CLI built for the full data flow from raw DICOM to published-grade results:\nDICOM download → conversion → feature extraction → clinical merge → modeling Each step is a single Unix-style command. Pipelines are assembled from those atomic commands using plain JSON plans, executed by Nextflow (per-patient parallel), Prefect, or inline. One command gets you started:\ncurl -sSL https://raw.githubusercontent.com/choilab-jefferson/qradiomics/main/scripts/kickoff.sh | bash Three earlier projects, unified qradiomics is the direct successor of three Choi Lab codebases that are now retired:\nEarlier project Stack Status taznux/lung-image-analysis MATLAB superseded taznux/radiomics-tools C++ / ITK / Ruffus superseded choilab-jefferson/LungCancerScreeningRadiomics MATLAB / Python superseded The feature extractors, spiculation pipeline, and LIDC-IDRI workflow from all three are now available as pure Python under a single MIT-licensed package.\nReproducibility: published results re-confirmed One of the primary goals of qradiomics is to make published results independently verifiable. Running the bundled pipelines on public TCIA datasets reproduces — or exceeds — the numbers from four peer-reviewed papers:\nPaper Method Our result Published Choi 2018 Med Phys radiomics50 AUC 0.872 ± 0.010 0.83 – 0.95 Choi 2021 CMPB — spic6 only 6 spiculation features AUC 0.816 ± 0.006 0.80 – 0.85 Choi 2021 CMPB — PM (CIR masks) radiomics + spic AUC 0.868 ± 0.039 0.85 Choi 2021 CMPB — LUNGx external radiomics50 + calibration AUC 0.756 0.76 The LUNGx external validation result (AUC 0.756) matches the published number exactly using only interpretable hand-crafted features — no neural-network encoder required.\nKey features qr tcia download — bulk-pull any TCIA collection with multi-process progress qr convert dicom-series / rtstruct — DICOM CT/PET/MR + RTSTRUCT → NRRD (SUV-corrected for PET, case-insensitive ROI lookup) qr extract — PyRadiomics with bundled pattern templates (nsclc-survival, ct-default, …) qr analyze survival / classify / importance — Cox PH, logistic regression, random-forest feature importance qr ml train / predict / evaluate — leakage-safe cross-validated model building qr workflow plan / scaffold / run — Nextflow / Prefect / inline pipeline assembly qr anonymize — strip PHI from DICOM trees (PS3.15 Annex E) qradiomics.shape — Python re-implementations of the Choi 2014 AHSN nodule detector and Choi 2021 spiculation quantifier Validated on four public cohorts The same pipeline has been validated end-to-end on TCIA data:\nNSCLC-Radiomics (Lung1) — Aerts 2014 discovery cohort (n=420) — open access LIDC-IDRI — full 1,018-scan reference benchmark — open access NSCLC-Cetuximab — external validation (n=460) — available via NCI data access agreement ACRIN-NSCLC-FDG-PET — PET/CT with cardiac and pulmonary ROIs — open access Get started # Install pip install -e .[rtstruct] # One-liner smoke test (synthetic data, no download required) python scripts/smoke.py # Full Lung1 end-to-end (~1 h on 16 cores) qr tcia download --collection NSCLC-Radiomics --modality CT -o /data/Lung1 -j 16 Full documentation: ../../projects/2026-05-17-qradiomics/\nSource code: github.com/choilab-jefferson/qradiomics\nBroader Choi Lab research — all publicly available qradiomics is the computational backbone, but the lab\u0026rsquo;s research portfolio covers several active fronts. All of the following are fully public.\nInterpretable spiculation quantification (Choi 2021, CMPB) A reproducible, geometry-based algorithm for quantifying nodule spiculation in CT — one of the most diagnostically important features for lung cancer malignancy assessment. Available as qradiomics.shape. Paper: doi:10.1016/j.cmpb.2020.105839.\nFunctional radiomics: cardiac PET in lung cancer RT (Choi 2023 / 2024) A novel functional radiomics method that uses serial cardiac FDG-PET uptake as a surrogate of radiation-induced cardiotoxicity. Featured in a JCO Clinical Cancer Informatics editorial.\nPosts: Novel Functional Delta-Radiomics (AAPM/ASTRO 2023) · JCO CCI editorial (2024)\nLooking back — and forward The first radiomics code from this lab was written in MATLAB in 2012. Since then, the stack evolved through C++/ITK (radiomics-tools), through separate MATLAB+Python scripts (LungCancerScreeningRadiomics), and is now a single Python package with automated pipelines, leakage-safe modeling, and full TCIA integration.\nThe pipeline was first presented publicly at AAPM 2025 (Washington, DC, Jul 27), validated on 207 institutional lung cancer patients (340 GTVs) and the TCIA NSCLC-Radiomics (Lung1) cohort (422 patients). The study demonstrated end-to-end automation — CT/RTSTRUCT/RTDOSE conversion, PyRadiomics extraction, and Prefect-orchestrated inference — processing the full Lung1 dataset in under 20 minutes:\nBhetwal P, Dichmann M, Ghimire R, Chen Y, Vinogradskiy Y, Werner-Wasik M, Dicker A, Choi W.\nDevelopment and Validation of a Scalable Radiomics Pipeline for Lung Cancer Research Using Clinical and Public Datasets (SU-1015-202-4).\nMedical Physics 52(10):e700597, AAPM 2025.\nA companion study presented at ASTRO 2025 applied the same pipeline to survival modeling across a 629-patient multi-institutional cohort (207 institutional + 422 TCIA Lung1), combining clinical and radiomic features with Cox PH models. Integrating radiomics with clinical variables improved overall survival prediction from C-index 0.50–0.56 (clinical-only) to 0.57–0.69. The institutional portion uses private clinical data; the TCIA Lung1 component is fully reproducible with qradiomics:\nBhetwal P, Dichmann M, Ghimire R, Chen Y, Vinogradskiy Y, Werner-Wasik M, Dicker AP, Choi W.\nIntegrating Clinical and Radiomic Features for Enhanced Prognostic Modeling for Lung Cancer Survival.\nIJROBP 123(1):e719, ASTRO 2025. doi:10.1016/S0360-3016(25)03724-1\nThe open-source release arrives roughly nine months after those presentations. The public release of qradiomics marks the point where reproducibility is no longer an afterthought — every result in our past papers can be re-run with one command on publicly available data.\nFull documentation: ../../projects/2026-05-17-qradiomics/\nSource code: github.com/choilab-jefferson/qradiomics\nChoi Lab, Department of Radiation Oncology, Sidney Kimmel Medical College at Thomas Jefferson University.\n","permalink":"https://qradiomics.com/posts/2026-05-20-introducing-qradiomics/","summary":"\u003cp\u003eWe are releasing \u003cstrong\u003e\u003ca href=\"https://github.com/choilab-jefferson/qradiomics\"\u003eqradiomics\u003c/a\u003e\u003c/strong\u003e — an open-source Python CLI that unifies more than a decade of Choi Lab radiomics work into a single, reproducible, pip-installable toolkit.\u003c/p\u003e\n\u003ch2 id=\"what-is-qradiomics\"\u003eWhat is qradiomics?\u003c/h2\u003e\n\u003cp\u003e\u003ccode\u003eqradiomics\u003c/code\u003e (command: \u003ccode\u003eqr\u003c/code\u003e) is a radiomics research CLI built for the full data flow from raw DICOM to published-grade results:\u003c/p\u003e\n\u003cpre tabindex=\"0\"\u003e\u003ccode\u003eDICOM download → conversion → feature extraction → clinical merge → modeling\n\u003c/code\u003e\u003c/pre\u003e\u003cp\u003eEach step is a single Unix-style command. Pipelines are assembled from those atomic commands using plain JSON plans, executed by Nextflow (per-patient parallel), Prefect, or inline. One command gets you started:\u003c/p\u003e","title":"Introducing qradiomics — A Unified Radiomics CLI for Reproducible Research"},{"content":"Thrilled to share that our work has been selected for an Oral Scientific Presentation in the BEST of Physics session at the American Society for Radiation Oncology (ASTRO) 2026 Annual Meeting, September 26–30 in Boston, MA. Out of ~2,700 abstracts submitted to ASTRO this year, only 300 were chosen for oral presentation, and BEST of Physics gathers the highest-rated physics work of the meeting.\nPresentation details Abstract # 75557 Title Early Adaptive Interventions in Lung Cancer: Leveraging Fusion of Longitudinal CBCT Trajectories and Clinical Variables for Robust Survival Prediction Session SS 19 — BEST of Physics Date / Time September 28, 2026 · 10:45 AM – 12:00 PM ET Venue Thomas M. Menino Convention \u0026amp; Exhibition Center, Boston, MA Format 7-min oral + 3-min Q\u0026amp;A Publication Red Journal supplement Authors Wookjin Choi, Pradeep Bhetwal, Michael Dichmann, Yingcui Jia, Wenchao Cao, Danfu Liang, Yingxuan Chen, Adam Dicker, Yevgeniy Vinogradskiy\nDepartment of Radiation Oncology, Sidney Kimmel Medical College at Thomas Jefferson University, Philadelphia, PA\nAcknowledgement. This work would not exist without Dr. Pradeep Bhetwal, who led the original data collection across the 189-patient cohort and built the first CBCT radiomics extraction pipeline and initial survival model during his time in the lab. The cumulative-longitudinal framework presented here was developed on the foundation of his earlier work — published as two first-author abstracts:\nBhetwal P, Dichmann M, Ghimire R, Chen Y, Vinogradskiy Y, Werner-Wasik M, Dicker A, Choi W. Development and Validation of a Scalable Radiomics Pipeline for Lung Cancer Research Using Clinical and Public Datasets (SU-1015-202-4). Medical Physics 52(10):e700597, AAPM 2025. Bhetwal P, Dichmann M, Ghimire R, Chen Y, Vinogradskiy Y, Werner-Wasik M, Dicker AP, Choi W. Integrating Clinical and Radiomic Features for Enhanced Prognostic Modeling for Lung Cancer Survival. IJROBP 123(1):e719, ASTRO 2025. Funding. This research was supported by a research grant from Varian Medical Systems, Inc. (related announcement).\nWhat the study is about Traditional prognostic models for lung cancer rely on static pre-treatment factors and miss the dynamic response of tumors during radiotherapy. Cone-beam CT (CBCT) provides serial imaging of this evolution, but snapshot or delta-radiomics approaches fail to capture the full response trajectory.\nWe propose a cumulative longitudinal radiomics framework that integrates clinical data with CBCT-derived trajectories. Across 189 patients · 225 treatment courses · 5,067 CBCT scans, we evaluated how early in the treatment course we can identify high-risk patients from imaging dynamics alone.\nKey finding: the cumulative CBCT model reaches peak prognostic accuracy by Week 2 (C-index 0.72), with stability improving monotonically through Week 6 — outperforming clinical-only, planning-CT, and delta-radiomics baselines. The framework uses standard-of-care imaging with no additional acquisition burden, offering a practical pathway toward earlier adaptive radiotherapy interventions.\nLooking forward to Boston Excited to present this work to the radiation oncology physics community in late September. Drop by SS 19 if you\u0026rsquo;re attending!\nThe full abstract will be published in the Red Journal supplement closer to the meeting. Stay tuned for slides and follow-up materials.\n","permalink":"https://qradiomics.com/posts/2026-05-18-astro-2026-best-of-physics-oral-acceptance/","summary":"\u003cp\u003eThrilled to share that our work has been selected for an \u003cstrong\u003eOral Scientific Presentation in the \u003cem\u003eBEST of Physics\u003c/em\u003e session\u003c/strong\u003e at the \u003cstrong\u003eAmerican Society for Radiation Oncology (ASTRO) 2026 Annual Meeting\u003c/strong\u003e, September 26–30 in Boston, MA. Out of \u003cstrong\u003e~2,700 abstracts submitted\u003c/strong\u003e to ASTRO this year, only \u003cstrong\u003e300 were chosen\u003c/strong\u003e for oral presentation, and \u003cem\u003eBEST of Physics\u003c/em\u003e gathers the highest-rated physics work of the meeting.\u003c/p\u003e\n\u003ch2 id=\"presentation-details\"\u003ePresentation details\u003c/h2\u003e\n\u003ctable\u003e\n  \u003cthead\u003e\n      \u003ctr\u003e\n          \u003cth\u003e\u003c/th\u003e\n          \u003cth\u003e\u003c/th\u003e\n      \u003c/tr\u003e\n  \u003c/thead\u003e\n  \u003ctbody\u003e\n      \u003ctr\u003e\n          \u003ctd\u003e\u003cstrong\u003eAbstract #\u003c/strong\u003e\u003c/td\u003e\n          \u003ctd\u003e75557\u003c/td\u003e\n      \u003c/tr\u003e\n      \u003ctr\u003e\n          \u003ctd\u003e\u003cstrong\u003eTitle\u003c/strong\u003e\u003c/td\u003e\n          \u003ctd\u003eEarly Adaptive Interventions in Lung Cancer: Leveraging Fusion of Longitudinal CBCT Trajectories and Clinical Variables for Robust Survival Prediction\u003c/td\u003e\n      \u003c/tr\u003e\n      \u003ctr\u003e\n          \u003ctd\u003e\u003cstrong\u003eSession\u003c/strong\u003e\u003c/td\u003e\n          \u003ctd\u003eSS 19 — \u003cem\u003eBEST of Physics\u003c/em\u003e\u003c/td\u003e\n      \u003c/tr\u003e\n      \u003ctr\u003e\n          \u003ctd\u003e\u003cstrong\u003eDate / Time\u003c/strong\u003e\u003c/td\u003e\n          \u003ctd\u003eSeptember 28, 2026 · 10:45 AM – 12:00 PM ET\u003c/td\u003e\n      \u003c/tr\u003e\n      \u003ctr\u003e\n          \u003ctd\u003e\u003cstrong\u003eVenue\u003c/strong\u003e\u003c/td\u003e\n          \u003ctd\u003eThomas M. Menino Convention \u0026amp; Exhibition Center, Boston, MA\u003c/td\u003e\n      \u003c/tr\u003e\n      \u003ctr\u003e\n          \u003ctd\u003e\u003cstrong\u003eFormat\u003c/strong\u003e\u003c/td\u003e\n          \u003ctd\u003e7-min oral + 3-min Q\u0026amp;A\u003c/td\u003e\n      \u003c/tr\u003e\n      \u003ctr\u003e\n          \u003ctd\u003e\u003cstrong\u003ePublication\u003c/strong\u003e\u003c/td\u003e\n          \u003ctd\u003e\u003ca href=\"https://www.redjournal.org\"\u003eRed Journal\u003c/a\u003e supplement\u003c/td\u003e\n      \u003c/tr\u003e\n  \u003c/tbody\u003e\n\u003c/table\u003e\n\u003ch2 id=\"authors\"\u003eAuthors\u003c/h2\u003e\n\u003cp\u003e\u003cstrong\u003eWookjin Choi\u003c/strong\u003e, Pradeep Bhetwal, Michael Dichmann, Yingcui Jia, Wenchao Cao, Danfu Liang, Yingxuan Chen, Adam Dicker, Yevgeniy Vinogradskiy\u003c/p\u003e","title":"Selected for ASTRO 2026 BEST of Physics — Oral Presentation in Boston"},{"content":"License: MIT · Python: 3.11+ · Version: 0.9.0 · Repo: choilab-jefferson/qradiomics\nActive successor for three earlier Choi Lab radiomics codebases. The C++/MATLAB pipelines in taznux/radiomics-tools, taznux/lung-image-analysis, and choilab-jefferson/LungCancerScreeningRadiomics are superseded by this repo. The feature extractors are now in qradiomics.feature.rtools (Python ITK port, numerically exact to the C++ binary). New work should land here.\nRadiomics research CLI. qr does two things equally well:\nAtomic tasks — convert DICOM, extract features, merge clinical, fit a model. Each is a single command, files in / files out. Workflow assembly — generate, mutate, scaffold, and run multi-step pipelines from those atomic tasks. Default executor is Nextflow (per-patient parallel + cache + HPC); Prefect is the secondary executor; inline is the small-cohort fallback. The canonical radiomics data flow has four stages — data → image → features → modeling — and one qr workflow plan call instantiates the whole chain:\n# Atomic tasks qr convert dicom-series / rtstruct / manifest-from-dir qr extract -m manifest.csv -p \u0026lt;pattern\u0026gt; -o features.csv qr results merge -f features.csv -c clinical.csv -o analysis_ready.csv qr analyze {survival,classify,importance} -i analysis_ready.csv ... qr ml {train,predict,evaluate} ... # Workflow assembly qr workflow plan -t dicom_to_ml -d \u0026lt;cohort\u0026gt; -c \u0026lt;clinical\u0026gt; -o plan.json qr workflow scaffold -p plan.json -e nextflow -o pipeline.nf qr workflow run plan.json --executor nextflow # default Kick-off Single backend (scripts/kickoff.sh) for both flows. It clones the repo (if not already), creates a .venv, pip install -e ., runs qr info, and runs the smoke tests.\nOne-liner install:\ncurl -sSL https://raw.githubusercontent.com/choilab-jefferson/qradiomics/main/scripts/kickoff.sh | bash Env knobs: QR_REPO_URL, QR_REPO_DIR, QR_BRANCH, QR_PYTHON, QR_VENV (set to - to skip the venv), QR_SKIP_SMOKE=1 to skip pytest.\nBackground — three earlier projects, unified qradiomics is the modern Python successor of three earlier Choi Lab radiomics codebases. The MATLAB pipelines, the ITK / Ruffus C++ tools, and the Docker-based screening workflow are distilled here into a single Click CLI built on PyRadiomics, scikit-learn, and lifelines:\nEarlier project Stack Role Status taznux/lung-image-analysis MATLAB · MIT LIDC-IDRI nodule detection / segmentation / characterization superseded taznux/radiomics-tools C++/Python (ITK, Ruffus) · MIT DICOM tools, GrowCut segmentation, feature extraction pipeline superseded choilab-jefferson/LungCancerScreeningRadiomics MATLAB / Python · GPL-3.0 LIDC + LUNGx end-to-end screening workflow with AutoML superseded (re-implemented under MIT using PyRadiomics) The AHSN shape descriptor pipeline (CMPB 2014) and the spiculation quantification pipeline (CMPB 2021, companion to choilab-jefferson/CIR) are re-integrated in qradiomics.shape. The longitudinal CBCT / delta-radiomics workflows (ASTRO / AAPM 2026) will be released here after publication.\nInstall pip install -e . # core CLI + library pip install -e .[rtstruct] # plus rt-utils for `qr convert rtstruct` Python 3.11 or newer is required. PyRadiomics, SimpleITK, lifelines, scikit-learn, statsmodels, scipy, and pandas are pulled in as dependencies.\nAfter install, qr, qradiomics, and qrdx are available on $PATH and point at qradiomics.cli.main:cli.\nDICOM Conversion Many TCIA cohorts ship as DICOM (CT/PET/MR series + RTSTRUCT). Two helpers convert into the NRRD form the rest of the pipeline consumes:\n# 1. CT/PET/MR DICOM series → single NRRD volume (PT auto-routes through SUV conversion) qr convert dicom-series \\ -i \u0026lt;dataset_root\u0026gt;/\u0026lt;patient\u0026gt;/\u0026lt;study\u0026gt;/CT/ \\ -o \u0026lt;out\u0026gt;/\u0026lt;patient\u0026gt;_CT.nrrd # 2. RTSTRUCT contour → binary label NRRD (same geometry as the reference CT) qr convert rtstruct \\ -d \u0026lt;dataset_root\u0026gt;/\u0026lt;patient\u0026gt;/\u0026lt;study\u0026gt;/CT/ \\ -r \u0026lt;dataset_root\u0026gt;/\u0026lt;patient\u0026gt;/\u0026lt;study\u0026gt;/RTSeries/RS.\u0026lt;uid\u0026gt;.dcm \\ --roi GTV \\ -o \u0026lt;out\u0026gt;/\u0026lt;patient\u0026gt;_GTV-label.nrrd # 3. (Optional) build a manifest by globbing image/mask pairs in a tree qr convert manifest-from-dir \\ -d \u0026lt;out\u0026gt;/ \\ --image-glob \u0026#39;*_CT.nrrd\u0026#39; \\ --mask-glob \u0026#39;*-label.nrrd\u0026#39; \\ -o manifest.csv RTSTRUCT conversion uses rt-utils (install via pip install qradiomics[rtstruct]). ROI lookup is case-insensitive. The mask is auto-reshaped to the CT geometry, with a ±1-slice z-axis trim/pad when the structure set references slices outside the series.\nEnd-to-end Example — TCIA NSCLC-Radiomics (Lung1) from scratch Starts from nothing — pulls DICOM straight from TCIA, converts, extracts, joins clinical, and reports the Cox PH ranking.\n# 0. One-time: install + workspace pip install -e .[rtstruct] export USER_DATA=/data/$USER # ≥ 30 GB free for Lung1 (~422 patients) mkdir -p $USER_DATA/{Lung1,Lung1-out} # 1. DICOM pull from TCIA qr tcia download \\ --collection NSCLC-Radiomics --modality CT \\ -o $USER_DATA/Lung1 -j 16 qr tcia download \\ --collection NSCLC-Radiomics --modality RTSTRUCT \\ -o $USER_DATA/Lung1 -j 16 # 2. DICOM → NRRD per patient: CT volume + GTV-1 binary mask for pat in $USER_DATA/Lung1/*/; do pid=$(basename \u0026#34;$pat\u0026#34;) qr convert dicom-series \\ -i \u0026#34;$pat\u0026#34;*/CT \\ -o \u0026#34;$USER_DATA/Lung1-out/${pid}_CT.nrrd\u0026#34; qr convert rtstruct \\ -d \u0026#34;$pat\u0026#34;*/CT \\ -r \u0026#34;$pat\u0026#34;*/RTSeries/*.dcm \\ --roi GTV-1 \\ -o \u0026#34;$USER_DATA/Lung1-out/${pid}_GTV-label.nrrd\u0026#34; done # 3. Manifest qr convert manifest-from-dir \\ -d \u0026#34;$USER_DATA/Lung1-out\u0026#34; \\ --image-glob \u0026#39;*_CT.nrrd\u0026#39; \\ --mask-glob \u0026#39;*_GTV-label.nrrd\u0026#39; \\ -o \u0026#34;$USER_DATA/Lung1-out/manifest.csv\u0026#34; # 4. Feature extraction (~1130 features per patient) qr extract \\ -m \u0026#34;$USER_DATA/Lung1-out/manifest.csv\u0026#34; \\ -p nsclc-survival \\ -o \u0026#34;$USER_DATA/Lung1-out/features.csv\u0026#34; # 5. Join clinical + Cox PH curl -sLo \u0026#34;$USER_DATA/Lung1-out/clinical.csv\u0026#34; \\ \u0026#34;https://www.cancerimagingarchive.net/wp-content/uploads/NSCLC-Radiomics-Lung1.clinical-version3-Oct-2019.csv\u0026#34; qr results merge \\ -f \u0026#34;$USER_DATA/Lung1-out/features.csv\u0026#34; \\ -c \u0026#34;$USER_DATA/Lung1-out/clinical.csv\u0026#34; \\ --clinical-id-col PatientID \\ --time-col Survival.time --event-col deadstatus.event \\ -o \u0026#34;$USER_DATA/Lung1-out/analysis_ready.csv\u0026#34; qr analyze survival \\ -i \u0026#34;$USER_DATA/Lung1-out/analysis_ready.csv\u0026#34; \\ --outcome OS_months --event OS_event \\ -o \u0026#34;$USER_DATA/Lung1-out/cox_results.csv\u0026#34; Expected outcome on Lung1 (≈ 420 patients): original_ngtdm_Busyness ranks at the top (HR ≈ 1.23, p \u0026lt; 1e-4), replicating the headline finding from the Aerts 2014 Nature Communications paper. A full run takes ≈ 1 h on a 16-core workstation. For a 5-patient smoke run on synthetic NRRD (no download required), see scripts/smoke.py.\nThe exact same sequence is bundled per cohort under pipelines/lung1/, pipelines/lidc_idri/, pipelines/nsclc_cetuximab/, and pipelines/acrin_heart/.\nDeployable Pipelines For each TCIA-public cohort, pipelines/ ships a ready-to-run bundle: plan.json + main.nf + prefect_flow.py + nextflow.config + deploy.sh. Run any cohort end-to-end with:\ncd pipelines/lung1/ cp /path/to/your/clinical.csv clinical/clinical.csv ./deploy.sh # nextflow (per-patient parallel, default) EXECUTOR=prefect ./deploy.sh # via Prefect 2.x EXECUTOR=inline ./deploy.sh # sequential subprocess (smoke tests) Available bundles: lung1/, nsclc_cetuximab/, lidc_idri/, acrin_heart/.\nWorkflow Assembly The canonical four-stage data flow is encoded in the template library that qr workflow plan draws from:\nTemplate Stages covered When to use nrrd_survival data → features → modeling cohort already in NRRD form dicom_survival data → image → features → modeling cohort ships as DICOM + RTSTRUCT dicom_to_ml data → image → features → modeling (ML) full end-to-end DICOM → trained model + CV metrics + held-out evaluation qr workflow plan -t dicom_to_ml \\ -d /data/cohort -c clinical.csv \\ --roi GTV --pattern nsclc-survival \\ -o plan.json qr workflow scaffold -p plan.json -e nextflow -o pipeline.nf qr workflow run plan.json The plan is plain JSON/YAML — agents can read, mutate, and re-run without re-templating.\nReproducibility — Published Paper Results Full report: reports/reproducibility.md · version 2.0 · last updated 2026-05-19\nAll results produced with qradiomics-public alone (no MATLAB, no Docker). Cohorts: TCIA NSCLC-Radiomics (Lung1), LIDC-IDRI (1,018 scans), LUNGx/SPIE-AAPM, CIRDataset (Zenodo 6762573).\nSummary Paper Cohort Method Our result Paper Verdict Aerts 2014 Lung1 (n=420) Cox PH 5-fold CV c-index 0.580 ± 0.029 0.65 ✓ within 0.07 Aerts 2014 — external Lung1 → NSCLC-Cetuximab (n=460) Aerts signature transfer c-index 0.562 0.69 ✓ signal transfers Choi 2014 CMPB — AHSN LIDC-IDRI 1,018 (33,108 candidates) AHSN + RF patient-grouped 5-fold AUC 0.727 ± 0.005 0.85–0.93 ✓ AHSN signal validated Choi 2018 Med Phys LIDC-IDRI 4,248 nodules radiomics50 AUC 0.872 ± 0.010 0.83–0.95 ✓ in range Choi 2021 CMPB — spic6 LIDC-IDRI 4,248 nodules spic6 (Np/Na/Nl/Na_att/s1/s2) AUC 0.816 ± 0.006 0.80–0.85 ✓✓ exact Choi 2021 CMPB — PM (CIR masks) LIDC-PM 72 patients, 474 nodules radiomics+spic AUC 0.868 ± 0.039 0.85 ✓✓ exceeds Choi 2021 CMPB — LUNGx ext + cal LUNGx 60-test + 10-cal radiomics50 CIR mask AUC 0.756 0.76 ✓✓ exact Choi 2022 MICCAI / CIRDataset LIDC-PM 72 + LUNGx 73 interpretable, no NN encoder AUC 0.755–0.868 0.813/0.743 ✓✓ matches/exceeds Three of four targeted Choi reproductions land at or above the paper\u0026rsquo;s published numbers using qradiomics-public\u0026rsquo;s atomic core and the CIRDataset masks.\nCohorts used Cohort Source Patients Nodules Note Lung1 / NSCLC-Radiomics TCIA 420 420 GTV-1 Aerts 2014 discovery cohort NSCLC-Cetuximab / RTOG-0617 local DICOM 489 PTV-based external for Aerts LIDC-IDRI (full reference) TCIA + LIDC-XML 1,018 4,248 (≥8 voxel) 7 institutions, 8 vendors LIDC-PM LIDC-IDRI subset 72 474 pathology-confirmed (CIR IDs) LUNGx / SPIE-AAPM-NCI TCIA + xlsx 74 91 1:1 size-matched benign/malignant CIRDataset (Zenodo 6762573) Choi/Dahiya/Nadeem 883 LIDC + 83 LUNGx 966 radiologist QA/QC\u0026rsquo;d paper-grade NRRD masks Choi 2018 Med Phys + Choi 2021 CMPB — detailed breakdown LIDC-IDRI malignancy ≥4 vs ≤2 binary classification. 5-fold patient-grouped CV.\nMethod Features n (RM) RM AUC PM AUC (XML mask) PM AUC (CIR mask) radiomics50 (Med Phys 2018) 1,409 → top-50 4,248 0.872 ± 0.010 0.748 ± 0.046 0.868 ± 0.039 spic6 (CMPB 2021) 6 4,248 0.816 ± 0.006 0.715 ± 0.059 0.831 ± 0.084 cmpb2021_size+spic 7 4,248 0.832 ± 0.021 0.727 ± 0.059 0.865 ± 0.051 radiomics+spic (union, top-50) 1,415 → top-50 4,248 0.867 ± 0.024 0.755 ± 0.046 0.868 ± 0.039 spic6 reproduces CMPB 2021 with very tight CI (0.816 ± 0.006 — paper midpoint, CI excludes both 0.80 and 0.83). With CIR paper-grade masks the LIDC-PM PM AUC reaches 0.868, exceeding the paper\u0026rsquo;s reported 0.85.\nChoi 2022 MICCAI / CIR — LUNGx external validation Train on LIDC RM (≥4 vs ≤2), domain-adapt on the LUNGx 10-patient CalibrationSet, test on the LUNGx 60-patient TestSet.\nMethod n train / cal / test AUC (no cal) AUC (ext + cal) radiomics50 (CIR mask) 4,248 / 10 / 73 0.725 0.756 radiomics+spic (CIR mask) 4,248 / 10 / 73 0.725 0.756 spic6 (CIR mask) 4,248 / 10 / 73 0.713 0.713 size_only (sanity) 4,248 / 10 / 73 ≤0.5 ≤0.5 This exactly matches the CMPB 2021 LUNGx external number (paper: 0.76) — reproduced using interpretable features only (no neural-network encoder). Note: LUNGx is 1:1 benign/malignant size-matched by design, nullifying size as a predictor and creating a large LIDC→LUNGx distribution shift. Without the 10-patient calibration step, radiomics50 drops to 0.725.\nLCSR port-vs-reference validation (shape module) qradiomics.shape.spiculation_from_voxel vs LCSR reference on the same CIRDataset input masks:\nCohort n Spearman ρ (qr_Na × lcsr_Na) Spearman ρ (qr_Nl × lcsr_Nl) LIDC 883 0.459 (p = 4×10⁻⁴⁷) 0.349 (p = 1×10⁻²⁶) LUNGx 83 0.653 (p = 2×10⁻¹¹) 0.370 (p = 6×10⁻⁴) For context, Choi 2021 reports ρ = 0.44 between spiculation count and radiologist spiculation score — our port-vs-LCSR ρ is in the same range. The qradiomics port runs in seconds per nodule (vs minutes for LCSR\u0026rsquo;s full cMCF+OMT C++ pipeline), making 1,018-patient cohort runs feasible on a single workstation.\nMethods harness pipelines/lidc_idri/methods_compare.py is a drop-in benchmark harness. Any feature-extraction method that produces a wide features CSV plugs in via a single line:\nMETHODS[\u0026#34;my_method\u0026#34;] = lambda df: [c for c in df.columns if c.startswith(\u0026#34;my_prefix_\u0026#34;)] The same RM / PM / LUNGx-cal / LUNGx-test splits and leakage-safe RF CV are applied automatically. Built-in methods: aerts4, radiomics50, spic6, cmpb2021_size+spic, radiomics+spic, shape_only, firstorder, size_only.\nValidated Cohorts Cohort Format on TCIA Conversion path NSCLC-Radiomics (LUNG1) DICOM CT + RTSTRUCT qr convert dicom-series + qr convert rtstruct --roi GTV-1 NSCLC-Cetuximab DICOM CT + RTSTRUCT qr convert dicom-series + qr convert rtstruct --roi PTV ACRIN-NSCLC-FDG-PET DICOM CT/PET + RTSTRUCT qr convert dicom-series + qr convert rtstruct --roi Heart Command Reference Command Stage Purpose qr tcia download data Bulk-download a TCIA collection (multi-process + progress) qr anonymize data Strip PHI from a DICOM tree (DICOM PS3.15 Annex E) qr convert dicom-series data/image DICOM CT/MR → NRRD; PT auto-routes through SUV conversion qr convert rtstruct data/image DICOM RTSTRUCT contour → label NRRD (case-insensitive ROI) qr convert manifest-from-dir data Glob image+mask pairs into a manifest CSV qr extract features PyRadiomics → features.csv (manifest + pattern) qr results merge features features.csv + clinical.csv → analysis_ready.csv qr analyze survival modeling Univariate Cox proportional hazards qr analyze classify modeling Univariate logistic regression qr analyze importance modeling Random-forest + permutation (+ optional SHAP) qr ml train modeling CV Cox / logistic + leakage-safe corr/univariate selection qr ml predict modeling Apply a trained model to new features qr ml evaluate modeling Hold-out evaluation report (c-index / AUC) qr workflow plan assembly Generate a multi-step plan from a template qr workflow show assembly Inspect a plan\u0026rsquo;s steps and variables qr workflow scaffold assembly Render a plan as shell / nextflow / prefect qr workflow run assembly Execute a plan (default executor: nextflow) qr pattern list / search meta Browse bundled pattern templates qr config get / set meta User preferences in ~/.qradiomics/config.yaml Python API — atomic core Every CLI command is a thin wrapper around a re-usable Python API. External libraries (e.g. longitudinal CBCT orchestrators) consume the atomic layer directly instead of shelling out.\nfrom qradiomics.atomic import ( load_image_and_mask, preprocess_pair, build_extractor, run_extractor, extract_features, register_pair, resample_to_fixed, histogram_match_hu, ) from qradiomics.data_model import ( Cohort, Patient, TreatmentCourse, Study, ImageSeries, RTStructureSet, ROI, AtomicUnit, Modality, StudyType, save_cohort, load_cohort, ) from qradiomics.manifest import flatten_cohort, read_manifest, write_manifest from qradiomics.delta import DeltaPair, compute_delta, compute_trend from qradiomics.io.dicom import read_pet_suv # Single atomic unit: one image, one mask → ≈1409 features image, mask = load_image_and_mask(\u0026#34;planCT.nrrd\u0026#34;, \u0026#34;Heart-label.nrrd\u0026#34;) cropped_img, cropped_msk = preprocess_pair(image, mask, pad_mm=20, resample_mm=1.0) extractor = build_extractor(image_types=[\u0026#34;Original\u0026#34;, \u0026#34;LoG\u0026#34;, \u0026#34;Wavelet\u0026#34;]) features = run_extractor(extractor, cropped_img, cropped_msk) Hierarchical cohort model qradiomics.data_model mirrors the canonical 5–6 level hierarchy used across the Choi-Lab ecosystem:\nCohort → Patient → TreatmentCourse → Study → ImageSeries / RTStructureSet → ROI (optional) Diagnostic-only cohorts omit TreatmentCourse and attach Study directly to Patient. flatten_cohort() walks the tree and produces a list of AtomicUnits — one per (image, mask) pair — which becomes the manifest CSV consumed by qr extract.\ncohort = Cohort(cohort_id=\u0026#34;lng-cbct\u0026#34;) patient = Patient(patient_id=\u0026#34;P001\u0026#34;) course = TreatmentCourse(course_id=\u0026#34;rt1\u0026#34;, fractions=30, prescription_dose_gy=60.0) study = Study(study_id=\u0026#34;S-week4\u0026#34;, timepoint=\u0026#34;week4\u0026#34;, relative_day=28) study.series[\u0026#34;CBCT\u0026#34;] = ImageSeries(series_id=\u0026#34;CBCT-w4\u0026#34;, image_path=\u0026#34;/data/CBCT_w4.nrrd\u0026#34;, modality=Modality.CBCT, image_tag=\u0026#34;CBCT-w4\u0026#34;) rs = RTStructureSet(rtstruct_id=\u0026#34;rs\u0026#34;, referenced_series_uid=\u0026#34;...\u0026#34;) rs.rois[\u0026#34;GTV\u0026#34;] = ROI(roi_id=\u0026#34;GTV\u0026#34;, mask_path=\u0026#34;/data/GTV-label.nrrd\u0026#34;, mask_tag=\u0026#34;manual\u0026#34;, mask_image_tag=\u0026#34;CBCT-w4\u0026#34;) study.structure_sets[\u0026#34;rs\u0026#34;] = rs course.studies[study.study_id] = study patient.treatment_courses[course.course_id] = course cohort.patients[patient.patient_id] = patient units = flatten_cohort(cohort) # list[AtomicUnit] write_manifest(units, \u0026#34;manifest.csv\u0026#34;) # canonical 10-column schema save_cohort(cohort, \u0026#34;cohort.yaml\u0026#34;) # full graph persistence Shape Analysis — qradiomics.shape Python re-implementations of two published Choi-Lab pipelines, used as a library (no CLI yet — call as functions):\n2014 CMPB — AHSN pulmonary nodule detection\nfrom qradiomics.shape import ( surface_elements, # Hessian eigendecomp + per-voxel normals (§2.2.1) detect_candidates, # Multi-scale Sato/Li dot enhancement (§2.2.2) ahsn, AHSNConfig, # Angular Histogram of Surface Normals (§2.3.1) wall_eliminate, # Iterative wall detection / elimination (§2.3.2) make, make_all, # Synthetic 3D lung phantoms for testing ) 2021 CMPB — Spiculation quantification (companion to CIR)\nfrom qradiomics.shape import ( voxel_to_mesh, # marching cubes → triangular mesh spherical_parameterization, # cotangent-Laplacian → unit sphere area_distortion, # per-vertex log-area distortion detect_peaks, # negative-distortion peaks = spike candidates spiculation_features, # Na / Nl / Na_att / s1 / s2 features spiculation_from_voxel, # one-shot mask → SpiculationFeatures ) See tests/shape/ for end-to-end usage on analytic shapes (sphere / spiked-sphere / phantoms).\nRepository Layout qradiomics/ ├── __init__.py # exposes PatternLoader, RadiomicsExtractor, __version__ ├── cli/ # Click CLI (qr / qradiomics / qrdx) │ ├── main.py │ ├── config_io.py │ ├── commands/ # extract, results, analyze, config_cmd │ └── pattern/ # list, match ├── atomic.py # load_image_and_mask, preprocess_pair, build/run_extractor ├── data_model.py # Cohort → Patient → TreatmentCourse → Study → Series → ROI ├── manifest.py # flatten_cohort, read/write_manifest ├── delta.py # DeltaPair, compute_delta, compute_trend ├── io/dicom.py # read_pet_suv ├── pattern_loader.py # YAML pattern templates → Pydantic models ├── extractor.py # PyRadiomics wrapper ├── shape/ # Published shape pipelines (re-implementation) │ ├── hessian.py # 2014 §2.2.1 — Hessian + surface elements │ ├── detection.py # 2014 §2.2.2 — multi-scale Sato/Li dot filter │ ├── ahsn.py # 2014 §2.3.1 — AHSN descriptor │ ├── wall_elim.py # 2014 §2.3.2 — iterative wall elimination │ ├── mesh_utils.py # 2021 — voxel → mesh + geometry primitives │ ├── spiculation.py # 2021 — spherical param + Na/Nl/Na_att/s1/s2 │ └── phantoms.py # Synthetic 3D lung phantoms for testing └── data/ ├── templates/ # pattern YAMLs (ct_default, nsclc_survival, ...) ├── pyradiomics/ # per-pattern PyRadiomics extractor configs └── schema/ # pattern-template JSON schema tests/ # pytest: analyze + results.merge (19 tests) LICENSE # MIT pyproject.toml Bundled Pattern Templates pattern_id Description ct-default Plain CT, single timepoint, multi image-type baseline standard-radiomics Multi-modality generic radiomics survival-analysis Cox + RSF + KM, time-to-event task nsclc-survival NSCLC CT GTV, LoG+Wavelet+Square/Sqrt/Log image types Drop a new *.yaml into qradiomics/data/templates/ to add a study; qr pattern list picks it up automatically.\nCiting If you use this CLI in published work, please cite the relevant upstream papers. PyRadiomics and the NSCLC-Radiomics cohort are the two essential citations for any qradiomics-derived feature analysis:\nPyRadiomics — van Griethuysen JJM, Fedorov A, Parmar C, et al. Computational Radiomics System to Decode the Radiographic Phenotype. Cancer Research 2017; 77(21):e104-e107. doi:10.1158/0008-5472.CAN-17-0339 NSCLC-Radiomics (TCIA LUNG1) — Aerts HJWL, Velazquez ER, Leijenaar RTH, et al. Decoding tumour phenotype by noninvasive imaging using a quantitative radiomics approach. Nature Communications 2014; 5:4006. doi:10.1038/ncomms5006 If you build on the lung-screening lineage that this CLI grew out of, please additionally cite:\nChoi W, Oh JH, Riyahi S, Liu C-J, Jiang F, Chen W, White C, Rimner A, Mechalakos JG, Deasy JO, Lu W. Radiomics analysis of pulmonary nodules in low-dose CT for early detection of lung cancer. Medical Physics 2018; 45(4):1537-1549. doi:10.1002/mp.12820 Choi W, Nadeem S, Riyahi S, Deasy JO, Tannenbaum A, Lu W. Reproducible and Interpretable Spiculation Quantification for Lung Cancer Screening. Computer Methods and Programs in Biomedicine 2021; 200:105839. doi:10.1016/j.cmpb.2020.105839 Choi WJ, Choi TS. Automated pulmonary nodule detection based on three-dimensional shape-based feature descriptor. Computer Methods and Programs in Biomedicine 2014; 113(1):37-54. doi:10.1016/j.cmpb.2013.08.015 Authors and Acknowledgements Wookjin Choi — overall architecture, CLI design, pattern templates Pradeep Bhetwal — survival analysis on the LUNG1 cohort Choi Lab, Department of Radiation Oncology, Sidney Kimmel Medical College at Thomas Jefferson University License MIT — see LICENSE.\n","permalink":"https://qradiomics.com/projects/2026-05-17-qradiomics/","summary":"\u003cp\u003e\u003cstrong\u003eLicense:\u003c/strong\u003e MIT · \u003cstrong\u003ePython:\u003c/strong\u003e 3.11+ · \u003cstrong\u003eVersion:\u003c/strong\u003e 0.9.0 · \u003cstrong\u003eRepo:\u003c/strong\u003e \u003ca href=\"https://github.com/choilab-jefferson/qradiomics\"\u003echoilab-jefferson/qradiomics\u003c/a\u003e\u003c/p\u003e\n\u003cblockquote\u003e\n\u003cp\u003e\u003cstrong\u003eActive successor for three earlier Choi Lab radiomics codebases.\u003c/strong\u003e The C++/MATLAB pipelines in\n\u003ca href=\"https://github.com/taznux/radiomics-tools\"\u003etaznux/radiomics-tools\u003c/a\u003e,\n\u003ca href=\"https://github.com/taznux/lung-image-analysis\"\u003etaznux/lung-image-analysis\u003c/a\u003e, and\n\u003ca href=\"https://github.com/choilab-jefferson/LungCancerScreeningRadiomics\"\u003echoilab-jefferson/LungCancerScreeningRadiomics\u003c/a\u003e\nare \u003cstrong\u003esuperseded\u003c/strong\u003e by this repo. The feature extractors are now in\n\u003ccode\u003eqradiomics.feature.rtools\u003c/code\u003e (Python ITK port, numerically exact to the C++ binary).\nNew work should land here.\u003c/p\u003e\u003c/blockquote\u003e\n\u003cp\u003eRadiomics research CLI. \u003ccode\u003eqr\u003c/code\u003e does two things equally well:\u003c/p\u003e\n\u003col\u003e\n\u003cli\u003e\u003cstrong\u003eAtomic tasks\u003c/strong\u003e — convert DICOM, extract features, merge clinical, fit a model. Each is a single command, files in / files out.\u003c/li\u003e\n\u003cli\u003e\u003cstrong\u003eWorkflow assembly\u003c/strong\u003e — generate, mutate, scaffold, and run multi-step pipelines from those atomic tasks. Default executor is \u003cstrong\u003eNextflow\u003c/strong\u003e (per-patient parallel + cache + HPC); \u003cstrong\u003ePrefect\u003c/strong\u003e is the secondary executor; \u003ccode\u003einline\u003c/code\u003e is the small-cohort fallback.\u003c/li\u003e\n\u003c/ol\u003e\n\u003cp\u003eThe canonical radiomics data flow has four stages — \u003ccode\u003edata → image → features → modeling\u003c/code\u003e — and one \u003ccode\u003eqr workflow plan\u003c/code\u003e call instantiates the whole chain:\u003c/p\u003e","title":"qradiomics — Radiomics Research CLI"},{"content":"https://datascience.nih.gov/tools-and-analytics/quantum-computing-new-frontiers-biomedical-research-innovation-lab\nLast December, I had the incredible opportunity to be part of something truly special. The NIH Office of Data Science Strategy (ODSS) and the National Cancer Institute (NCI) gathered 27 of us from wildly different fields for a five-day Innovation Lab. The goal? To answer a question that sounds like science fiction: How can quantum computing solve today\u0026rsquo;s most complex biomedical challenges?\nThe room buzzed with a vibrant mix of quantum physicists, computer scientists (both quantum and traditional computing), computational physicists, computational biologists, data scientists, and biomedical researchers. For five intense days, we were immersed in a whirlwind of collaboration, brainstorming, and problem-solving. The energy was electric as we united to bridge the gap between our disciplines and forge new paths for the future of medicine.\nTo catalyze our efforts, the NIH sponsored a challenge prize competition, dedicating $100,000 to the most promising projects developed during the lab. It wasn\u0026rsquo;t just about the funding; it was a powerful validation of the ideas born from this unique collaborative environment.\nOur Journey: Team Quantum Heart I am thrilled to announce that my team, Team Quantum Heart, was one of the three teams to receive the top prize of $25,000. Our project seeks to revolutionize the existing clinical decision-making framework by leveraging the unique strengths of quantum computing. It was a privilege to collaborate with the team:\nIman Borazjani, PhD, from Texas A\u0026amp;M University, Team leader\nWookjin Choi, PhD, from Sidney Kimmel Medical College at Thomas Jefferson University\nJiaqi (Jimmy) Leng, PhD, from the University of California, Berkeley\nZhenhua Jiang, PhD, from the University of Dayton Research Institute\nTogether, our diverse expertise in medical physics, AI, fluid simulations, and quantum algorithms allowed us to develop a concept we believe can make a real-world impact on patient care. This prize is not just an award; it\u0026rsquo;s the fuel that will help us propel our research forward.\nThe Road Ahead Leaving the Innovation Lab, I felt a profound sense of optimism. This event was more than just a competition; it was the formation of a new community. The connections made and the ideas sparked over those five days have laid the groundwork for years of future research.\nThe convergence of quantum computing and biomedical science is no longer a distant dream. It is happening now, and I am honored to be a part of it. On behalf of Team Quantum Heart, thank you to the NIH for this incredible opportunity.\n","permalink":"https://qradiomics.com/posts/2025-08-20-team-quantum-heart-wins-nih-prize-for-innovation/","summary":"\u003cp\u003e\u003ca href=\"https://datascience.nih.gov/tools-and-analytics/quantum-computing-new-frontiers-biomedical-research-innovation-lab\"\u003ehttps://datascience.nih.gov/tools-and-analytics/quantum-computing-new-frontiers-biomedical-research-innovation-lab\u003c/a\u003e\u003c/p\u003e\n\u003cp\u003eLast December, I had the incredible opportunity to be part of something truly special. The NIH Office of Data Science Strategy (ODSS) and the National Cancer Institute (NCI) gathered 27 of us from wildly different fields for a five-day Innovation Lab. The goal? To answer a question that sounds like science fiction: How can quantum computing solve today\u0026rsquo;s most complex biomedical challenges?\u003c/p\u003e\n\u003cp\u003eThe room buzzed with a vibrant mix of quantum physicists, computer scientists (both quantum and traditional computing), computational physicists, computational biologists, data scientists, and biomedical researchers. For five intense days, we were immersed in a whirlwind of collaboration, brainstorming, and problem-solving. The energy was electric as we united to bridge the gap between our disciplines and forge new paths for the future of medicine.\u003c/p\u003e","title":"Team Quantum Heart Wins NIH Prize for Innovation"},{"content":"I’m excited to share a new collaborative study I had the privilege of co-authoring, which was recently published in Nutrients. Led by Jefferson medical student Julia Logan, this work explores how large language models (LLMs) like ChatGPT and Gemini can deliver accessible, culturally sensitive dietary advice to cancer patients—many of whom lack access to professional nutritional counseling due to insurance limitations or socioeconomic barriers.\nWorking alongside colleagues from the Department of Radiation Oncology at Jefferson, we investigated whether AI tools could generate meal plans tailored to variables like location, budget, and cultural dietary preferences. While LLMs aren\u0026rsquo;t perfect, they showed surprising promise—providing personalized grocery lists and meal suggestions that, in many cases, aligned closely with professional dietitian recommendations.\nThis project highlights how AI, guided by clinician oversight, can serve as a scalable tool to reduce healthcare disparities and support cancer patients in managing their health more effectively.\n🔗 Read the full paper here\n","permalink":"https://qradiomics.com/posts/2025-04-08-empowering-cancer-care-with-ai-a-jefferson-medical-student-led-innovation/","summary":"\u003cp\u003eI’m excited to share a new collaborative study I had the privilege of co-authoring, which was recently published in \u003cem\u003eNutrients\u003c/em\u003e. Led by Jefferson medical student \u003cstrong\u003eJulia Logan\u003c/strong\u003e, this work explores how large language models (LLMs) like ChatGPT and Gemini can deliver accessible, culturally sensitive dietary advice to cancer patients—many of whom lack access to professional nutritional counseling due to insurance limitations or socioeconomic barriers.\u003c/p\u003e\n\u003cp\u003e\u003cimg loading=\"lazy\" src=\"/posts/2025-04-08-empowering-cancer-care-with-ai-a-jefferson-medical-student-led-innovation/images/image-5.png\"\u003e\u003c/p\u003e\n\u003cp\u003e\u003cimg alt=\"A schematic of LLM prompts designed to evaluate the dietary recommendations generated by ChatGPT and Gemini. A total of 31 zero-shot prompt templates with prompt variations within 8 categorical variables, including cancer stage, comorbidity, location, culture, age, dietary guideline, budget, and store, are shown. One variable was changed in each prompt. Seven of these prompts were selected (highlighted in gray) and four dietitians also responded to them.\" loading=\"lazy\" src=\"/posts/2025-04-08-empowering-cancer-care-with-ai-a-jefferson-medical-student-led-innovation/images/image-1.png\"\u003e\u003c/p\u003e","title":"Empowering Cancer Care with AI: A Jefferson Medical Student–Led Innovation"},{"content":"We’re excited to share our latest work published in Technology in Cancer Research \u0026amp; Treatment: “Deep Learning-Based Auto-Segmentation for Liver Yttrium-90 Selective Internal Radiation Therapy” — a collaboration between Jun Li, Rani Anne, and myself.\nThis study introduces a deep learning (DL) model built on the 3D U-Net architecture, developed to automatically segment the liver in CT scans for patients undergoing Y-90 Selective Internal Radiation Therapy (SIRT). Accurate liver segmentation is a critical step for calculating Y-90 dosage, traditionally done manually — a time-consuming and subjective process.\nOur DL-based pipeline:\nOutperformed Atlas-based methods (DSC: 0.94 vs. 0.83)\nAchieved near-perfect agreement in dose calculation (RA ~1.00)\nWas deployed clinically using a seamless DICOM workflow\nProcessed each case in under 2 minutes\nThis work demonstrates the clinical viability of AI-assisted planning in interventional radiology, particularly for liver-directed therapies.\n🔗 Read the full paper here\n","permalink":"https://qradiomics.com/posts/2025-04-08-ai-powered-auto-segmentation-in-liver-cancer-therapy/","summary":"\u003cp\u003eWe’re excited to share our latest work published in \u003cem\u003eTechnology in Cancer Research \u0026amp; Treatment\u003c/em\u003e: \u003cstrong\u003e“Deep Learning-Based Auto-Segmentation for Liver Yttrium-90 Selective Internal Radiation Therapy”\u003c/strong\u003e — a collaboration between Jun Li, Rani Anne, and myself.\u003c/p\u003e\n\u003cp\u003eThis study introduces a \u003cstrong\u003edeep learning (DL) model built on the 3D U-Net architecture\u003c/strong\u003e, developed to automatically segment the liver in CT scans for patients undergoing Y-90 Selective Internal Radiation Therapy (SIRT). Accurate liver segmentation is a critical step for calculating Y-90 dosage, traditionally done manually — a time-consuming and subjective process.\u003c/p\u003e","title":"AI-Powered Auto-Segmentation in Liver Cancer Therapy"},{"content":"Jefferson Investigates: Artificial Intelligence and Heart Disease — The Nexus\nhttps://medicalxpress.com/news/2024-06-machine-lung-cancer-scans-heart.html\n","permalink":"https://qradiomics.com/posts/2024-06-27-the-nexus-featured-our-cardiac-pet-radiomics-study/","summary":"\u003cp\u003e\u003ca href=\"https://nexus.jefferson.edu/science-and-technology/jefferson-investigates-artificial-intelligence-and-heart-disease-prenatal-drug-use-and-adhd-and-potassium-channels-and-neurological-disease/#lung-scans\"\u003eJefferson Investigates: Artificial Intelligence and Heart Disease — The Nexus\u003c/a\u003e\u003c/p\u003e\n\u003cp\u003e\u003cimg loading=\"lazy\" src=\"/posts/2024-06-27-the-nexus-featured-our-cardiac-pet-radiomics-study/images/image.png\"\u003e\u003c/p\u003e\n\u003cp\u003e\u003ca href=\"https://medicalxpress.com/news/2024-06-machine-lung-cancer-scans-heart.html\"\u003ehttps://medicalxpress.com/news/2024-06-machine-lung-cancer-scans-heart.html\u003c/a\u003e\u003c/p\u003e","title":"The Nexus featured our cardiac PET radiomics study"},{"content":"Our study on cardiac toxicity in lung cancer treatment is now featured in a JCO CCI editorial. Discoveries that could change patient care are on the horizon. Stay tuned! #CardiacToxicity#LungCancer#Innovation\nShining a Light: Unveiling Cardiac Risks Using Positron Emission Tomography Imaging in Lung Cancer Radiotherapy\n","permalink":"https://qradiomics.com/posts/2024-04-14-shining-a-light-unveiling-cardiac-risks-using-pet-imaging-in-lung-cancer-radiotherapy/","summary":"\u003cp\u003e\u003ca href=\"https://qradiomics.com/2023/09/11/novel-functional-delta-radiomics-for-predicting-overall-survival-in-lung-cancer-radiotherapy-using-cardiac-fdg-pet-uptake/\"\u003eOur study on cardiac toxicity in lung cancer treatment\u003c/a\u003e is now featured in a JCO CCI editorial. Discoveries that could change patient care are on the horizon. Stay tuned! \u003ca href=\"https://www.facebook.com/hashtag/cardiactoxicity?__eep__=6\u0026amp;__cft__%5B0%5D=AZVYuNlW1e31uhubkm-E3LkIOc41m_6ws0yeRNQoHoAAfTj9Hi9QyM7eqtYciuE7xVVbG3IeS9lMJZhc5vQuwAwe0Fl1ZEUTpwq3BaIuLOCTmwRfO-88Vg_sIQhl-_kK66nRPi2gNlTw28c-8Pz83HiJDqqdY9Q4k3WScrfQ5YYTpw\u0026amp;__tn__=*NK-R\"\u003e#CardiacToxicity\u003c/a\u003e\u003ca href=\"https://www.facebook.com/hashtag/lungcancer?__eep__=6\u0026amp;__cft__%5B0%5D=AZVYuNlW1e31uhubkm-E3LkIOc41m_6ws0yeRNQoHoAAfTj9Hi9QyM7eqtYciuE7xVVbG3IeS9lMJZhc5vQuwAwe0Fl1ZEUTpwq3BaIuLOCTmwRfO-88Vg_sIQhl-_kK66nRPi2gNlTw28c-8Pz83HiJDqqdY9Q4k3WScrfQ5YYTpw\u0026amp;__tn__=*NK-R\"\u003e#LungCancer\u003c/a\u003e\u003ca href=\"https://www.facebook.com/hashtag/innovation?__eep__=6\u0026amp;__cft__%5B0%5D=AZVYuNlW1e31uhubkm-E3LkIOc41m_6ws0yeRNQoHoAAfTj9Hi9QyM7eqtYciuE7xVVbG3IeS9lMJZhc5vQuwAwe0Fl1ZEUTpwq3BaIuLOCTmwRfO-88Vg_sIQhl-_kK66nRPi2gNlTw28c-8Pz83HiJDqqdY9Q4k3WScrfQ5YYTpw\u0026amp;__tn__=*NK-R\"\u003e#Innovation\u003c/a\u003e\u003c/p\u003e\n\u003cp\u003e\u003ca href=\"https://ascopubs.org/doi/10.1200/CCI.24.00045\"\u003e\u003cimg alt=\"Shining a Light: Unveiling Cardiac Risks Using Positron Emission Tomography Imaging in Lung Cancer Radiotherapy\" loading=\"lazy\" src=\"/posts/2024-04-14-shining-a-light-unveiling-cardiac-risks-using-pet-imaging-in-lung-cancer-radiotherapy/images/image.jpeg\"\u003e\u003c/a\u003e\u003c/p\u003e\n\u003cp\u003e\u003ca href=\"https://ascopubs.org/doi/10.1200/CCI.24.00045\"\u003eShining a Light: Unveiling Cardiac Risks Using Positron Emission Tomography Imaging in Lung Cancer Radiotherapy\u003c/a\u003e\u003c/p\u003e","title":"Shining a Light: Unveiling Cardiac Risks Using PET Imaging in Lung Cancer Radiotherapy"},{"content":"Maria Thor 1,4, Kelly Fitzgerald 2,4, Aditya Apte 1, Jung Hun Oh 1, Aditi Iyer 1, Otasowie Odiase 2, Saad Nadeem 1, Ellen D. Yorke 1, Jamie Chaft 3, Abraham J. Wu 2, Michael Offin 3, Charles B Simone II 2, Isabel Preeshagul 3, Daphna Y. Gelblum 2, Daniel Gomez 2, Joseph O. Deasy 1, Andreas Rimner 2\n1Department of Medical Physics, Memorial Sloan Kettering Cancer Center\n2Department of Radiation Oncology, Memorial Sloan Kettering Cancer Center\n3Department of Medicine, Memorial Sloan Kettering Cancer Center\nhttps://doi.org/10.1016/j.radonc.2023.109983\nThis paper examines the critical issue of identifying patients at risk of disease progression after SBRT treatment. The occurrence of disease progression in a significant percentage of cases highlights the necessity for improved predictive tools. In this context, the study utilizes an innovative approach by integrating spiculation as a crucial radiomics feature in the analysis. Spiculation, a visually apparent pattern in imaging, has gained recognition for its potential as a prognostic indicator. By utilizing spiculation alongside other radiomics features, this study seeks to improve the precision and dependability of forecasts related to progression-free survival among early-stage NSCLC patients after SBRT. Incorporating spiculation into the radiomics framework is a noteworthy advance toward more personalized and effective therapeutic approaches for this patient cohort.\nHighlights\nPre-treatment CT and PET features predict PFS to a larger extent than other non-image-based characteristics.\nA re-fitted model based on the two most published CT and PET features (SUVmax and tumor diameter) predicted PFS with high accuracy (AUC=0.78)\nThe performance of a model built on novel CT and PET features did not supersede that of the re-fitted model based on SUVmax and diameter (AUC=0.75)\n","permalink":"https://qradiomics.com/posts/2023-11-07-exploring-published-and-novel-pre-treatment-ct-and-pet-radiomics-to-stratify-risk-of-progression-among-early-stage-non-small-cell-lung-cancer-patients-treated-with-stereotactic-radiation/","summary":"\u003cp\u003eMaria Thor 1,4, Kelly Fitzgerald 2,4, Aditya Apte 1, Jung Hun Oh 1, Aditi Iyer 1, Otasowie Odiase 2, Saad Nadeem 1, Ellen D. Yorke 1, Jamie Chaft 3, Abraham J. Wu 2, Michael Offin 3, Charles B Simone II 2, Isabel Preeshagul 3, Daphna Y. Gelblum 2, Daniel Gomez 2, Joseph O. Deasy 1, Andreas Rimner 2\u003cbr\u003e\n1Department of Medical Physics, Memorial Sloan Kettering Cancer Center\u003cbr\u003e\n2Department of Radiation Oncology, Memorial Sloan Kettering Cancer Center\u003cbr\u003e\n3Department of Medicine, Memorial Sloan Kettering Cancer Center\u003c/p\u003e","title":"Exploring published and novel pre-treatment CT and PET radiomics to stratify risk of progression among early-stage non-small cell lung cancer patients treated with stereotactic radiation"},{"content":" AAPM 2023, ASTRO 2023\n","permalink":"https://qradiomics.com/posts/2023-10-07-deep-learning-segmentation-for-accurate-gtv-and-oar-segmentation-in-mr-guided-adaptive-radiotherapy-for-pancreatic-cancer-patients/","summary":"\u003cdiv class=\"slideshare-embed\" style=\"position:relative;padding-bottom:56.25%;height:0;margin:1rem 0;\"\u003e\n  \u003ciframe src=\"https://www.slideshare.net/slideshow/embed_code/260812562\"\n          width=\"595\" height=\"485\"\n          style=\"position:absolute;top:0;left:0;width:100%;height:100%;border:1px solid #CCC;\"\n          frameborder=\"0\" marginwidth=\"0\" marginheight=\"0\" scrolling=\"no\"\n          allowfullscreen\u003e\u003c/iframe\u003e\n\u003c/div\u003e\n\n\u003cdiv class=\"slideshare-embed\" style=\"position:relative;padding-bottom:56.25%;height:0;margin:1rem 0;\"\u003e\n  \u003ciframe src=\"https://www.slideshare.net/slideshow/embed_code/261888371\"\n          width=\"595\" height=\"485\"\n          style=\"position:absolute;top:0;left:0;width:100%;height:100%;border:1px solid #CCC;\"\n          frameborder=\"0\" marginwidth=\"0\" marginheight=\"0\" scrolling=\"no\"\n          allowfullscreen\u003e\u003c/iframe\u003e\n\u003c/div\u003e\n\n\u003cp\u003e\u003ca href=\"https://aapm.confex.com/aapm/2023am/meetingapp.cgi/Paper/3903\"\u003eAAPM 2023\u003c/a\u003e, \u003ca href=\"https://pubmed.ncbi.nlm.nih.gov/37785478/\"\u003eASTRO 2023\u003c/a\u003e\u003c/p\u003e","title":"Deep Learning Segmentation for Accurate GTV and OAR Segmentation in MR-Guided Adaptive Radiotherapy for Pancreatic Cancer Patients"},{"content":"Our paper “Novel Functional Radiomics for Prediction of Cardiac Positron Emission Tomography Avidity in Lung Cancer Radiotherapy” has been published in JCO CCI. This research work delves into an innovative approach to predict clinical cardiac assessment using functional imaging.\nNote: This post summarizes broader functional cardiac PET radiomics work. Only one related presentation below is specifically a delta-radiomics analysis.\nAbstract: Traditional methods for evaluating cardiotoxicity primarily focus on radiation doses to the heart. However, functional imaging offers the potential to enhance early prediction of cardiotoxicity in lung cancer patients undergoing radiotherapy. In this context, Fluorine-18 (18F) fluorodeoxyglucose (FDG)-positron emission tomography (PET)/computed tomography (CT) imaging plays a crucial role. This study aims to develop a radiomics model that predicts clinical cardiac assessment using 18F-FDG PET/CT scans before thoracic radiation therapy.\nKey Points: Purpose: To create a radiomics model for predicting clinical cardiac assessment based on 18F-FDG PET/CT scans.\nMethods: The study utilized pretreatment 18F-FDG PET/CT scans from three distinct study populations. These populations included two single-institutional protocols and one publicly available dataset.\nClinical Classification: A clinician classified the PET/CT scans according to clinical cardiac guidelines, categorizing them as no uptake, diffuse uptake, or focal uptake.\nHeart Delineation: The heart regions were delineated.\nNovel Radiomics Features: A total of 210 novel functional radiomics features were selected to characterize cardiac FDG uptake patterns.\nResults: The results showed that out of 202 scans, cardiac FDG uptake was scored as no uptake (39.6%), diffuse uptake (25.3%), and focal uptake (35.1%). The researchers reduced sixty-two independent radiomics features to nine clinically pertinent features. The best model showed a predictive accuracy of 93% in the training data set and 80% and 92% in two external validation data sets.\nConclusion: This study represents a significant advancement by developing and evaluating functional cardiac radiomic features from standard-of-care FDG PET/CT scans. The results demonstrate good predictive accuracy when compared to clinical imaging evaluation.\nFeel free to explore the full paper in the JCO Clinical Cancer Informatics, Volume 8, available at this link.\nRelated Presentations\nFunctional Delta-Radiomics Overall Survival Prediction (specific delta-radiomics study)\nFunctional Radiomics Classification of Cardiac Uptake Patterns\nhttps://www.abstractsonline.com/pp8/#!/10856/presentation/7201\n","permalink":"https://qradiomics.com/posts/2023-09-11-novel-functional-delta-radiomics-for-predicting-overall-survival-in-lung-cancer-radiotherapy-using-cardiac-fdg-pet-uptake/","summary":"\u003cp\u003eOur paper \u003cstrong\u003e“Novel Functional Radiomics for Prediction of Cardiac Positron Emission Tomography Avidity in Lung Cancer Radiotherapy”\u003c/strong\u003e has been published in \u003ca href=\"https://ascopubs.org/doi/10.1200/CCI.23.00241\"\u003eJCO CCI\u003c/a\u003e. This research work delves into an innovative approach to predict clinical cardiac assessment using functional imaging.\u003c/p\u003e\n\u003cblockquote\u003e\n\u003cp\u003eNote: This post summarizes broader \u003cstrong\u003efunctional cardiac PET radiomics\u003c/strong\u003e work. Only one related presentation below is specifically a \u003cstrong\u003edelta-radiomics\u003c/strong\u003e analysis.\u003c/p\u003e\u003c/blockquote\u003e\n\u003cp\u003e\u003cimg loading=\"lazy\" src=\"/posts/2023-09-11-novel-functional-delta-radiomics-for-predicting-overall-survival-in-lung-cancer-radiotherapy-using-cardiac-fdg-pet-uptake/images/image.png\"\u003e\u003c/p\u003e\n\u003cp\u003e\u003cimg loading=\"lazy\" src=\"/posts/2023-09-11-novel-functional-delta-radiomics-for-predicting-overall-survival-in-lung-cancer-radiotherapy-using-cardiac-fdg-pet-uptake/images/image-1.png\"\u003e\u003c/p\u003e\n\u003ch3 id=\"abstract\"\u003eAbstract:\u003c/h3\u003e\n\u003cp\u003eTraditional methods for evaluating cardiotoxicity primarily focus on radiation doses to the heart. However, functional imaging offers the potential to enhance early prediction of cardiotoxicity in lung cancer patients undergoing radiotherapy. In this context, \u003cstrong\u003eFluorine-18 (18F) fluorodeoxyglucose (FDG)-positron emission tomography (PET)/computed tomography (CT)\u003c/strong\u003e imaging plays a crucial role. This study aims to develop a radiomics model that predicts clinical cardiac assessment using 18F-FDG PET/CT scans before thoracic radiation therapy.\u003c/p\u003e","title":"Novel Functional Radiomics for Predicting Cardiotoxicity in Lung Cancer Radiotherapy using Cardiac FDG-PET Uptake"},{"content":" AAPM Annual Meeting (Houston, TX • July 23 ‒ 27, 2023)\nNovel Functional Delta-Radiomics for Predicting Overall Survival in Lung Cancer Radiotherapy Using Cardiac FDG-PET Uptake\nWookjin Choi, Yevgeniy Vinogradskiy\nInteractive ePoster Discussions: Sunday, July 23, 2023: 3:00 PM - 3:30 PM, GRBCC, Exhibit Hall | Forum 6\nSU-300-IePD-F6-4 Novel Functional Delta-Radiomics for Predicting Overall Survival in Lung Cancer Radiotherapy Using Cardiac FDG-PET Uptake\nDeep Learning Segmentation for Accurate GTV and OAR Segmentation in MR-Guided Adaptive Radiotherapy for Pancreatic Cancer Patients\nWookjin Choi, Hamidreza Nourzadeh, Yingxuan Chen, Christopher G. Ainsley, Vimal K. Desai, Alexander A. Kubli, Yevgeniy Vinogradskiy, Maria Werner-Wasik, Adam Mueller, and Karen E. Mooney\nPO-GePV-D-50 Deep Learning Segmentation for Accurate GTV and OAR Segmentation in MR-Guided Adaptive Radiotherapy for Pancreatic Cancer Patients\nAn MR-Conditional Motor for 1D Water Tank Measurements in an MR-Linac\nKaren E. Mooney, Sara A. Belko, Justin Williams, Andrew Gerry, Wookjin Choi, Maryellen Daley, and Robert S. Pugliese\nMO-345-IePD-F2-5 An MR-Conditional Motor for 1D Water Tank Measurements in an MR-Linac\nQuantitative Assessment of Dosimetric Effect of Using Alternative Spinalcord Delineation in Treatment Planning As Functions of Delineations, Setup Uncertainty, and Planning Techniques Using an Alternative Truth Assessment Method\nHashir Rashad, Abishek Karki, Jason Czak, Victor Gabriel Leandro Alves, Hamidreza Nourzadeh, Wookjin Choi, and Jeffrey V. Siebers\nMO-115-IePD-F5-6 Quantitative Assessment of Dosimetric Effect of Using Alternative Spinalcord Delineation in Treatment Planning As Functions of Delineations, Setup Uncertainty and Planning Techniques Using an Alternative Truth Assessment Method\nASTRO Annual Meeting (San Diego, CA • October 1 ‒ 4, 2023)\nNovel Functional Radiomics for Prediction of Cardiac PET Avidity in Lung Cancer Radiotherapy\nWookjin Choi, Yingcui Jia, Jennifer Kwak, Adam P. Dicker, Nicole L. Simone, Eugene Storozynsky, Varsha Jain, and Yevgeniy Vinogradskiy\nQuick Pitch Oral - QP 17b Phys 8: Outcome Prediction, October 3, 5:15PM-6:15PM\nhttps://pubmed.ncbi.nlm.nih.gov/37784390/\nNovel Deep Learning Segmentation Models for Accurate GTV and OAR Segmentation in MR-guided Adaptive Radiotherapy for Pancreatic Cancer Patients\nWookjin Choi, Hamidreza Nourzadeh, Yingxuan Chen, Christopher G. Ainsley, Vimal K. Desai, Alexander A. Kubli, Yevgeniy Vinogradskiy, Karen E. Mooney, Maria Werner-Wasik, and Adam Mueller\nPoster Viewing Q\u0026amp;A Session Time: Tuesday, October 3, 4:00 PM-5:00 PM\nhttps://pubmed.ncbi.nlm.nih.gov/37785478/\nDeep-learning based auto-segmentation for liver Yttrium-90 selective internal radiation therapy\nJun Li, Wookjin Choi, Pramila Rani Anne\nhttps://pubmed.ncbi.nlm.nih.gov/37786012/\nABS Annual Meeting (Vancouver, British Columbia, Canada • June 22 – 24, 2023)\nMulti-Center Investigation Of Inter-observer Variability Of A Novel Mobile CBCT Ring For Gynecological Cancer HDR Brachytherapy\nF Mourtada, A Ali, W Choi, R Anne, W Pinover, B Erickson, A Klopp, D Petereit, D Gaffney, E Fields, J Chino, C Yashar, M Kamrava, M Kollmeier, R Taleei, S Wan, Y Vinogradskiy\nhttps://www.sciencedirect.com/science/article/pii/S1538472123014964 INFORMS Annual Meeting (Phoenix, AZ • October 15 ‒ 18, 2023)\nArtificial Intelligence To Reduce Radiation-induced Cardiotoxicity In Lung Cancer Radiotherapy: A Novel Functional Radiomics Using Cardiac FDG-PET/CT\nWookjin Choi, Adam Dicker, Yevgeniy Vinogradskiy\nArtificial Intelligence to Reduce Radiation-Induced Cardiotoxicity in Lung Cancer Radiotherapy: A Novel Functional Radiomics Using Cardiac FDG-PET/CT (abstractsonline.com) ","permalink":"https://qradiomics.com/posts/2023-05-08-2023-accepted-invited-annual-meeting-abstracts/","summary":"\u003cul\u003e\n\u003cli\u003e\n\u003cp\u003eAAPM Annual Meeting (Houston, TX • July 23 ‒ 27, 2023)\u003c/p\u003e\n\u003col\u003e\n\u003cli\u003e\n\u003cp\u003eNovel Functional Delta-Radiomics for Predicting Overall Survival in Lung Cancer Radiotherapy Using Cardiac FDG-PET Uptake\u003cbr\u003e\n\u003cstrong\u003eWookjin Choi\u003c/strong\u003e, Yevgeniy Vinogradskiy\u003cbr\u003e\nInteractive ePoster Discussions: Sunday, July 23, 2023: 3:00 PM - 3:30 PM, GRBCC, Exhibit Hall | Forum 6\u003cbr\u003e\n\u003ca href=\"https://aapm.confex.com/aapm/2023am/meetingapp.cgi/Paper/2188\"\u003eSU-300-IePD-F6-4 Novel Functional Delta-Radiomics for Predicting Overall Survival in Lung Cancer Radiotherapy Using Cardiac FDG-PET Uptake\u003c/a\u003e\u003c/p\u003e\n\u003c/li\u003e\n\u003cli\u003e\n\u003cp\u003eDeep Learning Segmentation for Accurate GTV and OAR Segmentation in MR-Guided Adaptive Radiotherapy for Pancreatic Cancer Patients\u003cbr\u003e\n\u003cstrong\u003eWookjin Choi\u003c/strong\u003e, Hamidreza Nourzadeh, Yingxuan Chen, Christopher G. Ainsley, Vimal K. Desai, Alexander A. Kubli, Yevgeniy Vinogradskiy, Maria Werner-Wasik, Adam Mueller, and Karen E. Mooney\u003cbr\u003e\n\u003ca href=\"https://aapm.confex.com/aapm/2023am/meetingapp.cgi/Paper/3903\"\u003ePO-GePV-D-50 Deep Learning Segmentation for Accurate GTV and OAR Segmentation in MR-Guided Adaptive Radiotherapy for Pancreatic Cancer Patients\u003c/a\u003e\u003c/p\u003e","title":"2023 Accepted/Invited Annual Meeting abstracts"},{"content":"Varian will support my research project entitled \u0026ldquo;Longitudinal CBCT radiomics analysis for lung cancer radiotherapy response and prognosis prediction\u0026rdquo; with $230,000 over 2 years. This is the first research grant from Varian to the Department of Radiation Oncology, Sidney Kimmel Medical College at Thomas Jefferson University. This project can potentially impact the clinical practice of lung cancer patients by using standard imaging modalities (CBCT and 4D-CBCT) to provide early prediction of prognosis and toxicity.\nWe will develop Jefferson Whole Lung CBCT radiomics framework that provides comprehensive lung analysis for early prediction of local control and normal tissue toxicity during lung radiation therapy. This project will provide predictive models for treatment response and prognosis using structural, morphologic, and functional radiomic features acquired during treatment with Varian CBCT imaging, as well as a unique opportunity to combine Varian technology (4D CBCT) with novel image processing techniques to acquire functional images. This project will also include a clinical study of the novel 4D functional CBCT imaging technique.\nI am looking for a highly motivated postdoc to lead this project. If you are interested in working with us, please email me at \u0026ldquo;Wookjin.Choi@jefferson.edu.\u0026rdquo;\nUpdate — May 2026: A first results paper from this project has been selected for Oral Presentation in the BEST of Physics session at ASTRO 2026 (Boston, Sep 26–30). See Selected for ASTRO 2026 BEST of Physics — Oral Presentation in Boston for details.\n","permalink":"https://qradiomics.com/posts/2023-02-10-longitudinal-cbct-radiomics-in-lung-cancer-supported-by-varian-medical-systems-inc/","summary":"\u003cp\u003e\u003cstrong\u003eVarian\u003c/strong\u003e will support my research project entitled \u0026ldquo;\u003cstrong\u003eLongitudinal CBCT radiomics analysis for lung cancer radiotherapy response and prognosis prediction\u003c/strong\u003e\u0026rdquo; with $230,000 over 2 years. This is the first research grant from Varian to the Department of Radiation Oncology, Sidney Kimmel Medical College at Thomas Jefferson University. This project can potentially impact the clinical practice of lung cancer patients by using standard imaging modalities (CBCT and 4D-CBCT) to provide early prediction of prognosis and toxicity.\u003c/p\u003e","title":"Longitudinal CBCT radiomics in Lung Cancer supported by Varian Medical Systems Inc."},{"content":"MICCAI'22 Paper | CMPB'21 Paper | CIRDataset\nThis library serves as a one-stop solution for analyzing datasets using clinically-interpretable radiomics (CIR) in cancer imaging (https://github.com/choilab-jefferson/CIR). The primary motivation for this comes from our collaborators in radiology and radiation oncology inquiring about the importance of clinically-reported features in state-of-the-art deep learning malignancy/recurrence/treatment response prediction algorithms. Previous methods have performed such prediction tasks but without robust attribution to any clinically reported/actionable features (see extensive literature on the sensitivity of attribution methods to hyperparameters). This motivated us to curate datasets by annotating clinically-reported features at the voxel/vertex level on public datasets (using our published advanced mathematical algorithms) and relating these to prediction tasks (bypassing the “flaky” attribution schemes). With the release of these comprehensively-annotated datasets, we hope that previous malignancy prediction methods can also validate their explanations and provide clinically-actionable insights. We also provide strong end-to-end baselines for extracting these hard-to-compute clinically-reported features and using these in different prediction tasks.\nCIRDataset: A large-scale Dataset for Clinically-Interpretable lung nodule Radiomics and malignancy prediction [MICCAI'22] Wookjin Choi1, Navdeep Dahiya2, and Saad Nadeem3\n1 Department of Radiation Oncology, Thomas Jefferson University Hospital\n2 School of Electrical and Computer Engineering, Georgia Institute of Technology\n3 Department of Medical Physics, Memorial Sloan Kettering Cancer Center\nSpiculations/lobulations, and sharp/curved spikes on the surface of lung nodules, are good predictors of lung cancer malignancy and hence, are routinely assessed and reported by radiologists as part of the standardized Lung-RADS clinical scoring criteria. Given the 3D geometry of the nodule and 2D slice-by-slice assessment by radiologists, manual spiculation/lobulation annotation is a tedious task and thus no public datasets exist to date for probing the importance of these clinically-reported features in the SOTA malignancy prediction algorithms. As part of this paper, we release a large-scale Clinically-Interpretable Radiomics Dataset, CIRDataset, containing 956 radiologist QA/QC\u0026rsquo;ed spiculation/lobulation annotations on segmented lung nodules from two public datasets, LIDC-IDRI (N=883) and LUNGx (N=73). We also present an end-to-end deep learning model based on multi-class Voxel2Mesh extension to segment nodules (while preserving spikes), classify spikes (sharp/spiculation and curved/lobulation), and perform malignancy prediction. Previous methods have performed malignancy prediction for LIDC and LUNGx datasets but without robust attribution to any clinically reported/actionable features (due to known hyperparameter sensitivity issues with general attribution schemes). With the release of this comprehensively-annotated dataset and end-to-end deep learning baseline, we hope that malignancy prediction methods can validate their explanations, benchmark against our baseline, and provide clinically-actionable insights. Dataset, code and pre-trained models are available in this repository.\nDataset The first CIR dataset, released here, contains almost 1000 radiologist QA/QC’ed spiculation/lobulation annotations (computed using our published LungCancerScreeningRadiomics library and QA/QC\u0026rsquo;ed by a radiologist) on segmented lung nodules for two public datasets, LIDC (with visual radiologist malignancy RM scores for the entire cohort and pathology-proven malignancy PM labels for a subset) and LUNGx (with pathology-proven size-matched benign/malignant nodules to remove the effect of size on malignancy prediction).\nClinically-interpretable spiculation/lobulation annotation dataset samples; the first column - input CT image; the second column - overlaid semi-automated/QA/QC\u0026rsquo;ed contours and superimposed area distortion maps (for quantifying/classifying spikes, computed from spherical parameterization \u0026ndash; see our LungCancerScreeninigRadiomics Library); the third column - 3D mesh model with vertex classifications, red: spiculations, blue: lobulations, white: nodule base.\nEnd-to-End Deep Learning Nodule Segmentation, Spikes\u0026rsquo; Classification, and Malignancy Prediction Model We also release our multi-class Voxel2Mesh extension to provide a strong benchmark for end-to-end deep learning lung nodule segmentation, spikes’ classification (lobulation/spiculation), and malignancy prediction; Voxel2Mesh is the only published method to our knowledge that preserves sharp spikes during segmentation and hence its use as our base model. With the release of this comprehensively-annotated dataset, we hope that previous malignancy prediction methods can also validate their explanations/attributions and provide clinically-actionable insights. Users can also generate spiculation/lobulation annotations from scratch for LIDC/LUNGx as well as new datasets using our LungCancerScreeningRadiomics library.\nDepiction of end-to-end deep learning architecture based on multi-class Voxel2Mesh extension. The standard UNet based voxel encoder/decoder (top) extracts features from the input CT volumes while the mesh decoder deforms an initial spherical mesh into increasing finer resolution meshes matching the target shape. The mesh deformation utilizes feature vectors sampled from the voxel decoder through the Learned Neighborhood (LN) Sampling technique and also performs adaptive unpooling with increased vertex counts in high curvature areas. We extend the architecture by introducing extra mesh decoder layers for spiculation and lobulation classification. We also sample vertices (shape features) from the final mesh unpooling layer as input to Fully Connected malignancy prediction network. We optionally add deep voxel-features from the last voxel encoder layer to the malignancy prediction network\nResults The following tables show the expected results of running the pre-trained \u0026lsquo;Mesh Only\u0026rsquo; and \u0026lsquo;Mesh+Encoder\u0026rsquo; models.\nTable1. Nodule (Class0), spiculation (Class1), and lobulation (Class2) peak classification metrics\nTraining Network Chamfer Weighted Symmetric ↓ Jaccard Index ↑ Class0 Class1 Class2 Class0 Class1 Class2 Mesh Only 0.009 0.010 0.013 0.507 0.493 0.430 Mesh+Encoder 0.008 0.009 0.011 0.488 0.456 0.410 Validation Network Chamfer Weighted Symmetric ↓ Jaccard Index ↑ Class0 Class1 Class2 Class0 Class1 Class2 Mesh Only 0.010 0.011 0.014 0.526 0.502 0.451 Mesh+Encoder 0.014 0.015 0.018 0.488 0.472 0.433 Testing LIDC-PM N=72 Network Chamfer Weighted Symmetric ↓ Jaccard Index ↑ Class0 Class1 Class2 Class0 Class1 Class2 Mesh Only 0.011 0.011 0.014 0.561 0.553 0.510 Mesh+Encoder 0.009 0.010 0.012 0.558 0.541 0.507 Testing LUNGx N=73 Network Chamfer Weighted Symmetric ↓ Jaccard Index ↑ Class0 Class1 Class2 Class0 Class1 Class2 Mesh Only 0.029 0.028 0.030 0.502 0.537 0.545 Mesh+Encoder 0.017 0.017 0.019 0.506 0.523 0.525 Table 2. Malignancy prediction metrics.\nTraining Network AUC Accuracy Sensitivity Specificity F1 Mesh Only 0.885 80.25 54.84 93.04 65.03 Mesh+Encoder 0.899 80.71 55.76 93.27 65.94 Validation Network AUC Accuracy Sensitivity Specificity F1 Mesh Only 0.881 80.37 53.06 92.11 61.90 Mesh+Encoder 0.808 75.46 42.86 89.47 51.22 Testing LIDC-PM N=72 Network AUC Accuracy Sensitivity Specificity F1 Mesh Only 0.790 70.83 56.10 90.32 68.66 Mesh+Encoder 0.813 79.17 70.73 90.32 79.45 Testing LUNGx N=73 Network AUC Accuracy Sensitivity Specificity F1 Mesh Only 0.733 68.49 80.56 56.76 71.60 Mesh+Encoder 0.743 65.75 86.11 45.95 71.26 ","permalink":"https://qradiomics.com/posts/2022-06-29-clinically-interpretable-radiomics/","summary":"\u003cp\u003e\u003ca href=\"https://arxiv.org/pdf/2206.14903.pdf\"\u003eMICCAI'22 Paper\u003c/a\u003e | \u003ca href=\"https://arxiv.org/pdf/1808.08307.pdf\"\u003eCMPB'21 Paper\u003c/a\u003e | \u003ca href=\"https://zenodo.org/record/6762573\"\u003eCIRDataset\u003c/a\u003e\u003c/p\u003e\n\u003cp\u003eThis library serves as a one-stop solution for analyzing datasets using clinically-interpretable radiomics (CIR) in cancer imaging (\u003ca href=\"https://github.com/choilab-jefferson/CIR\"\u003ehttps://github.com/choilab-jefferson/CIR\u003c/a\u003e). The primary motivation for this comes from our collaborators in radiology and radiation oncology inquiring about the importance of clinically-reported features in state-of-the-art deep learning malignancy/recurrence/treatment response prediction algorithms. Previous methods have performed such prediction tasks but without robust attribution to any clinically reported/actionable features (see extensive literature on the sensitivity of attribution methods to hyperparameters). This motivated us to curate datasets by annotating clinically-reported features at the voxel/vertex level on public datasets (using our published \u003ca href=\"https://github.com/taznux/LungCancerScreeningRadiomics\"\u003eadvanced mathematical algorithms\u003c/a\u003e) and relating these to prediction tasks (bypassing the “flaky” attribution schemes). With the release of these comprehensively-annotated datasets, we hope that previous malignancy prediction methods can also validate their explanations and provide clinically-actionable insights. We also provide strong end-to-end baselines for extracting these hard-to-compute clinically-reported features and using these in different prediction tasks.\u003c/p\u003e","title":"Clinically-Interpretable Radiomics"},{"content":"Interpretable convolutional neural networks for survival prediction and pathway analysis applied to glioblastoma\nPathway image: Grid structure conversion for biological array data (a non-grid structured format) for CNNs. Interpretation of the CNN model using GradCAM. Source code: https://github.com/mskspi/PathCNN\nJung Hun Oh, Wookjin Choi, Euiseong Ko, Mingon Kang, Allen Tannenbaum, Joseph O Deasy, PathCNN: interpretable convolutional neural networks for survival prediction and pathway analysis applied to glioblastoma, Bioinformatics, Volume 37, Issue Supplement_1, July 2021, Pages i443–i450, https://doi.org/10.1093/bioinformatics/btab285\nModel Building\nPathCNN.py GradCAM\nPathCNN_GradCAM_modeling.py: to generate a model for GradCAM (PathCNN_model.h5) PathCNN_GradCAM.py: to generate GradCAM images and a resultant file (pathcnn_gradcam.csv) Multi-omics data\nGBM multi-omics data including mRNA expression, CNV, and DNA methylation were downloaded from the CBioPortal database. Pathway information was downloaded from the KEGG database. PCA was performed for each pathway in individual omics types. Five PCs in each omics type are in the following files:\nPCA_EXP.xlsx, PCA_CNV.xlsx, PCA_MT.xlsx Clinival variables are in the following file:\nClinical.xlsx ","permalink":"https://qradiomics.com/projects/2022-06-10-pathcnn/","summary":"\u003cp\u003eInterpretable convolutional neural networks for survival prediction and pathway analysis applied to glioblastoma\u003c/p\u003e\n\u003cul\u003e\n\u003cli\u003e\u003cem\u003ePathway image\u003c/em\u003e: Grid structure conversion for biological array data (a non-grid structured format) for CNNs.\u003c/li\u003e\n\u003cli\u003eInterpretation of the CNN model using GradCAM.\u003c/li\u003e\n\u003c/ul\u003e\n\u003cp\u003eSource code: \u003ca href=\"https://github.com/mskspi/PathCNN\"\u003ehttps://github.com/mskspi/PathCNN\u003c/a\u003e\u003c/p\u003e\n\u003cp\u003eJung Hun Oh, Wookjin Choi, Euiseong Ko, Mingon Kang, Allen Tannenbaum, Joseph O Deasy, PathCNN: interpretable convolutional neural networks for survival prediction and pathway analysis applied to glioblastoma, \u003cem\u003eBioinformatics\u003c/em\u003e, Volume 37, Issue Supplement_1, July 2021, Pages i443–i450, \u003ca href=\"https://doi.org/10.1093/bioinformatics/btab285\"\u003ehttps://doi.org/10.1093/bioinformatics/btab285\u003c/a\u003e\u003c/p\u003e","title":"PathCNN"},{"content":" ⚠️ This project is no longer maintained. It has been superseded by qradiomics, which provides a unified modern Python implementation.\nA comprehensive framework for lung cancer screening radiomics using LIDC-IDRI and LUNGx dataset.\nData preprocessing - download data, conversion, etc. Radiomics feature extraction including spiculation features AutoML model building and validation Source code https://github.com/taznux/LungCancerScreeningRadiomics\nWookjin Choi, Jung Hun Oh, Sadegh Riyahi, Chia-Ju Liu, Feng Jiang, Wengen Chen, Charles White, Andreas Rimner, James G. Mechalakos, Joseph O. Deasy, and Wei Lu, “Radiomics analysis of pulmonary nodules in low-dose CT for early detection of lung cancer”, Medical Physics, Vol. 45, No. 4, pp. 1537-1549, April 2018. https://doi.org/10.1002/mp.12820 Wookjin Choi, Saad Nadeem, Sadegh Riyahi, Joseph O. Deasy, Allen Tannenbaum, Wei Lu, “Reproducible and Interpretable Spiculation Quantification for Lung Cancer Screening.” Computer methods and programs in biomedicine. 200 2021. https://doi.org/10.1016/j.cmpb.2020.105839 ","permalink":"https://qradiomics.com/projects/2022-06-10-lung-cancer-screening-radiomics/","summary":"\u003cblockquote\u003e\n\u003cp\u003e⚠️ \u003cstrong\u003eThis project is no longer maintained.\u003c/strong\u003e It has been superseded by \u003ca href=\"/projects/2026-05-17-qradiomics/\"\u003eqradiomics\u003c/a\u003e, which provides a unified modern Python implementation.\u003c/p\u003e\u003c/blockquote\u003e\n\u003cp\u003eA comprehensive framework for lung cancer screening radiomics using LIDC-IDRI and LUNGx dataset.\u003c/p\u003e\n\u003cul\u003e\n\u003cli\u003eData preprocessing - download data, conversion, etc.\u003c/li\u003e\n\u003cli\u003eRadiomics feature extraction including spiculation features\u003c/li\u003e\n\u003cli\u003eAutoML model building and validation\u003c/li\u003e\n\u003c/ul\u003e\n\u003cp\u003eSource code \u003ca href=\"https://github.com/taznux/LungCancerScreeningRadiomics\"\u003ehttps://github.com/taznux/LungCancerScreeningRadiomics\u003c/a\u003e\u003c/p\u003e\n\u003col\u003e\n\u003cli\u003eWookjin Choi, Jung Hun Oh, Sadegh Riyahi, Chia-Ju Liu, Feng Jiang, Wengen Chen, Charles White, Andreas Rimner, James G. Mechalakos, Joseph O. Deasy, and Wei Lu, “Radiomics analysis of pulmonary nodules in low-dose CT for early detection of lung cancer”, Medical Physics, Vol. 45, No. 4, pp. 1537-1549, April 2018. \u003ca href=\"https://doi.org/10.1002/mp.12820\"\u003ehttps://doi.org/10.1002/mp.12820\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003eWookjin Choi, Saad Nadeem, Sadegh Riyahi, Joseph O. Deasy, Allen Tannenbaum, Wei Lu, “Reproducible and Interpretable Spiculation Quantification for Lung Cancer Screening.” Computer methods and programs in biomedicine. 200 2021. \u003ca href=\"https://doi.org/10.1016/j.cmpb.2020.105839\"\u003ehttps://doi.org/10.1016/j.cmpb.2020.105839\u003c/a\u003e\u003c/li\u003e\n\u003c/ol\u003e","title":"Lung Cancer Screening Radiomics"},{"content":"A comprehensive framework for lung cancer screening radiomics using LIDC-IDRI and LUNGx dataset.\nData preprocessing - download data, conversion, etc. Radiomics feature extraction including spiculation features AutoML model building and validation Source code https://github.com/choilab-jefferson/LungCancerScreeningRadiomics\nPublications Wookjin Choi, Jung Hun Oh, Sadegh Riyahi, Chia-Ju Liu, Feng Jiang, Wengen Chen, Charles White, Andreas Rimner, James G. Mechalakos, Joseph O. Deasy, and Wei Lu, “Radiomics analysis of pulmonary nodules in low-dose CT for early detection of lung cancer”, Medical Physics, Vol. 45, No. 4, pp. 1537-1549, April 2018. https://doi.org/10.1002/mp.12820 Wookjin Choi, Saad Nadeem, Sadegh Riyahi, Joseph O. Deasy, Allen Tannenbaum, Wei Lu, “Reproducible and Interpretable Spiculation Quantification for Lung Cancer Screening.” Computer methods and programs in biomedicine. 200 2021. https://doi.org/10.1016/j.cmpb.2020.105839 ","permalink":"https://qradiomics.com/posts/2022-06-08-lung-cancer-screening-radiomics/","summary":"\u003cp\u003eA comprehensive framework for lung cancer screening radiomics using LIDC-IDRI and LUNGx dataset.\u003c/p\u003e\n\u003cul\u003e\n\u003cli\u003eData preprocessing - download data, conversion, etc.\u003c/li\u003e\n\u003cli\u003eRadiomics feature extraction including spiculation features\u003c/li\u003e\n\u003cli\u003eAutoML model building and validation\u003c/li\u003e\n\u003c/ul\u003e\n\u003cp\u003eSource code \u003ca href=\"https://github.com/choilab-jefferson/LungCancerScreeningRadiomics\"\u003ehttps://github.com/choilab-jefferson/LungCancerScreeningRadiomics\u003c/a\u003e\u003c/p\u003e\n\u003ch3 id=\"publications\"\u003ePublications\u003c/h3\u003e\n\u003col\u003e\n\u003cli\u003eWookjin Choi, Jung Hun Oh, Sadegh Riyahi, Chia-Ju Liu, Feng Jiang, Wengen Chen, Charles White, Andreas Rimner, James G. Mechalakos, Joseph O. Deasy, and Wei Lu, “Radiomics analysis of pulmonary nodules in low-dose CT for early detection of lung cancer”, Medical Physics, Vol. 45, No. 4, pp. 1537-1549, April 2018. \u003ca href=\"https://doi.org/10.1002/mp.12820\"\u003ehttps://doi.org/10.1002/mp.12820\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003eWookjin Choi, Saad Nadeem, Sadegh Riyahi, Joseph O. Deasy, Allen Tannenbaum, Wei Lu, “Reproducible and Interpretable Spiculation Quantification for Lung Cancer Screening.” Computer methods and programs in biomedicine. 200 2021. \u003ca href=\"https://doi.org/10.1016/j.cmpb.2020.105839\"\u003ehttps://doi.org/10.1016/j.cmpb.2020.105839\u003c/a\u003e\u003c/li\u003e\n\u003c/ol\u003e","title":"Lung Cancer Screening Radiomics"},{"content":"Postdoctoral Fellow - Developing Clinically Interpretable Medical Imaging AI in Radiation Therapy https://recruit.jefferson.edu/psp/hcmp/EMPLOYEE/HRMS/c/HRS_HRAM_FL.HRS_CG_SEARCH_FL.GBL?Page=HRS_APP_JBPST_FL\u0026amp;Action=U\u0026amp;FOCUS=Applicant\u0026amp;SiteId=1\u0026amp;JobOpeningId=9272548\u0026amp;PostingSeq=1\nPI: Wookjin Choi, Ph.D. \u0026lt;Wookjin.Choi@jefferson.edu\u0026gt;\nAssistant Professor of Radiation Oncology, Thomas Jefferson University 2 Years Responsibilities POST-DOCTORAL POSITION, DEPARTMENT OF RADIATION ONCOLOGY: Thomas Jefferson University is now accepting applications for a post-doctoral fellow in the Department of Radiation Oncology with the Choi lab. The post-doctoral position is for developing AI techniques for image-guided radiation therapy and clinical outcome prediction and decision-making using radiomics, deep learning, and other computationally intensive techniques. Trainees must have the opportunity to carry out supervised biomedical research with the primary objective of developing or extending their research skills and knowledge in preparation for an independent research career.\nThis is an exciting opportunity to work on an emerging research project funded by Sidney Kimmel Cancer Center on the incorporation of medical imaging AI into radiation therapy and clinical care for cancer patients. The research focuses on the development of image analysis tools for cancer imaging, as well as clinically interpretable radiomics features and deep learning models for clinical outcome prediction and decision making. The post-doctoral fellow will have an opportunity to collaborate with Thomas Jefferson faculty, national and international collaborators, and work alongside investigators at the NCI Quantitative Imaging Network.\nThe entire Thomas Jefferson Medical Physics Division currently consists of 22 physicists and eight physics residents. The Jefferson physics faculty lead a highly-impactful and diverse research program. The group currently has ongoing funded projects by the National Cancer Institute, vendor-funded research, as well as Sidney Kimmel Cancer Center funding. System-wide equipment includes a ViewRay MRI-Linac, Varian TrueBeams, and Elekta Agility Linacs. The department has advanced scripting capabilities with multiple Radiation Oncology software packages including Mosaiq, Eclipse, and MIM Software.\nThomas Jefferson University is an Equal Opportunity Employer. Jefferson values diversity and encourages applications from women, members of minority groups, LGBTQ individuals, disabled individuals, and veterans. Applicants should forward a curriculum vitae and a statement of interest to the administrative assistant, Juli Johnson at julianne.johnson@jefferson.edu.\nQualifications Candidates must have a Ph.D. in Computer Science, Medical Physics, Physics, Mathematics, Electrical Engineering, Biomedical Engineering, or related field required. The ideal candidate will be highly interested in an academic Medical Physics career, have strong computational skills, and seek out a highly collaborative environment. Based on the interest of the post-doctoral fellow; opportunities will be provided to obtain clinical experience, treatment planning experience, as well as mentorship on clinical trial design and statistical modeling methods.\nConditions of Employment Covid Vaccination is a requirement for employment at Jefferson for employees working at Jefferson’s clinical entities or at the University. If you are not currently vac\n","permalink":"https://qradiomics.com/posts/2021-12-22-hiring-a-post-doctoral-fellow/","summary":"\u003ch4 id=\"postdoctoral-fellow---developing-clinically-interpretable-medical-imaging-ai-in-radiation-therapy\"\u003ePostdoctoral Fellow - Developing Clinically Interpretable Medical Imaging AI in Radiation Therapy\u003c/h4\u003e\n\u003cp\u003e\u003ca href=\"https://recruit.jefferson.edu/psp/hcmp/EMPLOYEE/HRMS/c/HRS\"\u003ehttps://recruit.jefferson.edu/psp/hcmp/EMPLOYEE/HRMS/c/HRS\u003c/a\u003e_HRAM_FL.HRS_CG_SEARCH_FL.GBL?Page=HRS_APP_JBPST_FL\u0026amp;Action=U\u0026amp;FOCUS=Applicant\u0026amp;SiteId=1\u0026amp;JobOpeningId=9272548\u0026amp;PostingSeq=1\u003c/p\u003e\n\u003cul\u003e\n\u003cli\u003ePI: Wookjin Choi, Ph.D. \u0026lt;\u003ca href=\"mailto:Wookjin.Choi@jefferson.edu\"\u003eWookjin.Choi@jefferson.edu\u003c/a\u003e\u0026gt;\u003cbr\u003e\nAssistant Professor of Radiation Oncology, Thomas Jefferson University\u003c/li\u003e\n\u003cli\u003e2 Years\u003c/li\u003e\n\u003c/ul\u003e\n\u003ch2 id=\"responsibilities\"\u003eResponsibilities\u003c/h2\u003e\n\u003cp\u003ePOST-DOCTORAL POSITION, DEPARTMENT OF RADIATION ONCOLOGY: Thomas Jefferson University is now accepting applications for a post-doctoral fellow in the Department of Radiation Oncology with the Choi lab.  The post-doctoral position is for developing AI techniques for image-guided radiation therapy and clinical outcome prediction and decision-making using radiomics, deep learning, and other computationally intensive techniques. Trainees must have the opportunity to carry out supervised biomedical research with the primary objective of developing or extending their research skills and knowledge in preparation for an independent research career.\u003c/p\u003e","title":"Hiring a Postdoctoral Fellow"},{"content":" ","permalink":"https://qradiomics.com/posts/2021-10-15-artificial-intelligence-in-radiation-oncology/","summary":"\u003cdiv class=\"slideshare-embed\" style=\"position:relative;padding-bottom:56.25%;height:0;margin:1rem 0;\"\u003e\n  \u003ciframe src=\"https://www.slideshare.net/slideshow/embed_code/254222500\"\n          width=\"595\" height=\"485\"\n          style=\"position:absolute;top:0;left:0;width:100%;height:100%;border:1px solid #CCC;\"\n          frameborder=\"0\" marginwidth=\"0\" marginheight=\"0\" scrolling=\"no\"\n          allowfullscreen\u003e\u003c/iframe\u003e\n\u003c/div\u003e\n\n\u003cdiv class=\"slideshare-embed\" style=\"position:relative;padding-bottom:56.25%;height:0;margin:1rem 0;\"\u003e\n  \u003ciframe src=\"https://www.slideshare.net/slideshow/embed_code/251348093\"\n          width=\"595\" height=\"485\"\n          style=\"position:absolute;top:0;left:0;width:100%;height:100%;border:1px solid #CCC;\"\n          frameborder=\"0\" marginwidth=\"0\" marginheight=\"0\" scrolling=\"no\"\n          allowfullscreen\u003e\u003c/iframe\u003e\n\u003c/div\u003e\n\n\u003cdiv class=\"slideshare-embed\" style=\"position:relative;padding-bottom:56.25%;height:0;margin:1rem 0;\"\u003e\n  \u003ciframe src=\"https://www.slideshare.net/slideshow/embed_code/250918971\"\n          width=\"595\" height=\"485\"\n          style=\"position:absolute;top:0;left:0;width:100%;height:100%;border:1px solid #CCC;\"\n          frameborder=\"0\" marginwidth=\"0\" marginheight=\"0\" scrolling=\"no\"\n          allowfullscreen\u003e\u003c/iframe\u003e\n\u003c/div\u003e\n\n\u003cdiv class=\"slideshare-embed\" style=\"position:relative;padding-bottom:56.25%;height:0;margin:1rem 0;\"\u003e\n  \u003ciframe src=\"https://www.slideshare.net/slideshow/embed_code/250324683\"\n          width=\"595\" height=\"485\"\n          style=\"position:absolute;top:0;left:0;width:100%;height:100%;border:1px solid #CCC;\"\n          frameborder=\"0\" marginwidth=\"0\" marginheight=\"0\" scrolling=\"no\"\n          allowfullscreen\u003e\u003c/iframe\u003e\n\u003c/div\u003e","title":"Artificial Intelligence in Radiation Oncology"},{"content":"Jung Hun Oh, Wookjin Choi, Euiseong Ko, Mingon Kang, Allen Tannenbaum, Joseph O Deasy\nThe authors wish it to be known that, in their opinion, Jung Hun Oh and Wookjin Choi should be regarded as Joint First Authors.\nhttps://academic.oup.com/bioinformatics/article/37/Supplement_1/i443/6319702\nhttps://github.com/mskspi/PathCNN/raw/main/img/pathcnn.png\nAn illustration of biological interpretation. (A) Grad-CAM procedure to generate class activation maps. The two images on the left bottom represent an example of the class activation maps for a sample in the cohort, which were generated from Grad-CAM procedure; (B) statistical analysis to identify significantly different pathways between the LTS and non-LTS groups. LTS, long-term survival; CNN, convolutional neural network; ReLU, rectified linear unit\nAbstract Motivation\nConvolutional neural networks (CNNs) have achieved great success in the areas of image processing and computer vision, handling grid-structured inputs and efficiently capturing local dependencies through multiple levels of abstraction. However, a lack of interpretability remains a key barrier to the adoption of deep neural networks, particularly in predictive modeling of disease outcomes. Moreover, because biological array data are generally represented in a non-grid structured format, CNNs cannot be applied directly.\nResults\nTo address these issues, we propose a novel method, called PathCNN, that constructs an interpretable CNN model on integrated multi-omics data using a newly defined pathway image. PathCNN showed promising predictive performance in differentiating between long-term survival (LTS) and non-LTS when applied to glioblastoma multiforme (GBM). The adoption of a visualization tool coupled with statistical analysis enabled the identification of plausible pathways associated with survival in GBM. In summary, PathCNN demonstrates that CNNs can be effectively applied to multi-omics data in an interpretable manner, resulting in promising predictive power while identifying key biological correlates of disease.Availability and implementation\nThe source code is freely available at: https://github.com/mskspi/PathCNN.\nhttps://www.youtube.com/watch?v=K0cuEp1ID0o\n","permalink":"https://qradiomics.com/posts/2021-07-22-pathcnn-interpretable-convolutional-neural-networks-for-survival-prediction-and-pathway-analysis-applied-to-glioblastoma/","summary":"\u003cp\u003eJung Hun Oh, Wookjin Choi, Euiseong Ko, Mingon Kang, Allen Tannenbaum, Joseph O Deasy\u003c/p\u003e\n\u003cp\u003eThe authors wish it to be known that, in their opinion, Jung Hun Oh and Wookjin Choi should be regarded as Joint First Authors.\u003c/p\u003e\n\u003cp\u003e\u003ca href=\"https://academic.oup.com/bioinformatics/article/37/Supplement_1/i443/6319702\"\u003ehttps://academic.oup.com/bioinformatics/article/37/Supplement_1/i443/6319702\u003c/a\u003e\u003c/p\u003e\n\u003cfigure\u003e\n\u003cp\u003e\u003ca href=\"https://github.com/mskspi/PathCNN/raw/main/img/pathcnn.png\"\u003ehttps://github.com/mskspi/PathCNN/raw/main/img/pathcnn.png\u003c/a\u003e\u003c/p\u003e\n\u003cfigcaption\u003e\n\u003cp\u003eAn illustration of biological interpretation. (\u003cstrong\u003eA\u003c/strong\u003e) Grad-CAM procedure to generate class activation maps. The two images on the left bottom represent an example of the class activation maps for a sample in the cohort, which were generated from Grad-CAM procedure; (\u003cstrong\u003eB\u003c/strong\u003e) statistical analysis to identify significantly different pathways between the LTS and non-LTS groups. LTS, long-term survival; CNN, convolutional neural network; ReLU, rectified linear unit\u003c/p\u003e","title":"PathCNN: interpretable convolutional neural networks for survival prediction and pathway analysis applied to glioblastoma"},{"content":"We won 4th place in the Artificial Intelligence (AI) Tracks at Sea Challenge. https://www.challenge.gov/?challenge=ai-tracks-at-sea\nThis national competition is organized by the U.S. Navy.\nVSU TrojanOne Team: Jose Diaz, Curtrell Trott, Advisor: Ju Wang, Wookjin Choi\nThe $200,000 prize was distributed among five winning teams, which submitted full working solutions, and three runners-up, which submitted partial working solutions. The monetary prize will be awarded to the school the corresponding team attends:\nTeams participating in the AI Tracks at Sea Challenge spanned collegiate institutions from east to west U.S. coasts, from both public and private colleges and universities. Collectively, the student submissions for the challenge represent various types of STEM research institutions, Ivy League Schools, Historically Black Colleges and Universities (HBCU) and Hispanic Serving Institutes (HSI). Of the challenge teams, 26% were comprised of students from HBCUs and 16% of the teams attend HSIs.\n“With 94% of the competitors attending colleges and universities outside of California, this challenge served as an avenue to make broader impacts in STEM,” said Yolanda Tanner, Naval Information Warfare Systems Command (NAVWAR) STEM Federal Action Officer and NIWC Pacific Internship and Fellowship project manager. “It was also a means by which students could further develop their STEM skills while working collaboratively to solve a real-world naval problem.”\nFlorida, North Carolina, and Texas had the largest population of participating collegiate teams.\nhttps://www.ccals.com/2021/03/16/vsu-team-takes-fourth-place-in-ai-tracks-at-sea-naval-challenge/\n","permalink":"https://qradiomics.com/posts/2021-02-01-fourth-place-winner-on-ai-tracks-at-sea-challenge/","summary":"\u003cp\u003eWe won 4th place in the Artificial Intelligence (AI) Tracks at Sea Challenge. \u003ca href=\"https://www.challenge.gov/?challenge=ai-tracks-at-sea\"\u003ehttps://www.challenge.gov/?challenge=ai-tracks-at-sea\u003c/a\u003e\u003cbr\u003e\nThis national competition is organized by the U.S. Navy.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eVSU TrojanOne\u003c/strong\u003e Team: Jose Diaz, Curtrell Trott, Advisor: Ju Wang, Wookjin Choi\u003c/p\u003e\n\u003cp\u003e\u003cimg loading=\"lazy\" src=\"/posts/2021-02-01-fourth-place-winner-on-ai-tracks-at-sea-challenge/images/image.jpeg\"\u003e\u003c/p\u003e\n\u003cp\u003eThe $200,000 prize was distributed among five winning teams, which submitted full working solutions, and three runners-up, which submitted partial working solutions. The monetary prize will be awarded to the school the corresponding team attends:\u003c/p\u003e","title":"Fourth place Winner on AI Tracks at Sea Challenge"},{"content":"Darrin Gladman, Jehu Osegbe, Wookjin Choi*, and Joon Suk Lee \u0026ldquo;Automatic motion tracking system for analysis of insect behavior\u0026rdquo;, Proc. SPIE 11510, Applications of Digital Image Processing XLIII, 115102W (21 August 2020); https://doi.org/10.1117/12.2568804\n*Corresponding author\nAbstract\nWe present a multi-object tracking system to track small insects such as ants and bees. Motion-based object tracking recognizes the movements of objects in videos using information extracted from the given video frames. We applied several computer vision techniques, such as blob detection and appearance matching, to track ants. Moreover, we discussed different object detection methodologies and investigated the various challenges of object detection, such as illumination variations and blob merge/split. The proposed system effectively tracked multiple objects in various environments.\n","permalink":"https://qradiomics.com/posts/2020-11-17-automatic-motion-tracking-system-for-analysis-of-insect-behavior/","summary":"\u003cp\u003eDarrin Gladman, Jehu Osegbe, Wookjin Choi*, and Joon Suk Lee \u0026ldquo;Automatic motion tracking system for analysis of insect behavior\u0026rdquo;, Proc. SPIE 11510, Applications of Digital Image Processing XLIII, 115102W (21 August 2020); \u003ca href=\"https://doi.org/10.1117/12.2568804\"\u003ehttps://doi.org/10.1117/12.2568804\u003c/a\u003e\u003c/p\u003e\n\u003cp\u003e*Corresponding author\u003c/p\u003e\n\u003cp\u003e\u003cimg loading=\"lazy\" src=\"/posts/2020-11-17-automatic-motion-tracking-system-for-analysis-of-insect-behavior/images/00289_psisdg11510_115102w_page_5_1.jpg\"\u003e\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eAbstract\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eWe present a multi-object tracking system to track small insects such as ants and bees. Motion-based object tracking recognizes the movements of objects in videos using information extracted from the given video frames. We applied several computer vision techniques, such as blob detection and appearance matching, to track ants. Moreover, we discussed different object detection methodologies and investigated the various challenges of object detection, such as illumination variations and blob merge/split. The proposed system effectively tracked multiple objects in various environments.\u003c/p\u003e","title":"Automatic motion tracking system for analysis of insect behavior"},{"content":"Choi, W., Nadeem, S., Alam, S. R., Deasy, J. O., Tannenbaum, A., \u0026amp; Lu, W. (2020). Reproducible and Interpretable Spiculation Quantification for Lung Cancer Screening. Computer Methods and Programs in Biomedicine, 105839. https://doi.org/10.1016/j.cmpb.2020.105839\nSource codes: https://github.com/choilab-jefferson/LungCancerScreeningRadiomics\nHighlights\nA novel interpretable spiculation feature is presented, computed using the area distortion metric from spherical conformal (angle-preserving) parameterization.\nA simple one-step feature and prediction model is introduced which only uses our interpretable features (size, spiculation, lobulation, vessel/wall attachment) and has the added advantage of using weak-labeled training data.\nA semi-automatic segmentation algorithm is also introduced for more accurate and reproducible lung nodule as well as vessel/wall attachment segmentation. This leads to more accurate spiculation quantification because the attachments can be excluded from spikes on the lung nodule surface (triangular mesh) data.\nUsing just our interpretable features (size, attachment, spiculation, lobulation), we were able to achieve AUC=0.82 on public Lung LIDC dataset and AUC=0.76 on public LUNGx dataset (the previous LUNGx best being AUC=0.68).\nState-of-the-art correlation is achieved between our spiculation score (the number of spiculations, Ns) and radiologists spiculation score (ρ = 0.44).\nAbstract\nSpiculations are important predictors of lung cancer malignancy, which are spikes on the surface of the pulmonary nodules. In this study, we proposed an interpretable and parameter-free technique to quantify the spiculation using area distortion metric obtained by the conformal (angle-preserving) spherical parameterization. We exploit the insight that for an angle-preserved spherical mapping of a given nodule, the corresponding negative area distortion precisely characterizes the spiculations on that nodule. We introduced novel spiculation scores based on the area distortion metric and spiculation measures. We also semi-automatically segment lung nodule (for reproducibility) as well as vessel and wall attachment to differentiate the real spiculations from lobulation and attachment. A simple pathological malignancy prediction model is also introduced. We used the publicly-available LIDC-IDRI dataset pathologists (strong-label) and radiologists (weak-label) ratings to train and test radiomics models containing this feature, and then externally validate the models. We achieved AUC = 0.80 and 0.76, respectively, with the models trained on the 811 weakly-labeled LIDC datasets and tested on the 72 strongly-labeled LIDC and 73 LUNGx datasets; the previous best model for LUNGx had AUC = 0.68. The number-of-spiculations feature was found to be highly correlated (Spearman’s rank correlation coefficient ) with the radiologists’ spiculation score. We developed a reproducible and interpretable, parameter-free technique for quantifying spiculations on nodules. The spiculation quantification measures was then applied to the radiomics framework for pathological malignancy prediction with reproducible semi-automatic segmentation of nodule. Using our interpretable features (size, attachment, spiculation, lobulation), we were able to achieve higher performance than previous models. In the future, we will exhaustively test our model for lung cancer screening in the clinic.\nhttps://qradiomics.com/2023/11/07/exploring-published-and-novel-pre-treatment-ct-and-pet-radiomics-to-stratify-risk-of-progression-among-early-stage-non-small-cell-lung-cancer-patients-treated-with-stereotactic-radiation/\n","permalink":"https://qradiomics.com/posts/2020-11-17-reproducible-and-interpretable-spiculation-quantification-for-lung-cancer-screening/","summary":"\u003cp\u003eChoi, W., Nadeem, S., Alam, S. R., Deasy, J. O., Tannenbaum, A., \u0026amp; Lu, W. (2020). Reproducible and Interpretable Spiculation Quantification for Lung Cancer Screening. \u003cem\u003eComputer Methods and Programs in Biomedicine\u003c/em\u003e, 105839. \u003ca href=\"https://doi.org/10.1016/j.cmpb.2020.105839\"\u003ehttps://doi.org/10.1016/j.cmpb.2020.105839\u003c/a\u003e\u003c/p\u003e\n\u003cp\u003eSource codes: \u003ca href=\"https://github.com/choilab-jefferson/LungCancerScreeningRadiomics\"\u003ehttps://github.com/choilab-jefferson/LungCancerScreeningRadiomics\u003c/a\u003e\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eHighlights\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003e\u003cimg loading=\"lazy\" src=\"/posts/2020-11-17-reproducible-and-interpretable-spiculation-quantification-for-lung-cancer-screening/images/1-s2.0-s0169260720316722-gr1_lrg.jpg\"\u003e\u003c/p\u003e\n\u003cul\u003e\n\u003cli\u003e\n\u003cp\u003eA novel interpretable spiculation feature is presented, computed using the area distortion metric from spherical conformal (angle-preserving) parameterization.\u003c/p\u003e\n\u003c/li\u003e\n\u003cli\u003e\n\u003cp\u003eA simple one-step feature and prediction model is introduced which only uses our interpretable features (size, spiculation, lobulation, vessel/wall attachment) and has the added advantage of using weak-labeled training data.\u003c/p\u003e","title":"Reproducible and Interpretable Spiculation Quantification for Lung Cancer Screening"},{"content":" The 2020 Joint AAPM | COMP Virtual Meeting\nhttps://w3.aapm.org/meetings/2020AM/programInfo/programAbs.php?sid=8490\u0026amp;aid=52949\n","permalink":"https://qradiomics.com/posts/2020-07-17-assessing-the-dosimetric-links-between-organ-at-risk-delineation-variability-and-treatment-planning-variability/","summary":"\u003cdiv class=\"slideshare-embed\" style=\"position:relative;padding-bottom:56.25%;height:0;margin:1rem 0;\"\u003e\n  \u003ciframe src=\"https://www.slideshare.net/slideshow/embed_code/237000959\"\n          width=\"595\" height=\"485\"\n          style=\"position:absolute;top:0;left:0;width:100%;height:100%;border:1px solid #CCC;\"\n          frameborder=\"0\" marginwidth=\"0\" marginheight=\"0\" scrolling=\"no\"\n          allowfullscreen\u003e\u003c/iframe\u003e\n\u003c/div\u003e\n\n\u003cp\u003eThe 2020 Joint AAPM | COMP Virtual Meeting\u003cbr\u003e\n\u003ca href=\"https://w3.aapm.org/meetings/2020AM/programInfo/programAbs.php?sid=8490\u0026amp;aid=52949\"\u003ehttps://w3.aapm.org/meetings/2020AM/programInfo/programAbs.php?sid=8490\u0026amp;aid=52949\u003c/a\u003e\u003c/p\u003e","title":"Assessing the Dosimetric Links between Organ-At-Risk Delineation Variability and Treatment Planning Variability"},{"content":" ","permalink":"https://qradiomics.com/posts/2019-11-03-quantitative-cancer-image-analysis/","summary":"\u003cdiv class=\"slideshare-embed\" style=\"position:relative;padding-bottom:56.25%;height:0;margin:1rem 0;\"\u003e\n  \u003ciframe src=\"https://www.slideshare.net/slideshow/embed_code/189820450\"\n          width=\"595\" height=\"485\"\n          style=\"position:absolute;top:0;left:0;width:100%;height:100%;border:1px solid #CCC;\"\n          frameborder=\"0\" marginwidth=\"0\" marginheight=\"0\" scrolling=\"no\"\n          allowfullscreen\u003e\u003c/iframe\u003e\n\u003c/div\u003e","title":"Quantitative Cancer Image Analysis"},{"content":" ","permalink":"https://qradiomics.com/posts/2019-07-18-simulation-of-realistic-organ-at-risk-delineation-variability-in-head-and-neck-radiation-therapy/","summary":"\u003cdiv class=\"slideshare-embed\" style=\"position:relative;padding-bottom:56.25%;height:0;margin:1rem 0;\"\u003e\n  \u003ciframe src=\"https://www.slideshare.net/slideshow/embed_code/156336028\"\n          width=\"595\" height=\"485\"\n          style=\"position:absolute;top:0;left:0;width:100%;height:100%;border:1px solid #CCC;\"\n          frameborder=\"0\" marginwidth=\"0\" marginheight=\"0\" scrolling=\"no\"\n          allowfullscreen\u003e\u003c/iframe\u003e\n\u003c/div\u003e","title":"Simulation of Realistic Organ-At-Risk Delineation Variability in Head and Neck Radiation Therapy"},{"content":" ","permalink":"https://qradiomics.com/posts/2018-10-01-radiomics-in-lung-cancer/","summary":"\u003cdiv class=\"slideshare-embed\" style=\"position:relative;padding-bottom:56.25%;height:0;margin:1rem 0;\"\u003e\n  \u003ciframe src=\"https://www.slideshare.net/slideshow/embed_code/117684751\"\n          width=\"595\" height=\"485\"\n          style=\"position:absolute;top:0;left:0;width:100%;height:100%;border:1px solid #CCC;\"\n          frameborder=\"0\" marginwidth=\"0\" marginheight=\"0\" scrolling=\"no\"\n          allowfullscreen\u003e\u003c/iframe\u003e\n\u003c/div\u003e","title":"Radiomics in Lung Cancer"},{"content":" UKC2018 Aug 4, 2018\nMSKCC Postdoctoral Research Symposium Sep 28, 2018\nhttps://twitter.com/arxiv_org/status/1034746650089021445\nPresented at MICCAI ShapeMI Workshop https://shapemi.github.io/program/\n","permalink":"https://qradiomics.com/posts/2018-09-11-interpretable-spiculation-quantification-for-lung-cancer-screening/","summary":"\u003cdiv class=\"slideshare-embed\" style=\"position:relative;padding-bottom:56.25%;height:0;margin:1rem 0;\"\u003e\n  \u003ciframe src=\"https://www.slideshare.net/slideshow/embed_code/108846563\"\n          width=\"595\" height=\"485\"\n          style=\"position:absolute;top:0;left:0;width:100%;height:100%;border:1px solid #CCC;\"\n          frameborder=\"0\" marginwidth=\"0\" marginheight=\"0\" scrolling=\"no\"\n          allowfullscreen\u003e\u003c/iframe\u003e\n\u003c/div\u003e\n\n\u003cp\u003eUKC2018 Aug 4, 2018\u003c/p\u003e\n\u003cdiv class=\"slideshare-embed\" style=\"position:relative;padding-bottom:56.25%;height:0;margin:1rem 0;\"\u003e\n  \u003ciframe src=\"https://www.slideshare.net/slideshow/embed_code/117014244\"\n          width=\"595\" height=\"485\"\n          style=\"position:absolute;top:0;left:0;width:100%;height:100%;border:1px solid #CCC;\"\n          frameborder=\"0\" marginwidth=\"0\" marginheight=\"0\" scrolling=\"no\"\n          allowfullscreen\u003e\u003c/iframe\u003e\n\u003c/div\u003e\n\n\u003cp\u003eMSKCC Postdoctoral Research Symposium Sep 28, 2018\u003c/p\u003e\n\u003cp\u003e\u003ca href=\"https://twitter.com/arxiv\"\u003ehttps://twitter.com/arxiv\u003c/a\u003e_org/status/1034746650089021445\u003c/p\u003e\n\u003cp\u003ePresented at MICCAI ShapeMI Workshop \u003ca href=\"https://shapemi.github.io/program/\"\u003ehttps://shapemi.github.io/program/\u003c/a\u003e\u003c/p\u003e","title":"Interpretable Spiculation Quantification for Lung Cancer Screening"},{"content":" Sep 17, 2018\nMay 21, 2018\n","permalink":"https://qradiomics.com/posts/2018-06-21-480/","summary":"\u003cdiv class=\"slideshare-embed\" style=\"position:relative;padding-bottom:56.25%;height:0;margin:1rem 0;\"\u003e\n  \u003ciframe src=\"https://www.slideshare.net/slideshow/embed_code/117684751\"\n          width=\"595\" height=\"485\"\n          style=\"position:absolute;top:0;left:0;width:100%;height:100%;border:1px solid #CCC;\"\n          frameborder=\"0\" marginwidth=\"0\" marginheight=\"0\" scrolling=\"no\"\n          allowfullscreen\u003e\u003c/iframe\u003e\n\u003c/div\u003e\n\n\u003cp\u003eSep 17, 2018\u003c/p\u003e\n\u003cdiv class=\"slideshare-embed\" style=\"position:relative;padding-bottom:56.25%;height:0;margin:1rem 0;\"\u003e\n  \u003ciframe src=\"https://www.slideshare.net/slideshow/embed_code/98787521\"\n          width=\"595\" height=\"485\"\n          style=\"position:absolute;top:0;left:0;width:100%;height:100%;border:1px solid #CCC;\"\n          frameborder=\"0\" marginwidth=\"0\" marginheight=\"0\" scrolling=\"no\"\n          allowfullscreen\u003e\u003c/iframe\u003e\n\u003c/div\u003e\n\n\u003cp\u003eMay 21, 2018\u003c/p\u003e","title":"Quantitative Image Analysis for Cancer Diagnosis and Radiation Therapy"},{"content":"KOCSEA Technical Symposium 2017, Invited Talk, KSEA Travel Grant\n","permalink":"https://qradiomics.com/posts/2017-11-12-radiomics-and-deep-learning-for-lung-cancer-screening/","summary":"\u003cp\u003eKOCSEA Technical Symposium 2017, Invited Talk, KSEA Travel Grant\u003c/p\u003e\n\u003cdiv class=\"slideshare-embed\" style=\"position:relative;padding-bottom:56.25%;height:0;margin:1rem 0;\"\u003e\n  \u003ciframe src=\"https://www.slideshare.net/slideshow/embed_code/81927502\"\n          width=\"595\" height=\"485\"\n          style=\"position:absolute;top:0;left:0;width:100%;height:100%;border:1px solid #CCC;\"\n          frameborder=\"0\" marginwidth=\"0\" marginheight=\"0\" scrolling=\"no\"\n          allowfullscreen\u003e\u003c/iframe\u003e\n\u003c/div\u003e","title":"Radiomics and Deep Learning for Lung Cancer Screening"},{"content":"2017 ASTRO annual meeting\nhttp://www.redjournal.org/article/S0360-3016(17)31540-7/fulltext\n","permalink":"https://qradiomics.com/posts/2017-10-02-robust-normal-lung-ct-texture-features-for-the-prediction-of-radiation-induced-lung-disease/","summary":"\u003cp\u003e2017 ASTRO annual meeting\u003c/p\u003e\n\u003cdiv class=\"slideshare-embed\" style=\"position:relative;padding-bottom:56.25%;height:0;margin:1rem 0;\"\u003e\n  \u003ciframe src=\"https://www.slideshare.net/slideshow/embed_code/80349716\"\n          width=\"595\" height=\"485\"\n          style=\"position:absolute;top:0;left:0;width:100%;height:100%;border:1px solid #CCC;\"\n          frameborder=\"0\" marginwidth=\"0\" marginheight=\"0\" scrolling=\"no\"\n          allowfullscreen\u003e\u003c/iframe\u003e\n\u003c/div\u003e\n\n\u003cdiv class=\"slideshare-embed\" style=\"position:relative;padding-bottom:56.25%;height:0;margin:1rem 0;\"\u003e\n  \u003ciframe src=\"https://www.slideshare.net/slideshow/embed_code/80349717\"\n          width=\"595\" height=\"485\"\n          style=\"position:absolute;top:0;left:0;width:100%;height:100%;border:1px solid #CCC;\"\n          frameborder=\"0\" marginwidth=\"0\" marginheight=\"0\" scrolling=\"no\"\n          allowfullscreen\u003e\u003c/iframe\u003e\n\u003c/div\u003e\n\n\u003cp\u003e\u003ca href=\"http://www.redjournal.org/article/S0360-3016(17)31540-7/fulltext\"\u003ehttp://www.redjournal.org/article/S0360-3016(17)31540-7/fulltext\u003c/a\u003e\u003c/p\u003e","title":"Robust Normal Lung CT Texture Features for the Prediction of Radiation-Induced Lung Disease"},{"content":"2017 AAPM annual meeting\nhttp://www.aapm.org/meetings/2017AM/PRAbs.asp?mid=127\u0026amp;aid=36486\n","permalink":"https://qradiomics.com/posts/2017-08-03-radiomics-analysis-of-pulmonary-nodules-in-low-dose-ct-for-early-detection-of-lung-cancer/","summary":"\u003cp\u003e2017 AAPM annual meeting\u003c/p\u003e\n\u003cdiv class=\"slideshare-embed\" style=\"position:relative;padding-bottom:56.25%;height:0;margin:1rem 0;\"\u003e\n  \u003ciframe src=\"https://www.slideshare.net/slideshow/embed_code/78325656\"\n          width=\"595\" height=\"485\"\n          style=\"position:absolute;top:0;left:0;width:100%;height:100%;border:1px solid #CCC;\"\n          frameborder=\"0\" marginwidth=\"0\" marginheight=\"0\" scrolling=\"no\"\n          allowfullscreen\u003e\u003c/iframe\u003e\n\u003c/div\u003e\n\n\u003cp\u003e\u003ca href=\"http://www.aapm.org/meetings/2017AM/PRAbs.asp?mid=127\u0026amp;aid=36486\"\u003ehttp://www.aapm.org/meetings/2017AM/PRAbs.asp?mid=127\u0026amp;aid=36486\u003c/a\u003e\u003c/p\u003e","title":"Radiomics Analysis of Pulmonary Nodules in Low Dose CT for Early Detection of Lung Cancer"},{"content":"This paper has been published in the Computational and Structural Biotechnology Journal.\nPreoperative 18F-FDG PET/CT and CT radiomics for identifying aggressive histopathological subtypes in early stage lung adenocarcinoma Wookjin Choi a d1, Chia-Ju Liu b 1, Sadegh Riyahi Alam a, Jung Hun Oh a, Raj Vaghjiani c, John Humm a, Wolfgang Weber b, Prasad S. Adusumilli c, Joseph O. Deasy a, Wei Lu a\na Department of Medical Physics, Memorial Sloan Kettering Cancer Center, New York, NY 10065, USA b Department of Radiology, Memorial Sloan Kettering Cancer Center, New York, NY 10065, USA c Department of Surgery, Memorial Sloan Kettering Cancer Center, New York, NY 10065, USA d Department of Radiation Oncology, Thomas Jefferson University, Philadelphia, PA 19107, USA\n1 Both authors equally contributed to this work.\nAbstract Lung adenocarcinoma (ADC) is the most common non-small cell lung cancer. Surgical resection is the primary treatment for early-stage lung ADC while lung-sparing surgery is an alternative for non-aggressive cases. Identifying histopathologic subtypes before surgery helps determine the optimal surgical approach. Predominantly solid or micropapillary (MIP) subtypes are aggressive and associated with a higher likelihood of recurrence and metastasis and lower survival rates. This study aims to non-invasively identify these aggressive subtypes using preoperative 18F-FDG PET/CT and diagnostic CT radiomics analysis. We retrospectively studied 119 patients with stage I lung ADC and tumors ≤ 2 cm, where 23 had aggressive subtypes (18 solid and 5 MIPs). Out of 214 radiomic features from the PET/CT and CT scans and 14 clinical parameters, 78 significant features (3 CT and 75 PET features) were identified through univariate analysis and hierarchical clustering with minimized feature collinearity. A combination of Support Vector Machine classifier and Least Absolute Shrinkage and Selection Operator built predictive models. Ten iterations of 10-fold cross-validation (10 ×10-fold CV) evaluated the model. A pair of texture feature (PET GLCM Correlation) and shape feature (CT Sphericity) emerged as the best predictor. The radiomics model significantly outperformed the conventional predictor SUVmax (accuracy: 83.5% vs. 74.7%, p = 9e-9) and identified aggressive subtypes by evaluating FDG uptake in the tumor and tumor shape. It also demonstrated a high negative predictive value of 95.6% compared to SUVmax (88.2%, p = 2e-10). The proposed radiomics approach could reduce unnecessary extensive surgeries for non-aggressive subtype patients, improving surgical decision-making for early-stage lung ADC patients.\nhttps://www.sciencedirect.com/science/article/pii/S2001037023004233\n2017 AAPM annual meeting\nhttp://www.aapm.org/meetings/2017AM/PRAbs.asp?mid=127\u0026amp;aid=37917\n","permalink":"https://qradiomics.com/posts/2017-08-01-aggressive-lung-adenocarcinoma-subtype-prediction-using-fdg-petct-radiomics/","summary":"\u003cp\u003eThis paper has been published in the Computational and Structural Biotechnology Journal.\u003c/p\u003e\n\u003ch2 id=\"preoperative-18f-fdg-petct-and-ct-radiomics-for-identifying-aggressive-histopathological-subtypes-in-early-stage-lung-adenocarcinoma\"\u003ePreoperative 18F-FDG PET/CT and CT radiomics for identifying aggressive histopathological subtypes in early stage lung adenocarcinoma\u003c/h2\u003e\n\u003cp\u003eWookjin Choi a d1, Chia-Ju Liu b 1, Sadegh Riyahi Alam a, Jung Hun Oh a, Raj Vaghjiani c, John Humm a, Wolfgang Weber b, Prasad S. Adusumilli c, Joseph O. Deasy a, Wei Lu a\u003c/p\u003e\n\u003cp\u003ea Department of Medical Physics, Memorial Sloan Kettering Cancer Center, New York, NY 10065, USA b Department of Radiology, Memorial Sloan Kettering Cancer Center, New York, NY 10065, USA c Department of Surgery, Memorial Sloan Kettering Cancer Center, New York, NY 10065, USA d Department of Radiation Oncology, Thomas Jefferson University, Philadelphia, PA 19107, USA\u003c/p\u003e","title":"Aggressive Lung Adenocarcinoma Subtype Prediction Using FDG-PET/CT Radiomics"},{"content":"2016 ASTRO annual meeting This poster has been selected for the ARRO poster walk (6 out of 250 physics posters).\nhttp://onlinelibrary.wiley.com/doi/10.1118/1.4963213/full\n","permalink":"https://qradiomics.com/posts/2016-09-21-individually-optimized-contrast-enhanced-4d-ct-for-radiotherapy-simulation-in-pancreatic-adenocarcinoma/","summary":"\u003cp\u003e2016 ASTRO annual meeting This poster has been selected for the ARRO poster walk (6 out of 250 physics posters).\u003c/p\u003e\n\u003cdiv class=\"slideshare-embed\" style=\"position:relative;padding-bottom:56.25%;height:0;margin:1rem 0;\"\u003e\n  \u003ciframe src=\"https://www.slideshare.net/slideshow/embed_code/66243409\"\n          width=\"595\" height=\"485\"\n          style=\"position:absolute;top:0;left:0;width:100%;height:100%;border:1px solid #CCC;\"\n          frameborder=\"0\" marginwidth=\"0\" marginheight=\"0\" scrolling=\"no\"\n          allowfullscreen\u003e\u003c/iframe\u003e\n\u003c/div\u003e\n\n\u003cp\u003e\u003ca href=\"http://onlinelibrary.wiley.com/doi/10.1118/1.4963213/full\"\u003ehttp://onlinelibrary.wiley.com/doi/10.1118/1.4963213/full\u003c/a\u003e\u003c/p\u003e","title":"Individually Optimized Contrast-Enhanced 4D-CT for Radiotherapy Simulation in Pancreatic Adenocarcinoma"},{"content":" ","permalink":"https://qradiomics.com/posts/2016-09-14-current-projects-sep-13-2016/","summary":"\u003cdiv class=\"slideshare-embed\" style=\"position:relative;padding-bottom:56.25%;height:0;margin:1rem 0;\"\u003e\n  \u003ciframe src=\"https://www.slideshare.net/slideshow/embed_code/66003783\"\n          width=\"595\" height=\"485\"\n          style=\"position:absolute;top:0;left:0;width:100%;height:100%;border:1px solid #CCC;\"\n          frameborder=\"0\" marginwidth=\"0\" marginheight=\"0\" scrolling=\"no\"\n          allowfullscreen\u003e\u003c/iframe\u003e\n\u003c/div\u003e","title":"Current Projects - Sep 13, 2016"},{"content":" ⚠️ This project is no longer maintained. It has been superseded by qradiomics, which provides a unified modern Python implementation.\nA basic framework for pulmonary nodule detection and characterization in CT https://github.com/taznux/lung-image-analysis\nTested on LIDC-IDRI dataset (https://wiki.cancerimagingarchive.net/display/Public/LIDC-IDRI)\nLIDC XML parsing Simple lung segmentation, nodule detection, and feature extraction algorithms Evaluation of nodule segmentation, detection, and characterization by LIDC XML annotations written in Matlab by Wookjin Choi and Ji-Seok Yoon\nThis framework is the essential parts of the following papers.\nWookjin Choi, Tae-Sun Choi, “Automated Pulmonary Nodule Detection based on Three-dimensional Shape-based Feature Descriptor”, Computer Methods and Programs in Biomedicine, Vol. 113, No. 1, January 2014, pp. 37–54, doi: http://dx.doi.org/10.1016/j.cmpb.2013.08.015 Wookjin Choi, Tae-Sun Choi, “Automated Pulmonary Nodule Detection System in Computed Tomography Images: A Hierarchical Block Classification Approach”, Entropy, Vol. 15, No. 2, pp. 507-523, February 2013, doi: http://dx.doi.org/10.3390/e15020507 Wookjin Choi, Tae-Sun Choi, “Genetic Programming-based feature transform and classification for the automatic detection of pulmonary nodules on computed tomography images”, Information Sciences, Vol. 212, pp. 57-78, December 2012, doi:http://dx.doi.org/10.1016/j.ins.2012.05.008 ","permalink":"https://qradiomics.com/projects/2016-08-27-lung-image-analysis-framwork/","summary":"\u003cblockquote\u003e\n\u003cp\u003e⚠️ \u003cstrong\u003eThis project is no longer maintained.\u003c/strong\u003e It has been superseded by \u003ca href=\"/projects/2026-05-17-qradiomics/\"\u003eqradiomics\u003c/a\u003e, which provides a unified modern Python implementation.\u003c/p\u003e\u003c/blockquote\u003e\n\u003cp\u003eA basic framework for pulmonary nodule detection and characterization in CT \u003ca href=\"https://github.com/taznux/lung-image-analysis\"\u003ehttps://github.com/taznux/lung-image-analysis\u003c/a\u003e\u003c/p\u003e\n\u003cp\u003eTested on LIDC-IDRI dataset (\u003ca href=\"https://wiki.cancerimagingarchive.net/display/Public/LIDC-IDRI\"\u003ehttps://wiki.cancerimagingarchive.net/display/Public/LIDC-IDRI\u003c/a\u003e)\u003c/p\u003e\n\u003cul\u003e\n\u003cli\u003eLIDC XML parsing\u003c/li\u003e\n\u003cli\u003eSimple lung segmentation, nodule detection, and feature extraction algorithms\u003c/li\u003e\n\u003cli\u003eEvaluation of nodule segmentation, detection, and characterization by LIDC XML annotations\u003c/li\u003e\n\u003c/ul\u003e\n\u003cp\u003ewritten in Matlab by Wookjin Choi and Ji-Seok Yoon\u003c/p\u003e\n\u003cp\u003e \u003c/p\u003e\n\u003cp\u003eThis framework is the essential parts of the following papers.\u003c/p\u003e","title":"Lung Image Analysis Framwork"},{"content":"2016 AAPM annual meeting\nhttp://onlinelibrary.wiley.com/doi/10.1118/1.4955803/abstract\n","permalink":"https://qradiomics.com/posts/2016-08-05-identification-of-robust-normal-lung-ct-texture-features-for-the-prediction-of-radiation-induced-lung-disease/","summary":"\u003cp\u003e2016 AAPM annual meeting\u003c/p\u003e\n\u003cdiv class=\"slideshare-embed\" style=\"position:relative;padding-bottom:56.25%;height:0;margin:1rem 0;\"\u003e\n  \u003ciframe src=\"https://www.slideshare.net/slideshow/embed_code/64719797\"\n          width=\"595\" height=\"485\"\n          style=\"position:absolute;top:0;left:0;width:100%;height:100%;border:1px solid #CCC;\"\n          frameborder=\"0\" marginwidth=\"0\" marginheight=\"0\" scrolling=\"no\"\n          allowfullscreen\u003e\u003c/iframe\u003e\n\u003c/div\u003e\n\n\u003cp\u003e\u003ca href=\"http://onlinelibrary.wiley.com/doi/10.1118/1.4955803/abstract\"\u003ehttp://onlinelibrary.wiley.com/doi/10.1118/1.4955803/abstract\u003c/a\u003e\u003c/p\u003e","title":"Identification of Robust Normal Lung CT Texture Features for the Prediction of Radiation-Induced Lung Disease"},{"content":"2016 AAPM annual meeting\nhttp://scitation.aip.org/content/aapm/journal/medphys/43/6/10.1118/1.4958261\n","permalink":"https://qradiomics.com/posts/2016-08-05-individually-optimized-contrast-enhanced-4d-ct-for-radiotherapy-simulation-in-pancreatic-ductal-adenocarcinoma/","summary":"\u003cp\u003e2016 AAPM annual meeting\u003c/p\u003e\n\u003cdiv class=\"slideshare-embed\" style=\"position:relative;padding-bottom:56.25%;height:0;margin:1rem 0;\"\u003e\n  \u003ciframe src=\"https://www.slideshare.net/slideshow/embed_code/64719798\"\n          width=\"595\" height=\"485\"\n          style=\"position:absolute;top:0;left:0;width:100%;height:100%;border:1px solid #CCC;\"\n          frameborder=\"0\" marginwidth=\"0\" marginheight=\"0\" scrolling=\"no\"\n          allowfullscreen\u003e\u003c/iframe\u003e\n\u003c/div\u003e\n\n\u003cp\u003e\u003ca href=\"http://scitation.aip.org/content/aapm/journal/medphys/43/6/10.1118/1.4958261\"\u003ehttp://scitation.aip.org/content/aapm/journal/medphys/43/6/10.1118/1.4958261\u003c/a\u003e\u003c/p\u003e\n\u003cdiv style=\"position: relative; padding-bottom: 56.25%; height: 0; overflow: hidden;\"\u003e\n      \u003ciframe allow=\"accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture; web-share; fullscreen\" loading=\"eager\" referrerpolicy=\"strict-origin-when-cross-origin\" src=\"https://www.youtube.com/embed/Vo1IBDz3DBs?autoplay=0\u0026amp;controls=1\u0026amp;end=0\u0026amp;loop=0\u0026amp;mute=0\u0026amp;start=0\" style=\"position: absolute; top: 0; left: 0; width: 100%; height: 100%; border:0;\" title=\"YouTube video\"\u003e\u003c/iframe\u003e\n    \u003c/div\u003e","title":"Individually Optimized Contrast-Enhanced 4D-CT for Radiotherapy Simulation in Pancreatic Ductal Adenocarcinoma"},{"content":"This video clip shows how to estimate peak enhancement time by using the test injection technique.\nW Choi et al. Individually Optimized Contrast-Enhanced 4D-CT for Radiotherapy Simulation in Pancreatic Ductal Adenocarcinoma http://onlinelibrary.wiley.com/doi/10.1118/1.4963213/full\nhttps://youtu.be/Vo1IBDz3DBs\n","permalink":"https://qradiomics.com/posts/2016-08-05-estimate-peak-enhancement-time/","summary":"\u003cp\u003eThis video clip shows how to estimate peak enhancement time by using the test injection technique.\u003c/p\u003e\n\u003cp\u003eW Choi et al. Individually Optimized Contrast-Enhanced 4D-CT for Radiotherapy Simulation in Pancreatic Ductal Adenocarcinoma \u003ca href=\"http://onlinelibrary.wiley.com/doi/10.1118/1.4963213/full\"\u003ehttp://onlinelibrary.wiley.com/doi/10.1118/1.4963213/full\u003c/a\u003e\u003c/p\u003e\n\u003cp\u003e\u003ca href=\"https://youtu.be/Vo1IBDz3DBs\"\u003ehttps://youtu.be/Vo1IBDz3DBs\u003c/a\u003e\u003c/p\u003e","title":"How to estimate peak enhancement time of pancreas region by test injection with a ROI in aorta"},{"content":" ⚠️ This project is no longer maintained. It has been superseded by qradiomics, which provides a unified modern Python implementation.\nImage processing tools and ruffus based pipeline for radiomics feature analysis\nGithub repository\nhttps://github.com/taznux/radiomics-tools/ First release 0.1 with OSX binary\nhttps://github.com/taznux/radiomics-tools/releases/tag/release/0.1 Test dataset - https://wiki.cancerimagingarchive.net/display/Public/SPIE-AAPM+Lung+CT+Challenge Publications\nWookjin Choi, Jung Hun Oh, Sadegh Riyahi, Chia-Ju Liu, Feng Jiang, Wengen Chen, Charles White, Andreas Rimner, James G. Mechalakos, Joseph O. Deasy, and Wei Lu, “Radiomics analysis of pulmonary nodules in low-dose CT for early detection of lung cancer”, Medical Physics, Vol. 45, No. 4, pp. 1537-1549, April 2018. https://doi.org/10.1002/mp.12820 Wookjin Choi, Sadegh Riyahi, Seth J. Kligerman, Chia-Ju Liu, James G. Mechalakos and Wei Lu, “Technical Note: Identification of Normal Lung CT Texture Features Robust to Tumor Size for the Prediction of Radiation-Induced Lung Disease”, International Journal of Medical Physics, Clinical Engineering and Radiation Oncology, Vol.7 No.3, Paper ID 86485, pp. 330-338, August 2018. doi:10.4236/ijmpcero.2018.73027 Sadegh Riyahi, Wookjin Choi, Chia-Ju Liu, Hualiang Zhong, Abraham J Wu, James G Mechalakos, Wei Lu, “Quantifying local tumor morphological changes with Jacobian map for prediction of pathologic tumor response to chemo-radiotherapy in locally advanced esophageal cancer”, Physics in Medicine and Biology, Vol. 63, No. 14, 145020 (13pp), July 2018. doi:10.1088/1361-6560/aacd22 ","permalink":"https://qradiomics.com/projects/2016-07-23-radiomics-tools/","summary":"\u003cblockquote\u003e\n\u003cp\u003e⚠️ \u003cstrong\u003eThis project is no longer maintained.\u003c/strong\u003e It has been superseded by \u003ca href=\"/projects/2026-05-17-qradiomics/\"\u003eqradiomics\u003c/a\u003e, which provides a unified modern Python implementation.\u003c/p\u003e\u003c/blockquote\u003e\n\u003cp\u003eImage processing tools and \u003ca href=\"http://www.ruffus.org.uk/\"\u003eruffus\u003c/a\u003e based pipeline for radiomics feature analysis\u003c/p\u003e\n\u003cul\u003e\n\u003cli\u003eGithub repository\u003cbr\u003e\n\u003ca href=\"https://github.com/taznux/radiomics-tools/\"\u003ehttps://github.com/taznux/radiomics-tools/\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003eFirst release 0.1 with OSX binary\u003cbr\u003e\n\u003ca href=\"https://github.com/taznux/radiomics-tools/releases/tag/release/0.1\"\u003ehttps://github.com/taznux/radiomics-tools/releases/tag/release/0.1\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003eTest dataset -\n\u003ca href=\"https://wiki.cancerimagingarchive.net/display/Public/SPIE-AAPM+Lung+CT+Challenge\"\u003ehttps://wiki.cancerimagingarchive.net/display/Public/SPIE-AAPM+Lung+CT+Challenge\u003c/a\u003e\u003c/li\u003e\n\u003c/ul\u003e\n\u003cp\u003ePublications\u003c/p\u003e\n\u003col\u003e\n\u003cli\u003e\u003cstrong\u003eWookjin Choi\u003c/strong\u003e, Jung Hun Oh, Sadegh Riyahi, Chia-Ju Liu, Feng Jiang, Wengen Chen, Charles White, Andreas Rimner, James G. Mechalakos, Joseph O. Deasy, and Wei Lu, “Radiomics analysis of pulmonary nodules in low-dose CT for early detection of lung cancer”, Medical Physics, Vol. 45, No. 4, pp. 1537-1549, April 2018. \u003ca href=\"https://doi.org/10.1002/mp.12820\"\u003ehttps://doi.org/10.1002/mp.12820\u003c/a\u003e \u003c/li\u003e\n\u003cli\u003e\u003cstrong\u003eWookjin Choi\u003c/strong\u003e, Sadegh Riyahi, Seth J. Kligerman, Chia-Ju Liu, James G. Mechalakos and Wei Lu, “Technical Note: Identification of Normal Lung CT Texture Features Robust to Tumor Size for the Prediction of Radiation-Induced Lung Disease”, International Journal of Medical Physics, Clinical Engineering and Radiation Oncology, Vol.7 No.3, Paper ID 86485, pp. 330-338, August 2018. \u003ca href=\"https://doi.org/10.1016/j.ins.2012.05.008\"\u003edoi:\u003c/a\u003e\u003ca href=\"https://doi.org/10.4236/ijmpcero.2018.73027\"\u003e10.4236/ijmpcero.2018.73027\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003eSadegh Riyahi, \u003cstrong\u003eWookjin Choi\u003c/strong\u003e, Chia-Ju Liu, Hualiang Zhong, Abraham J Wu, James G Mechalakos, Wei Lu, “Quantifying local tumor morphological changes with Jacobian map for prediction of pathologic tumor response to chemo-radiotherapy in locally advanced esophageal cancer”, Physics in Medicine and Biology, Vol. 63, No. 14, 145020 (13pp), July 2018. \u003ca href=\"https://doi.org/10.1016/j.ins.2012.05.008\"\u003edoi:\u003c/a\u003e\u003ca href=\"https://doi.org/10.1088/1361-6560/aacd22\"\u003e10.1088/1361-6560/aacd22\u003c/a\u003e\u003c/li\u003e\n\u003c/ol\u003e","title":"Radiomics Tools"},{"content":"Dr. Jin Sung Kim introduced an insightful video clip to give you a better understanding of target volumes for moving target in radiation therapy. This clip visualize a concept of moving target volume which was reported by Wolthaus et al., 2006.\nWolthaus JWH, Schneider C, Sonke JJ et al. Mid-ventilation CT scan construction from four-dimensional respiration-correlated CT scans for radiotherapy planning of lung cancer patients. Int. J. Radiat. Oncol. Biol. Phys.65(5), 1560–1571 (2006)\nhttps://www.youtube.com/embed/MQ4-x1pqKFI\n방사선치료에서 Target Volume이라는 것은 중요한 의미를 가진다. 어디까지 수술을 해야하느냐.. 와 동일한 의미로.어디까지 방사선을 주어야하느냐.. 를 결정하기 때문이다.그러한 Target Volume에는 GTV, CTV, ITV, PTV 등이 있고, 이에 대한 자세한 설명은 ICRU 50, 62, 83 레포트를 보면 확인할 수가 있다. 그 중에 움직이는 종양에 대한 정의를 하기 위해서 2006년 Wolthaus가 보고한 논문의 그림이 있는데, 강의자료로 사용하기 위해서 유사하게 그려보았고, Powerpoint의 기능을…\nvia Relationship of Target Volumes for moving target — Medical Physics\n","permalink":"https://qradiomics.com/posts/2016-07-03-concept-of-target-volumes/","summary":"\u003cp\u003e\u003ca href=\"http://mpjinsung.tistory.com/\"\u003eDr. Jin Sung Kim\u003c/a\u003e introduced an insightful video clip to give you a better understanding of target volumes for moving target in radiation therapy. This clip visualize a concept of moving target volume which was reported by Wolthaus et al., 2006.\u003c/p\u003e\n\u003cp\u003eWolthaus JWH, Schneider C, Sonke JJ et al. Mid-ventilation CT scan construction from four-dimensional respiration-correlated CT scans for radiotherapy planning of lung cancer patients. Int. J. Radiat. Oncol. Biol. Phys.65(5), 1560–1571 (2006)\u003c/p\u003e","title":"Relationship of Target Volumes for moving target — Medical Physics"},{"content":"Wookjin Choi, Ph.D. Associate Professor of Radiation Oncology Computational Healthcare \u0026amp; Oncology Informatics Lab Sidney Kimmel Medical College at Thomas Jefferson University Email: Wookjin.Choi@jefferson.edu, wchoi1022@gmail.com\nResearch Area\nMedical Image Analysis Radiomics/Computer-Aided Diagnosis Machine learning and Deep learning Selected Publications [Google Scholar][Scopus]\nWookjin Choi, Yingcui Jia, Jennifer Kwak, Maria Werner-Wasik, Adam P. Dicker, Nicole L. Simone, Eugene Storozynsky, Varsha Jain, Yevgeniy Vinogradskiy, Novel Functional Radiomics for Prediction of Cardiac Positron Emission Tomography Avidity in Lung Cancer Radiotherapy. JCO Clin Cancer Inform 8, e2300241(2024). https://doi.org/10.1200/CCI.23.00241 (featured in JCO CCI Editorial) Wookjin Choi, Chia-Ju Liu, Sadegh Riyahi Alam, Jung Hun Oh, Raj Vaghjiani, John Humm, Wolfgang Weber, Prasad S. Adusumilli, Joseph O. Deasy, and Wei Lu, \u0026ldquo;Preoperative 18F-FDG PET/CT and CT Radiomics for Identifying Aggressive Histopathological Subtypes in Early Stage Lung Adenocarcinoma\u0026rdquo;, Computational and Structural Biotechnology Journal, Volume 21, 2023, Pages 5601-5608, https://doi.org/10.1016/j.csbj.2023.11.008 Wookjin Choi, Navdeep Dahiya, Saad Nadeem, \u0026ldquo;CIRDataset: A large-scale Dataset for Clinically-Interpretable lung nodule Radiomics and malignancy prediction,\u0026rdquo; International Conference on Medical Image Computing and Computer-Assisted Intervention, Sep 2022. https://arxiv.org/abs/2206.14903 https://link.springer.com/chapter/10.1007/978-3-031-16443-9_2 Jung Hun Oh, Wookjin Choi, Euiseong Ko, Mingon Kang, Allen Tannenbaum, Joseph O Deasy, \u0026ldquo;PathCNN: interpretable convolutional neural networks for survival prediction and pathway analysis applied to glioblastoma,\u0026rdquo; Bioinformatics, Volume 37, Issue Supplement_1, July 2021, Pages i443–i450, the first two authors should be regarded as Joint First Authors. doi.org/10.1093/bioinformatics/btab285, Codes Wookjin Choi, Saad Nadeem, Sadegh Riyahi, Joseph O. Deasy, Allen Tannenbaum, Wei Lu, \u0026ldquo;Reproducible and Interpretable Spiculation Quantification for Lung Cancer Screening,\u0026rdquo; Computer Methods and Programs in Biomedicine 200, 105839, March 2021, doi:10.1016/j.cmpb.2020.105839 Slides Wookjin Choi, Jung Hun Oh, Sadegh Riyahi, Chia-Ju Liu, Feng Jiang, Wengen Chen, Charles White, Andreas Rimner, James G. Mechalakos, Joseph O. Deasy, and Wei Lu, \u0026ldquo;Radiomics analysis of pulmonary nodules in low-dose CT for early detection of lung cancer,\u0026rdquo; Medical Physics, Vol. 45, No. 4, pp. 1537-1549, April 2018. doi:10.1002/mp.12820 Selected as an Editor\u0026rsquo;s Pick Slides Wookjin Choi, M Xue, B Lane, M Kang, K Patel, W Regine, P Klahr, J Wang, S Chen, W D\u0026rsquo;Souza, W Lu, \u0026ldquo;Individually Optimized Contrast-Enhanced 4D-CT for Radiotherapy Simulation in Pancreatic Ductal Adenocarcinoma\u0026rdquo;, Medical Physics, Vol. 43, No. 10, pp. 5659-5666, October 2016. doi:10.1118/1.4963213 Selected as Today\u0026rsquo;s Science Sparks of MSKCC Library (10/17/2016) Slides Animation Poster Wookjin Choi, Tae-Sun Choi, \u0026ldquo;Automated Pulmonary Nodule Detection based on Three-dimensional Shape-based Feature Descriptor,\u0026rdquo; Computer Methods and Programs in Biomedicine, Vol. 113, No. 1, pp. 37–54, January 2014. doi:10.1016/j.cmpb.2013.08.015 Wookjin Choi, Tae-Sun Choi, \u0026ldquo;Genetic Programming-based feature transform and classification for the automatic detection of pulmonary nodules on computed tomography images,\u0026rdquo; Information Sciences, Vol. 212, pp. 57-78, December 2012. doi:10.1016/j.ins.2012.05.008 Research Grants and Contracts\n1/2022 - 12/2025 080-34000-N39801 PI: Wookjin Choi \u0026ldquo;Computational development for MRI-Linac\u0026rdquo; ViewRay Technologies, Inc. Total Direct Costs: $368,182 1/2022 – 1/2024 SKCC Research Grant PI: Wookjin Choi \u0026ldquo;Interpretable Predictive Models for Radiation Therapy\u0026rdquo; Sidney Kimmel Cancer Center at Thomas Jefferson University Hospital Total Direct Costs: $140,000 5/2021 - 5/2022 W911NF2110280 PI: Wookjin Choi \u0026ldquo;Acquisition of a GPU-Accelerated Deep-Learning Research Cluster\u0026rdquo; DoD Research and Education Program for HBCU/MI Equipment/Instrumentation Total Direct Costs: $588,244 7/2020 – 7/2021 CCAM E-055 PI: Wookjin Choi \u0026ldquo;A Robust Human Action Recognition System using Multi-View Depth Videos for Safe and Reliable Human-Robot Interactions in a Mixed Reality Environment\u0026rdquo; Innovation Fund, VSU \u0026amp; Commonwealth Center for Advanced Manufacturing (CCAM) Total Direct Costs: $50,000 11/2013 – 7/2014 NRF-2013R1A1-A2058113 PI: Wookjin Choi \u0026ldquo;3D Image Analysis for Computer Aided Diagnosis in Lung CT Image\u0026rdquo; Basic Science Research Program, National Research Foundation of Korea (Similar to K99/R00) Total Direct Costs: $39,000 12/2013 – 12/2014 2013RS-03-00000-P-00173 PI: Wookjin Choi founded QuaLIA, Inc. \u0026ldquo;A System for Computer-Aided Detection of Pulmonary Disease\u0026rdquo; Start-up Seed Grant, Small and Medium Business Administration of Korea (Similar to SBIR) Total Direct Costs: $90,000 Teaching (at Virginia State University 2019 \u0026ndash; 2021)\nCSCI 150/151 Programming I \u0026amp; Lab (Fall 2020) CSCI 281 Discrete Structures (Spring 2020, Spring 2021) CSCI 287 Data Structures (Fall 2019, Fall 2020) CSCI 392 Algorithms and Adv. Data Structures (Fall 2019, Spring 2021) CSCI 445 Computer Communications Network (Fall 2020) CSCI 471 Parallel and Distributed Programming (Fall 2021) CSCI 493 Senior Project I (Spring 2020, Spring 2021) CSCI 494 Senior Project II (Fall 2019, Fall 2020) CSCI 545 Advanced Data Communications (Fall 2020) CSCI 592 Adv. Algorithms (Spring 2020, Spring 2021) CSCI 643 Spe. Top.: Intro. to Machine Learning (Spring 2021) CSCI 640 Spe. Top.: Intro. to Deep Learning (Fall 2021) ","permalink":"https://qradiomics.com/profile/","summary":"\u003ch1 id=\"wookjin-choi-phd\"\u003e\u003cstrong\u003eWookjin Choi, Ph.D.\u003c/strong\u003e\u003c/h1\u003e\n\u003cp\u003eAssociate Professor of Radiation Oncology\n\u003cstrong\u003eC\u003c/strong\u003eomputational \u003cstrong\u003eH\u003c/strong\u003eealthcare \u0026amp; \u003cstrong\u003eO\u003c/strong\u003encology \u003cstrong\u003eI\u003c/strong\u003enformatics Lab\nSidney Kimmel Medical College at Thomas Jefferson University\nEmail: \u003ca href=\"mailto:Wookjin.Choi@jefferson.edu\"\u003eWookjin.Choi@jefferson.edu\u003c/a\u003e, \u003ca href=\"mailto:wchoi1022@gmail.com\"\u003ewchoi1022@gmail.com\u003c/a\u003e\u003c/p\u003e\n\u003cp class=\"profile-icons\" style=\"display:flex;gap:.5rem;align-items:center;flex-wrap:wrap;\"\u003e\n\u003ca href=\"images/wookjin-choi-cv.pdf\" title=\"CV\"\u003e\u003cimg src=\"images/thin-081_file_document_cv_curriculum_vitae-32.png\" alt=\"CV\" width=\"32\" height=\"32\"\u003e\u003c/a\u003e\n\u003ca href=\"https://academictree.org/etree/tree.php?pid=811166\u0026pnodecount=6\u0026cnodecount=3\u0026fontsize=1\" title=\"Academic Tree\"\u003e\u003cimg src=\"images/thin-081_file_document_cv_curriculum_vitae-32.png\" alt=\"Academic Tree\" width=\"32\" height=\"32\"\u003e\u003c/a\u003e\n\u003ca href=\"https://www.researchgate.net/profile/Wookjin_Choi2\" title=\"ResearchGate\"\u003e\u003cimg src=\"images/rg.png\" alt=\"ResearchGate\" width=\"32\" height=\"32\"\u003e\u003c/a\u003e\n\u003ca href=\"https://www.linkedin.com/in/wookjin-choi-5309a325/\" title=\"LinkedIn\"\u003e\u003cimg src=\"images/174857.png\" alt=\"LinkedIn\" width=\"32\" height=\"32\"\u003e\u003c/a\u003e\n\u003ca href=\"https://github.com/taznux\" title=\"GitHub\"\u003e\u003cimg src=\"images/Octicons-mark-github.svg\" alt=\"GitHub\" width=\"32\" height=\"32\"\u003e\u003c/a\u003e\n\u003ca href=\"https://publons.com/a/520211/\" title=\"Publons\"\u003e\u003cimg src=\"images/publons.png\" alt=\"Publons\" width=\"32\" height=\"32\"\u003e\u003c/a\u003e\n\u003ca href=\"https://orcid.org/0000-0001-8038-5876\" title=\"ORCID\"\u003e\u003cimg src=\"images/orcid.png\" alt=\"ORCID\" width=\"32\" height=\"32\"\u003e\u003c/a\u003e\n\u003ca href=\"https://www.kaggle.com/qradiomics\" title=\"Kaggle\"\u003e\u003cimg src=\"images/189_Kaggle_logo_logos-512.png\" alt=\"Kaggle\" width=\"32\" height=\"32\"\u003e\u003c/a\u003e\n\u003c/p\u003e\n\u003chr\u003e\n\u003cul\u003e\n\u003cli\u003e\n\u003cp\u003eResearch Area\u003c/p\u003e\n\u003cul\u003e\n\u003cli\u003eMedical Image Analysis\u003c/li\u003e\n\u003cli\u003eRadiomics/Computer-Aided Diagnosis\u003c/li\u003e\n\u003cli\u003eMachine learning and Deep learning\u003c/li\u003e\n\u003c/ul\u003e\n\u003c/li\u003e\n\u003cli\u003e\n\u003cp\u003eSelected Publications [\u003ca href=\"http://scholar.google.com/citations?user=iHgsGLUAAAAJ\u0026amp;hl=en\"\u003eGoogle Scholar\u003c/a\u003e][\u003ca href=\"http://www.scopus.com/authid/detail.url?authorId=7402516217\"\u003eScopus\u003c/a\u003e]\u003c/p\u003e\n\u003col\u003e\n\u003cli\u003e\u003cstrong\u003eWookjin Choi\u003c/strong\u003e, Yingcui Jia, Jennifer Kwak, Maria Werner-Wasik, Adam P. Dicker, Nicole L. Simone, Eugene Storozynsky, Varsha Jain, Yevgeniy Vinogradskiy, Novel Functional Radiomics for Prediction of Cardiac Positron Emission Tomography Avidity in Lung Cancer Radiotherapy. JCO Clin Cancer Inform 8, e2300241(2024). \u003ca href=\"https://doi.org/10.1200/CCI.23.00241\"\u003ehttps://doi.org/10.1200/CCI.23.00241\u003c/a\u003e (featured in \u003ca href=\"https://ascopubs.org/doi/10.1200/CCI.24.00045\"\u003eJCO CCI Editorial\u003c/a\u003e)\u003c/li\u003e\n\u003cli\u003e\u003cstrong\u003eWookjin Choi\u003c/strong\u003e, Chia-Ju Liu, Sadegh Riyahi Alam, Jung Hun Oh, Raj Vaghjiani, John Humm, Wolfgang Weber, Prasad S. Adusumilli, Joseph O. Deasy, and Wei Lu, \u0026ldquo;Preoperative 18F-FDG PET/CT and CT Radiomics for Identifying Aggressive Histopathological Subtypes in Early Stage Lung Adenocarcinoma\u0026rdquo;, Computational and Structural Biotechnology Journal, \u003ca href=\"https://www.sciencedirect.com/journal/computational-and-structural-biotechnology-journal/vol/21/suppl/C\"\u003eVolume 21\u003c/a\u003e, 2023, Pages 5601-5608, \u003ca href=\"https://doi.org/10.1016/j.csbj.2023.11.008\"\u003ehttps://doi.org/10.1016/j.csbj.2023.11.008\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e\u003cstrong\u003eWookjin Choi\u003c/strong\u003e, Navdeep Dahiya, Saad Nadeem, \u0026ldquo;CIRDataset: A large-scale Dataset for Clinically-Interpretable lung nodule Radiomics and malignancy prediction,\u0026rdquo; International Conference on Medical Image Computing and Computer-Assisted Intervention, Sep 2022. \u003ca href=\"https://arxiv.org/abs/2206.14903\"\u003ehttps://arxiv.org/abs/2206.14903\u003c/a\u003e \u003ca href=\"https://link.springer.com/chapter/10.1007/978-3-031-16443-9_2\"\u003ehttps://link.springer.com/chapter/10.1007/978-3-031-16443-9_2\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003eJung Hun Oh, \u003cstrong\u003eWookjin Choi\u003c/strong\u003e, Euiseong Ko, Mingon Kang, Allen Tannenbaum, Joseph O Deasy, \u0026ldquo;PathCNN: interpretable convolutional neural networks for survival prediction and pathway analysis applied to glioblastoma,\u0026rdquo; Bioinformatics, Volume 37, Issue Supplement_1, July 2021, Pages i443–i450, the first two authors should be regarded as Joint First Authors. \u003ca href=\"https://doi.org/10.1093/bioinformatics/btab285\"\u003edoi.org/10.1093/bioinformatics/btab285\u003c/a\u003e, \u003ca href=\"https://github.com/mskspi/PathCNN\"\u003eCodes\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e\u003cstrong\u003eWookjin Choi\u003c/strong\u003e, Saad Nadeem, Sadegh Riyahi, Joseph O. Deasy, Allen Tannenbaum, Wei Lu, \u0026ldquo;Reproducible and Interpretable Spiculation Quantification for Lung Cancer Screening,\u0026rdquo; Computer Methods and Programs in Biomedicine 200, 105839, March 2021, \u003ca href=\"https://doi.org/10.1016/j.cmpb.2020.105839\"\u003edoi:10.1016/j.cmpb.2020.105839\u003c/a\u003e \u003ca href=\"https://qradiomics.wordpress.com/2018/09/11/interpretable-spiculation-quantification-for-lung-cancer-screening/\"\u003eSlides\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e\u003cstrong\u003eWookjin Choi\u003c/strong\u003e, Jung Hun Oh, Sadegh Riyahi, Chia-Ju Liu, Feng Jiang, Wengen Chen, Charles White, Andreas Rimner, James G. Mechalakos, Joseph O. Deasy, and Wei Lu, \u0026ldquo;Radiomics analysis of pulmonary nodules in low-dose CT for early detection of lung cancer,\u0026rdquo; Medical Physics, Vol. 45, No. 4, pp. 1537-1549, April 2018. \u003ca href=\"http://doi.org/10.1002/mp.12820\"\u003edoi:10.1002/mp.12820\u003c/a\u003e \u003cstrong\u003eSelected as an Editor\u0026rsquo;s Pick\u003c/strong\u003e \u003ca href=\"https://qradiomics.wordpress.com/2017/08/03/radiomics-analysis-of-pulmonary-nodules-in-low-dose-ct-for-early-detection-of-lung-cancer/\"\u003eSlides\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e\u003cstrong\u003eWookjin Choi\u003c/strong\u003e, M Xue, B Lane, M Kang, K Patel, W Regine, P Klahr, J Wang, S Chen, W D\u0026rsquo;Souza, W Lu, \u0026ldquo;Individually Optimized Contrast-Enhanced 4D-CT for Radiotherapy Simulation in Pancreatic Ductal Adenocarcinoma\u0026rdquo;, Medical Physics, Vol. 43, No. 10, pp. 5659-5666, October 2016. \u003ca href=\"http://dx.doi.org/10.1118/1.4963213\"\u003edoi:10.1118/1.4963213\u003c/a\u003e \u003ca href=\"https://library.mskcc.org/sparks/quarter/2016/4/prod\"\u003eSelected as Today\u0026rsquo;s Science Sparks of MSKCC Library (10/17/2016)\u003c/a\u003e \u003ca href=\"https://qradiomics.wordpress.com/2016/08/05/individually-optimized-contrast-enhanced-4d-ct-for-radiotherapy-simulation-in-pancreatic-ductal-adenocarcinoma/\"\u003eSlides\u003c/a\u003e \u003ca href=\"https://qradiomics.wordpress.com/2016/08/05/estimate-peak-enhancement-time/\"\u003eAnimation\u003c/a\u003e \u003ca href=\"https://qradiomics.wordpress.com/2016/09/21/individually-optimized-contrast-enhanced-4d-ct-for-radiotherapy-simulation-in-pancreatic-adenocarcinoma/\"\u003ePoster\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e\u003cstrong\u003eWookjin Choi\u003c/strong\u003e, Tae-Sun Choi, \u0026ldquo;Automated Pulmonary Nodule Detection based on Three-dimensional Shape-based Feature Descriptor,\u0026rdquo; Computer Methods and Programs in Biomedicine, Vol. 113, No. 1, pp. 37–54, January 2014. \u003ca href=\"https://doi.org/10.1016/j.cmpb.2013.08.015\"\u003edoi:10.1016/j.cmpb.2013.08.015\u003c/a\u003e\u003c/li\u003e\n\u003cli\u003e\u003cstrong\u003eWookjin Choi\u003c/strong\u003e, Tae-Sun Choi, \u0026ldquo;Genetic Programming-based feature transform and classification for the automatic detection of pulmonary nodules on computed tomography images,\u0026rdquo; Information Sciences, Vol. 212, pp. 57-78, December 2012. \u003ca href=\"https://doi.org/10.1016/j.ins.2012.05.008\"\u003edoi:10.1016/j.ins.2012.05.008\u003c/a\u003e\u003c/li\u003e\n\u003c/ol\u003e\n\u003c/li\u003e\n\u003cli\u003e\n\u003cp\u003eResearch Grants and Contracts\u003c/p\u003e","title":"Profile"},{"content":" ","permalink":"https://qradiomics.com/posts/2016-04-28-robust-breathing-signal-extraction-from-cone-beam-ct-projections-based-on-adaptive-and-global-optimization-techniques/","summary":"\u003cdiv class=\"slideshare-embed\" style=\"position:relative;padding-bottom:56.25%;height:0;margin:1rem 0;\"\u003e\n  \u003ciframe src=\"https://www.slideshare.net/slideshow/embed_code/61487038\"\n          width=\"595\" height=\"485\"\n          style=\"position:absolute;top:0;left:0;width:100%;height:100%;border:1px solid #CCC;\"\n          frameborder=\"0\" marginwidth=\"0\" marginheight=\"0\" scrolling=\"no\"\n          allowfullscreen\u003e\u003c/iframe\u003e\n\u003c/div\u003e","title":"Robust breathing signal extraction from cone beam CT projections based on adaptive and global optimization techniques"},{"content":" ","permalink":"https://qradiomics.com/posts/2016-04-28-dual-energy-ct-in-radiotherapy-current-applications-and-future-outlook/","summary":"\u003cdiv class=\"slideshare-embed\" style=\"position:relative;padding-bottom:56.25%;height:0;margin:1rem 0;\"\u003e\n  \u003ciframe src=\"https://www.slideshare.net/slideshow/embed_code/61487028\"\n          width=\"595\" height=\"485\"\n          style=\"position:absolute;top:0;left:0;width:100%;height:100%;border:1px solid #CCC;\"\n          frameborder=\"0\" marginwidth=\"0\" marginheight=\"0\" scrolling=\"no\"\n          allowfullscreen\u003e\u003c/iframe\u003e\n\u003c/div\u003e","title":"Dual energy CT in radiotherapy: Current applications and future outlook"},{"content":"Invited talk in GIST, Nov 2014\n","permalink":"https://qradiomics.com/posts/2016-03-10-image-processing-in-lung-cancer-screening-and-treatment/","summary":"\u003cp\u003eInvited talk in GIST, Nov 2014\u003c/p\u003e\n\u003cdiv class=\"slideshare-embed\" style=\"position:relative;padding-bottom:56.25%;height:0;margin:1rem 0;\"\u003e\n  \u003ciframe src=\"https://www.slideshare.net/slideshow/embed_code/59354573\"\n          width=\"595\" height=\"485\"\n          style=\"position:absolute;top:0;left:0;width:100%;height:100%;border:1px solid #CCC;\"\n          frameborder=\"0\" marginwidth=\"0\" marginheight=\"0\" scrolling=\"no\"\n          allowfullscreen\u003e\u003c/iframe\u003e\n\u003c/div\u003e","title":"Image processing in lung cancer screening and treatment"},{"content":" ⚠️ This project is no longer maintained. It has been superseded by qradiomics, which provides a unified modern Python implementation.\nhttps://github.com/taznux/qualia\nQuaLIA (Quantitative Lung Image Analysis)\nOpen-source framework for Computer-Aided Detection/Diagnosis OSX/Java/ITK/VTK/Gradle QuaLIA CAD Download Source code Download Binary\n","permalink":"https://qradiomics.com/projects/2016-01-11-qualia-cad/","summary":"\u003cblockquote\u003e\n\u003cp\u003e⚠️ \u003cstrong\u003eThis project is no longer maintained.\u003c/strong\u003e It has been superseded by \u003ca href=\"/projects/2026-05-17-qradiomics/\"\u003eqradiomics\u003c/a\u003e, which provides a unified modern Python implementation.\u003c/p\u003e\u003c/blockquote\u003e\n\u003cp\u003e\u003ca href=\"https://github.com/taznux/qualia\"\u003ehttps://github.com/taznux/qualia\u003c/a\u003e\u003c/p\u003e\n\u003cp\u003eQuaLIA (Quantitative Lung Image Analysis)\u003c/p\u003e\n\u003cul\u003e\n\u003cli\u003eOpen-source framework for Computer-Aided Detection/Diagnosis\u003c/li\u003e\n\u003cli\u003eOSX/Java/ITK/VTK/Gradle\u003c/li\u003e\n\u003c/ul\u003e\n\u003cp\u003e\u003cimg alt=\"QuaLIA CAD\" loading=\"lazy\" src=\"/projects/2016-01-11-qualia-cad/images/untitled.png\"\u003e\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003e\u003ca href=\"https://github.com/QuaLIACAD/qualia\"\u003eQuaLIA CAD\u003c/a\u003e\u003c/strong\u003e \u003ca href=\"https://github.com/QuaLIACAD/qualia/archive/master.zip\"\u003eDownload Source code\u003c/a\u003e   \u003ca href=\"https://docs.google.com/uc?export=download\u0026amp;confirm=5MsF\u0026amp;id=0BwUtEL5FMGdzOGtDeU9nWGVGQVU\"\u003eDownload Binary\u003c/a\u003e\u003c/p\u003e\n\u003cdiv style=\"position: relative; padding-bottom: 56.25%; height: 0; overflow: hidden;\"\u003e\n      \u003ciframe allow=\"accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture; web-share; fullscreen\" loading=\"eager\" referrerpolicy=\"strict-origin-when-cross-origin\" src=\"https://www.youtube.com/embed/uEPYpfTG5uw?autoplay=0\u0026amp;controls=1\u0026amp;end=0\u0026amp;loop=0\u0026amp;mute=0\u0026amp;start=0\" style=\"position: absolute; top: 0; left: 0; width: 100%; height: 100%; border:0;\" title=\"YouTube video\"\u003e\u003c/iframe\u003e\n    \u003c/div\u003e","title":"QuaLIA CAD"},{"content":" ","permalink":"https://qradiomics.com/posts/2015-09-15-radiomics-novel-paradigm-of-deep-learning-for-clinical-decision-support-toward-plan-b-using-liquid-biopsy-korean/","summary":"\u003cdiv class=\"slideshare-embed\" style=\"position:relative;padding-bottom:56.25%;height:0;margin:1rem 0;\"\u003e\n  \u003ciframe src=\"https://www.slideshare.net/slideshow/embed_code/52826006\"\n          width=\"595\" height=\"485\"\n          style=\"position:absolute;top:0;left:0;width:100%;height:100%;border:1px solid #CCC;\"\n          frameborder=\"0\" marginwidth=\"0\" marginheight=\"0\" scrolling=\"no\"\n          allowfullscreen\u003e\u003c/iframe\u003e\n\u003c/div\u003e","title":"Radiomics: Novel Paradigm of Deep Learning for Clinical Decision Support toward Plan B using Liquid Biopsy (Korean)"},{"content":" ","permalink":"https://qradiomics.com/posts/2015-09-15-radiomics-novel-paradigm-of-deep-learning-for-clinical-decision-support-toward-plan-b-using-liquid-biopsy/","summary":"\u003cdiv class=\"slideshare-embed\" style=\"position:relative;padding-bottom:56.25%;height:0;margin:1rem 0;\"\u003e\n  \u003ciframe src=\"https://www.slideshare.net/slideshow/embed_code/52825938\"\n          width=\"595\" height=\"485\"\n          style=\"position:absolute;top:0;left:0;width:100%;height:100%;border:1px solid #CCC;\"\n          frameborder=\"0\" marginwidth=\"0\" marginheight=\"0\" scrolling=\"no\"\n          allowfullscreen\u003e\u003c/iframe\u003e\n\u003c/div\u003e","title":"Radiomics: Novel Paradigm of Deep Learning for Clinical Decision Support toward Plan B using Liquid Biopsy"},{"content":"2015 AAPM annual meeting\n","permalink":"https://qradiomics.com/posts/2015-09-15-quantitative-image-feature-analysis-of-multiphase-liver-ct-for-hepatocellular-carcinoma-hcc-in-radiation-therapy/","summary":"\u003cp\u003e2015 AAPM annual meeting\u003c/p\u003e\n\u003cdiv class=\"slideshare-embed\" style=\"position:relative;padding-bottom:56.25%;height:0;margin:1rem 0;\"\u003e\n  \u003ciframe src=\"https://www.slideshare.net/slideshow/embed_code/52825646\"\n          width=\"595\" height=\"485\"\n          style=\"position:absolute;top:0;left:0;width:100%;height:100%;border:1px solid #CCC;\"\n          frameborder=\"0\" marginwidth=\"0\" marginheight=\"0\" scrolling=\"no\"\n          allowfullscreen\u003e\u003c/iframe\u003e\n\u003c/div\u003e","title":"Quantitative Image Feature Analysis of Multiphase Liver CT for Hepatocellular Carcinoma (HCC) in Radiation Therapy"},{"content":"2015 AAPM annual meeting\n","permalink":"https://qradiomics.com/posts/2015-09-15-image-quality-assessment-of-contrast-enhanced-4d-ct-for-pancreatic-adenocarcinoma-in-radiotherapy-simulation/","summary":"\u003cp\u003e2015 AAPM annual meeting\u003c/p\u003e\n\u003cdiv class=\"slideshare-embed\" style=\"position:relative;padding-bottom:56.25%;height:0;margin:1rem 0;\"\u003e\n  \u003ciframe src=\"https://www.slideshare.net/slideshow/embed_code/52825645\"\n          width=\"595\" height=\"485\"\n          style=\"position:absolute;top:0;left:0;width:100%;height:100%;border:1px solid #CCC;\"\n          frameborder=\"0\" marginwidth=\"0\" marginheight=\"0\" scrolling=\"no\"\n          allowfullscreen\u003e\u003c/iframe\u003e\n\u003c/div\u003e","title":"Image quality assessment of contrast-enhanced 4D-CT for pancreatic adenocarcinoma in radiotherapy simulation"},{"content":" ","permalink":"https://qradiomics.com/posts/2014-10-03-computer-aided-detection-of-pulmonary-nodules-in-ct-scans/","summary":"\u003cdiv class=\"slideshare-embed\" style=\"position:relative;padding-bottom:56.25%;height:0;margin:1rem 0;\"\u003e\n  \u003ciframe src=\"https://www.slideshare.net/slideshow/embed_code/39782128\"\n          width=\"595\" height=\"485\"\n          style=\"position:absolute;top:0;left:0;width:100%;height:100%;border:1px solid #CCC;\"\n          frameborder=\"0\" marginwidth=\"0\" marginheight=\"0\" scrolling=\"no\"\n          allowfullscreen\u003e\u003c/iframe\u003e\n\u003c/div\u003e","title":"Computer Aided Detection of Pulmonary Nodules in CT Scans"},{"content":" ","permalink":"https://qradiomics.com/posts/2014-10-02-pulmonary-nodule-detection-using-voxel-classification-in-lung-ct-images/","summary":"\u003cdiv class=\"slideshare-embed\" style=\"position:relative;padding-bottom:56.25%;height:0;margin:1rem 0;\"\u003e\n  \u003ciframe src=\"https://www.slideshare.net/slideshow/embed_code/39782549\"\n          width=\"595\" height=\"485\"\n          style=\"position:absolute;top:0;left:0;width:100%;height:100%;border:1px solid #CCC;\"\n          frameborder=\"0\" marginwidth=\"0\" marginheight=\"0\" scrolling=\"no\"\n          allowfullscreen\u003e\u003c/iframe\u003e\n\u003c/div\u003e","title":"Pulmonary Nodule Detection using Voxel Classification in Lung CT images (Korean)"},{"content":" ","permalink":"https://qradiomics.com/posts/2014-10-02-lung-structure-segmentation-and-nodule-detection-based-on-3d-block-analysis-in-ct-image-korean/","summary":"\u003cdiv class=\"slideshare-embed\" style=\"position:relative;padding-bottom:56.25%;height:0;margin:1rem 0;\"\u003e\n  \u003ciframe src=\"https://www.slideshare.net/slideshow/embed_code/39782550\"\n          width=\"595\" height=\"485\"\n          style=\"position:absolute;top:0;left:0;width:100%;height:100%;border:1px solid #CCC;\"\n          frameborder=\"0\" marginwidth=\"0\" marginheight=\"0\" scrolling=\"no\"\n          allowfullscreen\u003e\u003c/iframe\u003e\n\u003c/div\u003e","title":"Lung structure segmentation and nodule detection based on 3D block analysis in CT image (Korean)"},{"content":" ","permalink":"https://qradiomics.com/posts/2014-10-02-lung-volume-segmentation-using-graph-cut-korean/","summary":"\u003cdiv class=\"slideshare-embed\" style=\"position:relative;padding-bottom:56.25%;height:0;margin:1rem 0;\"\u003e\n  \u003ciframe src=\"https://www.slideshare.net/slideshow/embed_code/39782556\"\n          width=\"595\" height=\"485\"\n          style=\"position:absolute;top:0;left:0;width:100%;height:100%;border:1px solid #CCC;\"\n          frameborder=\"0\" marginwidth=\"0\" marginheight=\"0\" scrolling=\"no\"\n          allowfullscreen\u003e\u003c/iframe\u003e\n\u003c/div\u003e","title":"Lung Volume Segmentation using Graph-Cut (Korean)"},{"content":" ","permalink":"https://qradiomics.com/posts/2014-10-02-computer-aided-detection-of-pulmonary-nodules-using-genetic-programming-korean/","summary":"\u003cdiv class=\"slideshare-embed\" style=\"position:relative;padding-bottom:56.25%;height:0;margin:1rem 0;\"\u003e\n  \u003ciframe src=\"https://www.slideshare.net/slideshow/embed_code/39782552\"\n          width=\"595\" height=\"485\"\n          style=\"position:absolute;top:0;left:0;width:100%;height:100%;border:1px solid #CCC;\"\n          frameborder=\"0\" marginwidth=\"0\" marginheight=\"0\" scrolling=\"no\"\n          allowfullscreen\u003e\u003c/iframe\u003e\n\u003c/div\u003e","title":"Computer-aided Detection of Pulmonary Nodules using Genetic Programming (Korean)"},{"content":" ","permalink":"https://qradiomics.com/posts/2014-10-02-computer-aided-detection-of-pulmonary-nodules-using-genetic-programming-2/","summary":"\u003cdiv class=\"slideshare-embed\" style=\"position:relative;padding-bottom:56.25%;height:0;margin:1rem 0;\"\u003e\n  \u003ciframe src=\"https://www.slideshare.net/slideshow/embed_code/39782554\"\n          width=\"595\" height=\"485\"\n          style=\"position:absolute;top:0;left:0;width:100%;height:100%;border:1px solid #CCC;\"\n          frameborder=\"0\" marginwidth=\"0\" marginheight=\"0\" scrolling=\"no\"\n          allowfullscreen\u003e\u003c/iframe\u003e\n\u003c/div\u003e","title":"Computer aided detection of pulmonary nodules using genetic programming"},{"content":"2010 IEEE ICIP\n","permalink":"https://qradiomics.com/posts/2014-10-02-computer-aided-detection-of-pulmonary-nodules-using-genetic-programming/","summary":"\u003cp\u003e2010 IEEE ICIP\u003c/p\u003e\n\u003cdiv class=\"slideshare-embed\" style=\"position:relative;padding-bottom:56.25%;height:0;margin:1rem 0;\"\u003e\n  \u003ciframe src=\"https://www.slideshare.net/slideshow/embed_code/39782553\"\n          width=\"595\" height=\"485\"\n          style=\"position:absolute;top:0;left:0;width:100%;height:100%;border:1px solid #CCC;\"\n          frameborder=\"0\" marginwidth=\"0\" marginheight=\"0\" scrolling=\"no\"\n          allowfullscreen\u003e\u003c/iframe\u003e\n\u003c/div\u003e","title":"Computer-aided Detection of Pulmonary Nodules using Genetic Programming"},{"content":"Invited talk in CNUH, Apr 2014\n","permalink":"https://qradiomics.com/posts/2014-10-02-image-analysis-and-nodule-detection-system-in-3d-lung-ct-images-using-insight-toolkit-korean/","summary":"\u003cp\u003eInvited talk in CNUH, Apr 2014\u003c/p\u003e\n\u003cdiv class=\"slideshare-embed\" style=\"position:relative;padding-bottom:56.25%;height:0;margin:1rem 0;\"\u003e\n  \u003ciframe src=\"https://www.slideshare.net/slideshow/embed_code/39782322\"\n          width=\"595\" height=\"485\"\n          style=\"position:absolute;top:0;left:0;width:100%;height:100%;border:1px solid #CCC;\"\n          frameborder=\"0\" marginwidth=\"0\" marginheight=\"0\" scrolling=\"no\"\n          allowfullscreen\u003e\u003c/iframe\u003e\n\u003c/div\u003e","title":"Image Analysis and Nodule Detection System in 3D Lung CT Images using Insight toolkit (Korean)"},{"content":" ","permalink":"https://qradiomics.com/posts/2014-10-02-automatic-detection-of-pulmonary-nodules-in-lung-ct-images/","summary":"\u003cdiv class=\"slideshare-embed\" style=\"position:relative;padding-bottom:56.25%;height:0;margin:1rem 0;\"\u003e\n  \u003ciframe src=\"https://www.slideshare.net/slideshow/embed_code/39782110\"\n          width=\"595\" height=\"485\"\n          style=\"position:absolute;top:0;left:0;width:100%;height:100%;border:1px solid #CCC;\"\n          frameborder=\"0\" marginwidth=\"0\" marginheight=\"0\" scrolling=\"no\"\n          allowfullscreen\u003e\u003c/iframe\u003e\n\u003c/div\u003e","title":"Automatic detection of pulmonary nodules in lung CT images"},{"content":" Automatic Pulmonary Nodule Detection https://www.youtube.com/watch?v=1rbdBf_-USo\nThree dimensional shape reconstruction from auto-focused microscopic image ","permalink":"https://qradiomics.com/posts/2014-10-02-previous-works/","summary":"\u003cul\u003e\n\u003cli\u003eAutomatic Pulmonary Nodule Detection\u003c/li\u003e\n\u003c/ul\u003e\n\u003cp\u003e\u003ca href=\"https://www.youtube.com/watch?v=1rbdBf\"\u003ehttps://www.youtube.com/watch?v=1rbdBf\u003c/a\u003e_-USo\u003c/p\u003e\n\u003cp\u003e \u003c/p\u003e\n\u003cul\u003e\n\u003cli\u003eThree dimensional shape reconstruction from auto-focused microscopic image\u003c/li\u003e\n\u003c/ul\u003e\n\u003cdiv style=\"position: relative; padding-bottom: 56.25%; height: 0; overflow: hidden;\"\u003e\n      \u003ciframe allow=\"accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture; web-share; fullscreen\" loading=\"eager\" referrerpolicy=\"strict-origin-when-cross-origin\" src=\"https://www.youtube.com/embed/aiAOs7AZAb8?autoplay=0\u0026amp;controls=1\u0026amp;end=0\u0026amp;loop=0\u0026amp;mute=0\u0026amp;start=0\" style=\"position: absolute; top: 0; left: 0; width: 100%; height: 100%; border:0;\" title=\"YouTube video\"\u003e\u003c/iframe\u003e\n    \u003c/div\u003e","title":"Previous Works"},{"content":" Lung cancer is the primary cause of cancer-related death in the world.\nMost patients diagnosed with lung cancer are already at an advanced stage (40% are stage IV, 30% are stage III) The current five-year survival rate is only 16%. If defective nodules are detected at an early stage, the survival rate can be increased. Computed tomography (CT) is one of the most sensitive methods for detecting pulmonary nodules.\nNodule: a rounded and irregular opaque figure (~30 mm) The early detection of pulmonary nodules is important in the treatment of lung cancer\nA tiring process Each scan contains hundreds of images and must be evaluated by a radiologist The use of a computer-aided detection (CAD) system can provide an effective solution\nIncreasing the scanning efficiency and potentially improving nodule detection QuaLIA CAD System - https://github.com/taznux/qualia Lung image analysis framework - https://github.com/taznux/lung-image-analysis\nhttp://www.youtube.com/watch?v=uEPYpfTG5uw\n","permalink":"https://qradiomics.com/cad/","summary":"\u003cul\u003e\n\u003cli\u003e\n\u003cp\u003eLung cancer is the primary cause of cancer-related death in the world.\u003c/p\u003e\n\u003cul\u003e\n\u003cli\u003eMost patients diagnosed with lung cancer are already at an advanced stage (40% are stage IV, 30% are stage III)\u003c/li\u003e\n\u003cli\u003eThe current five-year survival rate is only 16%.\u003c/li\u003e\n\u003cli\u003eIf defective nodules are detected at an early stage, the survival rate can be increased.\u003c/li\u003e\n\u003c/ul\u003e\n\u003c/li\u003e\n\u003cli\u003e\n\u003cp\u003eComputed tomography (CT) is one of the most sensitive methods for detecting pulmonary nodules.\u003c/p\u003e\n\u003cul\u003e\n\u003cli\u003eNodule: a rounded and irregular opaque figure (~30 mm)\u003c/li\u003e\n\u003c/ul\u003e\n\u003c/li\u003e\n\u003cli\u003e\n\u003cp\u003eThe early detection of pulmonary nodules is important in the treatment of lung cancer\u003c/p\u003e","title":"Introduction of Lung CAD"}]