Project 3: Integration of mammographic AI, clinical, and genomics information to improve breast cancer subtype- specific risk-based screening and prevention

The project will develop a deep-learning mammographic AI model to predict risk for molecular subtypes of fast- and slow-growing breast cancer in large, diverse cohorts. It will then develop and validate a next-generation WISDOM risk model by integrating the AI model, Project 2's polygenic risk score (PRS) model, and the latest clinical risk models. Finally, the mammographic AI model will be transferred from standard 2D mammography to newer 3D tomosynthesis in a diverse cohort. The resulting model will update the CISNET simulation model in Project 4 to estimate benefits, harms, costs, and health value outcomes, ultimately identifying a unified risk-based approach for the WISDOM study.