Skip to main content

Organized by the University of Chicago’s Eric and Wendy Schmidt AI in Science Postdoctoral Fellowship Program.

Meeting location
William Eckhardt Research Center. Room 401
5640 S Ellis Avenue, Chicago, IL 60637
Map It

Agenda
4:30pm – 5:15pm: Presentation
5:15pm – 5:30pm: Q&A
5:30pm – 6:00pm: Reception

Abstract: Breast cancer histology is routinely analyzed to determine cancer grade and histologic subtype, but recent studies have demonstrated that less intuitive features such as mutational status and molecular subtype can be predicted through quantitative analysis of histology. This talk will focus on several approaches to analyze histology to improve the characterization and treatment of breast cancer. In particular, we will discuss approaches to approximate standard gene expression signatures used to determine need for chemotherapy using histology alone, approaches to precisely characterize the immune microenvironment to predict response to therapy, and the use of generative adversarial networks for explainability.

Dr. Howard’s research focuses on answering several important questions at the intersection of digital health and breast medical oncology: 1) Can artificial intelligence be used to identify good responders to standard neoadjuvant chemotherapy to better personalize treatment decisions? 2) Can deep learning use readily available pathologic and imaging data to improve upon or supplement existing genomic biomarkers in breast cancer in order to reduce cost, prevent unnecessary treatment delays, and improve access to biomarkers? and 3) Given the rapid growth of big data / artificial intelligence tools in oncology, what safeguards need to be in place to ensure these tools do not recapitulate healthcare disparities that are currently prevalent in cancer care?

Parking
Campus North Parking
5505 S Ellis Ave
Map It

arrow-left-smallarrow-right-large-greyarrow-right-large-yellowarrow-right-largearrow-right-long-yellowarrow-right-smallclosefacet-arrow-down-whitefacet-arrow-downCheckedCheckedlink-outmag-glass