Research
- Computer Vision We develop novel vision architectures and training strategies for high-stakes visual recognition tasks — from lesion detection to surgical scene understanding — where performance and reliability are non-negotiable.
- Clinical AI & Medical Imaging Our imaging research focuses on automated analysis of radiological, pathological, and ophthalmic images. We build AI pipelines that assist clinicians with diagnosis, triage, and treatment planning at scale.
- Deep Learning & Machine Learning We investigate foundational deep learning methods including self-supervised learning, domain adaptation, and few-shot learning — tackling the core challenge of building robust models from limited labeled clinical data.
- Patient Outcomes & Clinical Research We partner with clinicians to measure how AI tools affect real patient outcomes, workflow efficiency, and diagnostic accuracy — ensuring our research translates into meaningful clinical benefit.
- Trustworthy AI in Healthcare We study explainability, uncertainty quantification, bias detection, and fairness in clinical AI system
Highlighted
Enhancing efficient deep learning models with multimodal, multi-teacher insights for medical image segmentation
Scientific Reports
·
07 May 2025
·
doi:10.1038/s41598-025-91430-0
Teach-Former, a novel knowledge distillation (KD) framework that leverages a Transformer backbone to effectively condense the knowledge of multiple teacher models into a single, streamlined student model. Moreover, it excels in the contextual and spatial interpretation of relationships across multimodal images for more accurate and precise segmentation.
All
2025
Enhancing efficient deep learning models with multimodal, multi-teacher insights for medical image segmentation
Scientific Reports
·
07 May 2025
·
doi:10.1038/s41598-025-91430-0
Teach-Former, a novel knowledge distillation (KD) framework that leverages a Transformer backbone to effectively condense the knowledge of multiple teacher models into a single, streamlined student model. Moreover, it excels in the contextual and spatial interpretation of relationships across multimodal images for more accurate and precise segmentation.
2023
Swin-SFTNet : Spatial Feature Expansion and Aggregation Using Swin Transformer for Whole Breast Micro-Mass Segmentation
2023 IEEE 20th International Symposium on Biomedical Imaging (ISBI)
·
18 Apr 2023
·
doi:10.1109/isbi53787.2023.10230342
Revolutionizing Space Health (Swin-FSR) Advancing Super-Resolution of Fundus Images for SANS Visual Assessment Technology
Lecture Notes in Computer Science
·
01 Jan 2023
·
doi:10.1007/978-3-031-43990-2_65
2022
Virtual-Reality Based Vestibular Ocular Motor Screening for Concussion Detection Using Machine-Learning
Lecture Notes in Computer Science
·
01 Jan 2022
·
doi:10.1007/978-3-031-20716-7_18
ECG-ATK-GAN Robustness Against Adversarial Attacks on ECGs Using Conditional Generative Adversarial Networks
Lecture Notes in Computer Science
·
01 Jan 2022
·
doi:10.1007/978-3-031-17721-7_8
2021
ECG-Adv-GAN Detecting ECG Adversarial Examples with Conditional Generative Adversarial Networks
2021 20th IEEE International Conference on Machine Learning and Applications (ICMLA)
·
01 Dec 2021
·
doi:10.1109/icmla52953.2021.00016
2020
Open collaborative writing with Manubot
PLOS Computational Biology
·
04 Dec 2020
·
doi:10.1371/journal.pcbi.1007128
Lorem ipsum dolor sit amet, consectetur adipiscing elit, sed do eiusmod tempor incididunt ut labore et dolore magna aliqua.
Constructing knowledge graphs and their biomedical applications
Computational and Structural Biotechnology Journal
·
01 Jan 2020
·
doi:10.1016/j.csbj.2020.05.017
2018
Sci-Hub provides access to nearly all scholarly literature
eLife
·
01 Mar 2018
·
doi:10.7554/eLife.32822