Wesley Surento

Breast cancer risk assessment can help early prediction and intervention planning, lower mortality, and improve care outcomes. Many current tools utilize risk factors such as age, menopausal status, personal biopsy history, and family history of breast cancer. Although these characteristics do a reasonable job at capturing risk, they omit all information from imaging studies such as mammograms or MRIs. Even when negative for disease, analysis of these images could provide a number of markers that might also capture risk. There remains much unexplored potential in leveraging imaging markers as part of risk assessment models for prevention and early prediction.
In this work, we aim to develop and assess a new risk prediction model that incorporates MRI-derived features along with clinical risk factors.
In the first step, I collected relevant risk factors for predicting cancer within 5 years from the MRI for a cohort of high-risk patients. I built a REDcap data repository to store their clinical risk factors obtained from electronic health records, such as select demographic information, menopausal status, BRCA mutation, and family history of breast cancer.
In the second step, I identified predictive quantitative breast MRI markers. I extracted quantitative markers of background parenchymal enhancement using an image processing pipeline which I helped develop, and proceeded to assess their ability to predict 5-year cancer risk.
In the third step, I performed multimodal combination of imaging markers and clinical risk factors to predict 5-year cancer. We also explored the performance of these combinations for several cohort subsets. Our findings showed that multimodal combination of imaging markers can improve the predictive performance of a conventional risk assessment tool.