activity
20242026
collaborators

6 papers

cs.CV2026

Lymphocyte Mimicry Correction via Region-Level Tissue Reasoning and Unbalanced Optimal Transport

Xiang Li, Yuqi Wang, Casey C. Heirman +2

Cell mimicry arises when different cell types appear morphologically similar. Human pathologists resolve this ambiguity using surrounding tissue context, whereas current vision mod…

stat.AP2025

Demographic Distribution Matching between real world and virtual phantom population

Dhrubajyoti Ghosh, Fakrul Islam Tushar, Lavsen Dahal +5

Virtual imaging trials (VITs) offer scalable and cost-effective tools for evaluating imaging systems and protocols. However, their translational impact depends on rigorous comparab…

cs.CL2025

Zero-Shot Multi-Disease Labeling of Chest, Abdomen, and Pelvis CT Reports Using Open-Weight Large Language Models: The Effect of Labeling Conventions

Michael E. Garcia-Alcoser, Mobina Ghojoghnejad, Fakrul Islam Tushar +4

Purpose: To compare five lightweight open-weight large language models (LLMs) with a rule-based algorithm (RBA) and fine-tuned RadBERT for zero-shot labeling of chest-abdomen-pelvi…

cs.LG2025

Virtual Patients, Real Gains: Digital Twin-Based Simulated CT for Multitask Lung Nodule Analysis

Fakrul Islam Tushar, Lavsen Dahal, Paul Segars +1

AI-based lung cancer screening is constrained by scarce, annotated CT data, particularly for rare nodule presentations. We investigate whether physics-based, anatomy-informed simul…

eess.IV2024

XCAT-3.0: A Comprehensive Library of Personalized Digital Twins Derived from CT Scans

Lavsen Dahal, Mobina Ghojoghnejad, Dhrubajyoti Ghosh +10

Virtual Imaging Trials (VIT) offer a cost-effective and scalable approach for evaluating medical imaging technologies. Computational phantoms, which mimic real patient anatomy and…

cs.CV2024

Reproducible Benchmarking for Lung Nodule Detection and Malignancy Classification Across Multiple Low-Dose CT Datasets

Fakrul Islam Tushar, Avivah Wang, Lavsen Dahal +7

Evaluation of artificial intelligence (AI) models for low-dose CT lung cancer screening is limited by heterogeneous datasets, annotation standards, and evaluation protocols, making…