Associate Professor of Biomedical Informatics, Harvard Medical School

 

 

Abstract:
Artificial intelligence (AI) is reshaping the landscape of cancer research and clinical diagnosis. Recent advances in microscopic image digitization, multi-modal machine learning algorithms, and scalable computing have enabled AI-powered pathology at an unprecedented scale. In this talk, I will highlight recent breakthroughs in uncertainty-aware pathology foundation models and their effectiveness in analyzing high-resolution digital pathology images. In addition, I will present new approaches in fairness-aware pathology AI that mitigate performance differences across populations and institutions. Furthermore, I will discuss recent studies that leverage AI to uncover novel connections between cell morphology and molecular profiles. Finally, I will outline persistent challenges and future directions in developing robust, generalizable, and clinically deployable medical AI systems.