4:30–6:00 pm
William Eckhardt Research Center, Room 401 5640 S. Ellis Avenue, Chicago, IL 60637
Lee Cooper, Northwestern University
"Transparent modeling of invasive breast cancer outcomes from history"
Organized by the University of Chicago’s Eric and Wendy Schmidt AI in Science Postdoctoral Fellowship Program.
Histologic grading of breast cancers is a time-honored practice that evaluates characteristics of cancer epithelium. The subjectivity of grading by pathologists can result in suboptimal clinical management of patients diagnosed with invasive breast cancer. Furthermore, despite evidence that stroma and immune cells play an important role in biology and prognosis, these elements are currently not evaluated in routine grading. This talk will describe the development and validation of a prognostic model built on interpretable features of epithelial, stromal, and immune cells made from digital images of pathology slides. The Histomic Prognostic Signature (HiPS) is built from 26 thematic features to explain breast cancer specific survival in the Cancer Prevention Study-II cohort. Validation in additional datasets indicates that HiPS improves prediction of clinical outcomes and relies heavily on stromal and immune features. The molecular correlates of these features suggest that they capture the strength and composition of immune response as well as subtypes of cancer-associated fibroblasts. Adoption of HiPS could provide patients diagnosed with breast cancers with a more accurate estimate of the risk associated with their disease, empowering them to make informed decisions about their clinical care.
4:30pm – 5:15pm: Presentation
5:15pm – 5:30pm: Q&A
5:30pm – 6:00pm: Reception
Meeting location
William Eckhardt Research Center, Room 401
5640 S Ellis Avenue, Chicago, IL 60637
Map It
Lee Cooper, PhD: Dr. Cooper received his PhD in Electrical and Computer Engineering from Ohio State University in 2009. He joined the Biomedical Informatics faculty at Emory University in 2012 where he was jointly appointed with Biomedical Engineering at Georgia Institute of Technology. He joined the department of pathology at Northwestern in 2019 as an Associate Professor and Director of Computational Pathology.
My lab focuses on the applications of machine learning in cancer and fundamental research in machine learning. We develop algorithms to predict clinical outcomes from genomic, imaging, and histopathology data, and to extract quantitative phenotypic information from digital pathology images. Our work has produced a number of software tools that enable researchers to manage large and complex datasets and to interact with these data using machine learning algorithms. Our goal is to improve the quality of predictions used in clinical management and to provide investigators with new tools for basic and clinical science. Our research has been funded by NLM, NCI, NIBIB, NINDS, and industry and foundation sources,
Parking
Campus North Parking
5505 S Ellis Avenue, Chicago, IL 60637
Map It