Daniela Raicu presents Learning with uncertain labels: advances and applications

Topic:

Learning with uncertain labels: advances and applications in computer-aided diagnosis

Abstract:

Traditionally, image studies evaluating the effectiveness of computer aided diagnosis (CAD) systems use a single label from a medical expert compared with a single predicted label from the CAD system. However, the situation can be more complicated. In fact, the disagreement among medical experts in providing diagnosis is recognized as a complicating factor in such evaluations, and it has been recommended that ignoring this disagreement reduces the validity of such analyses. In this talk, I will present recent research in the area of learning with uncertain labels from the Medical Informatics (MedIX) research lab at DePaul University. While the talk will focus on the research advances in the medical field, the presented research can be applied to any field where completely reliable labels are expensive and difficult to obtain.

About Daniela:

Daniela Stan Raicu is an Associate Professor of School of Computing, College of Computing and Digital Media at DePaul University, Chicago. She is the co-director of the Medical Informatics and the Intelligent Multimedia Processing Laboratories, and the Director of the Data Mining and Predictive Analytics Center at DePaul. Her research interests include medical imaging, multimedia retrieval, pattern recognition and data mining. Daniela's projects have been funded by the National Science Foundation (NSF), Argonne National Laboratory, Department of Education, and McArthur Foundation. She is the recipient of the DePaul Excellence in Teaching Award 2008 and the DePaul Spirit of Inquiry Award in 2010. She also serves on the National Council of the Upsilon Pi Epsilon (UPE) honor society in Computer and Information Sciences since 2008. Daniela holds a Ph.D. in Computer Science from Oakland University, Michigan, a M.A. in Computer Science from Wayne State University, Michigan, and a B.S. in Mathematics from University of Bucharest, Romania.