collaborators

9 papers

q-bio.TO2026

Gaze2Report: Radiology Report Generation via Visual-Gaze Prompt Tuning of LLMs

Aishik Konwer, Moinak Bhattacharya, Prateek Prasanna

Existing deep learning methods for radiology report generation enhance diagnostic efficiency but often overlook physician-informed medical priors. This leads to a suboptimal alignm…

cs.CV2026

Vessel-Aware Deep Learning for OCTA-Based Detection of AMD

Margalit G. Mitzner, Moinak Bhattacharya, Zhilin Zou +2

Age-related macular degeneration (AMD) is characterized by early micro-vascular alterations that can be captured non-invasively using optical coherence tomography angiography (OCTA…

cs.CV2025

PEaRL: Pathway-Enhanced Representation Learning for Gene and Pathway Expression Prediction from Histology

Sejuti Majumder, Saarthak Kapse, Moinak Bhattacharya +3

Integrating histopathology with spatial transcriptomics (ST) provides a powerful opportunity to link tissue morphology with molecular function. Yet most existing multimodal approac…

cs.CV2025

SoC-DT: Standard-of-Care Aligned Digital Twins for Patient-Specific Tumor Dynamics

Moinak Bhattacharya, Gagandeep Singh, Prateek Prasanna

Accurate prediction of tumor trajectories under standard-of-care (SoC) therapies remains a major unmet need in oncology. This capability is essential for optimizing treatment plann…

eess.IV2025

Anatomy-DT: A Cross-Diffusion Digital Twin for Anatomical Evolution

Moinak Bhattacharya, Gagandeep Singh, Prateek Prasanna

Accurately modeling the spatiotemporal evolution of tumor morphology from baseline imaging is a pre-requisite for developing digital twin frameworks that can simulate disease progr…

cs.CV2025

NeuroRAD-FM: A Foundation Model for Neuro-Oncology with Distributionally Robust Training

Moinak Bhattacharya, Angelica P. Kurtz, Fabio M. Iwamoto +2

Neuro-oncology poses unique challenges for machine learning due to heterogeneous data and tumor complexity, limiting the ability of foundation models (FMs) to generalize across coh…