Artificial Intelligence and Digital Pathology: Making the Most of Limited Annotated Data

Explore the challenges and solutions in medical imaging AI projects through this 37-minute conference talk from the Toronto Machine Learning Series. Discover how Professor Anne Martel from the University of Toronto addresses the difficulties of obtaining large, expertly annotated datasets for medical imaging AI. Learn about semi-supervised and self-supervised approaches that efficiently utilize small and weakly labeled datasets, with a focus on digital pathology. Gain insights into methods applicable to various medical imaging modalities, and understand how to overcome the hurdles of limited patient data with both imaging and follow-up information for outcome prediction models.