Research

For the complete publication list, please visit my Google Scholar

1) Generalizable & Large-Scale Foundation Models for Medical Image Segmentation

Building more generalizable and large-scale segmentation tools for different medical image segmentation tasks. Part of this is with the collaboration with GE Healthcare.

Relevant papers

Semi-supervised semantic segmentation of cell nuclei with diffusion model and collaborative learning, Journal of Medical Imaging, 2025.
Paper

SynthFM: Training Modality-agnostic Foundation Models for Medical Image Segmentation without Real Medical Data, ISBI 2025 (Oral).
Paper

Is SAM 2 better than SAM in medical image segmentation?, SPIE Medical Imaging 2025.
Paper

2) Interpretable Deep Learning for Medical Imaging

Designing self-interpretable models and theory-grounded attribution based on statistical decision theory for medical image classification tasks.

Relevant papers

A Test Statistic Estimation-based Approach for Establishing Self-interpretable CNN-based Binary Classifiers, IEEE Transactions on Medical Imaging (IEEE TMI), 2024.
Paper

Investigation of adversarial robust training for establishing interpretable CNN-based numerical observers, SPIE Medical Imaging, 2024.
Paper

What is the Optimal Attribution Method for Explainable Ophthalmic Disease Classification?, MICCAI OMIA Workshop (Best Paper Award), 2020.
Paper

3) Information Theory for Objective Medical Image Quality Assessmenr

How does any medical image processing algorithm affect information in medical images? How does it affect any downstream clinical or biological tasks? Is a medical image processing algorithm always helpful in improving downstream task performance?

Relevant papers

On the utility of virtual staining for downstream applications as it relates to task network capacity, Biomedical Optics Express, 2025.
Paper

Observer-Usable Information as a Task-specific Image Quality Metric, Under Review, 2025.
Pre-print