About me


I am a Postdoctoral Scholar at the Stanford University School of Medicine, working with Mirabela Rusu in the Laboratory for Integrative Personalized Medicine (PIMed). My current work focuses on vision-language AI models for personalized medicine and cancer detection.

I received my Ph.D. in Electrical and Computer Engineering from the University of Illinois, Urbana-Champaign in 2026, supervised by Mark A. Anastasio in the Computational Imaging Science Lab. During my Ph.D., I also worked closely with the Center for Label-free Imaging and spent two summers as an AI/ML Ph.D. intern at GE Healthcare, building foundation models for zero-shot medical image segmentation.

Previously, from 2018 to 2020, I was a Master’s student at the University of Waterloo, under the brilliant supervision of Vasudevan Lakshminarayanan and John Zelek.

I was an undergraduate at Jadavpur University, India in the Department of Electrical Engineering, from 2014 to 2018.

Here is my curriculum vitae.

If you’re interested in collaborating or have any questions about my research, feel free to reach out at souryas2@stanford.edu


Research Interests

I have broad interests in solving Medical Imaging problems using advanced computational methods. Specific topics that I am interested in include multi-modal AI and vision-language models, foundation models for medical image segmentation, interpretable deep learning, and information theory applications in imaging science. I am also interested in AI in healthcare, in general.

News and Updates

2026

  • Received a Fast Grant from the Biswas Family Foundation for research at the intersection of AI and health!
  • Participated in the CHIMERA-agent Challenge at MICCAI 2026 (Strasbourg, France), and was accepted to the MICCAI 2026 Doctoral Symposium to present my thesis work!
  • Joined Stanford University School of Medicine as a Postdoctoral Scholar with Mirabela Rusu!
  • Completed my Ph.D. in Electrical and Computer Engineering at UIUC!
  • Received the Elsa and Floyd Dunn Award, UIUC!
  • Paper on “Observer-Usable Information as a Task-specific Image Quality Metric” accepted to IEEE Transactions on Medical Imaging!
  • Paper on “Synthetic Volumetric Data Generation Enables Zero-Shot Generalization of Foundation Models in 3D Medical Image Segmentation” accepted to ISBI 2026!

2025

  • Our virtual staining work was featured in Beckman Institute News!
  • Paper on “On the utility of virtual staining for downstream applications as it relates to task network capacity” accepted to Biomedical Optics Express!
  • Paper on “Semi-supervised semantic segmentation of cell nuclei with diffusion model and collaborative learning” accepted to Journal of Medical Imaging, SPIE!
  • Filed a U.S. patent application (No. 19/291,155) on synthetic data generation for modality-agnostic zero-shot foundation models for medical images!
  • Joined GE Healthcare as an AI/ML PhD Summer Research Intern for the second consecutive summer!
  • Paper on “SynthFM: Training Modality-agnostic Foundation Models for Medical Image Segmentation without Real Medical Data” accepted to ISBI 2025 (Oral)!
  • Paper on “Is SAM 2 better than SAM in medical image segmentation?” accepted to SPIE Medical Imaging 2025!

2024

  • Joined GE Healthcare as AI/ML PhD Summer Research Intern!
  • Our self-interpretable classifier work was covered by The Week!
  • Paper on “A Test Statistic Estimation-based Approach for Establishing Self-interpretable CNN-based Binary Classifiers” accepted to IEEE Transactions on Medical Imaging!

2023

  • Paper on “Semi-Supervised Semantic Segmentation of Cell Nuclei via Diffusion-based Large-Scale Pre-Training and Collaborative Learning” out on arXiv!
  • Paper on “Revisiting model self-interpretability in a decision-theoretic way for binary medical image classification” accepted to ICML 2023 Workshop Interpretable Machine Learning in Healthcare!
  • Received the prestigious Bahl Graduate Student Award from the Department of ECE, UIUC!

2022

  • Paper on “Semi-supervised contrastive learning for white blood cell segmentation from label-free quantitative phase imaging” accepted to SPIE Medical Imaging 2023 (Oral Presentation)!
  • Paper on “White blood cell detection, classification and analysis using phase imaging with computational specificity (PICS)” accepted to Scientific Reports!
  • Passed my PhD Qualification Exam!

2021

  • Received prestigious NIH T32 Pre-doctoral trainee award!
  • Paper on “De-speckling of Optical Coherence Tomography Images Using Anscombe Transform and a Noisier2noise Model” accepted to MICCAI 2022 Workshop OMIA!
  • Paper on “Analyzing neural networks applied to an anatomical simulation of the breast” accepted to SPIE Medical Imaging 2022 (Oral Presentation)!
  • Paper on “Investigation of adversarial robust training for establishing interpretable CNN-based numerical observers” accepted to SPIE Medical Imaging 2022!

Media Highlights


Outreach

I am a part of “bigyan”, a science outreach group that aims to popularize science in the Bengali language. Please feel free to message me on any social media platform or send me an email if you are interested in contributing to “bigyan” or discussing science outreach more generally.