I am a 1st year PhD student at the Electrical Engineering and Computer Science (EECS) department at MIT. I am currently advised by Dr. Mahmood. After graduating from Johns Hopkins University in 2019 and prior to starting my PhD, I worked as a researcher at Harvard Medical School in Faisal’s lab, where I developed interpretable machine learning algorithms to improve disease diagnosis and prognosis from gigapixel histology slides and contributed open-source software tools for digital pathology image analysis. The algorithms I developed have seen success in a wide array of clinical applications ranging from cancer subtyping, metastasis detection, predicting the primary origins for cancers of unknown primary, to survival prediction and endomyocardial biopsy assessment. During my PhD training, I hope to focus more on algorithms that can learn meaningful representations from diverse modalities of biological and healthcare data for important tasks such as clinical outcome prediction and patient stratification and use the learned representations to gain further insights into biological processes and mechanisms of diseases.
PhD in Computer Science, 2021 - present
Massachusetts Institute of Technology
BSc in Applied Mathematics and Statistics, 2019
Johns Hopkins University
BSc in Biomedical Engineering, 2019
Johns Hopkins University
Using co-attention mapping between WSIs and genomic to capture multimodal interactions between histology images and genes for predicting patient survival. By adapting Transformer layers as a general encoder backbone in MIL, we consistently outperform current SOTA for survival prediction across 5 different cancer datasets (4,730 WSIs, 67 million patches).
A spotlight article on recent advances in multiplex immunofluorescence (mIF) and the potential of combining machine learning and mIF assays for clinical outcome prediction and biomarker discovery.