The overall goal of my research project is to develop a practical computational framework capable of predicting and optimizing the response of breast cancer patients to neoadjuvant therapy (NAT) using only routinely acquired magnetic resonance imaging (MRI) data. NAT is the standard-of-care therapeutic approach for patients with stage II-III locally advanced breast cancer. However, while NAT often reduces tumor size, many patients do not achieve pathologic complete response after treatment. Critically, patients who have residual disease after NAT are at increased risk of early recurrence and death. My research uses data from I-SPY 2, an adaptive clinical trial designed to improve outcomes for women with locally advanced and high-risk breast cancer, to predict patient-specific tumor growth. If this framework is shown to be successful in the large, heterogeneous I-SPY 2 dataset with only routine MRI, the approach may be applied in the clinic to improve patient outcomes.