Paper on Qualia Radiomics

Empowering Cancer Care with AI: A Jefferson Medical Student–Led Innovation

Tue, 08 Apr 2025 12:05:54 -0400

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.

AI-Powered Auto-Segmentation in Liver Cancer Therapy

Tue, 08 Apr 2025 11:48:42 -0400

We’re excited to share our latest work published in Technology in Cancer Research & Treatment: “Deep Learning-Based Auto-Segmentation for Liver Yttrium-90 Selective Internal Radiation Therapy” — a collaboration between Jun Li, Rani Anne, and myself.

This 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.

Clinically-Interpretable Radiomics

Wed, 29 Jun 2022 21:01:32 -0400

MICCAI'22 Paper | CMPB'21 Paper | CIRDataset

This 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.

PathCNN: interpretable convolutional neural networks for survival prediction and pathway analysis applied to glioblastoma

Thu, 22 Jul 2021 12:57:18 -0400

Jung Hun Oh, Wookjin Choi, Euiseong Ko, Mingon Kang, Allen Tannenbaum, Joseph O Deasy

The authors wish it to be known that, in their opinion, Jung Hun Oh and Wookjin Choi should be regarded as Joint First Authors.

https://academic.oup.com/bioinformatics/article/37/Supplement_1/i443/6319702

https://github.com/mskspi/PathCNN/raw/main/img/pathcnn.png

An 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

Reproducible and Interpretable Spiculation Quantification for Lung Cancer Screening

Tue, 17 Nov 2020 20:24:09 -0500

Choi, W., Nadeem, S., Alam, S. R., Deasy, J. O., Tannenbaum, A., & 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

Source codes: https://github.com/choilab-jefferson/LungCancerScreeningRadiomics

Highlights

A novel interpretable spiculation feature is presented, computed using the area distortion metric from spherical conformal (angle-preserving) parameterization.
A 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.

Aggressive Lung Adenocarcinoma Subtype Prediction Using FDG-PET/CT Radiomics

Tue, 01 Aug 2017 12:07:40 -0400

This paper has been published in the Computational and Structural Biotechnology Journal.

Preoperative 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

a 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