About the Talk
Presenter
Prof. Dr. Çiğdem Gündüz Demir
Çiğdem Gündüz Demir received her BSc and MS degrees in computer engineering from Boğaziçi University in 1999 and 2001 respectively, and her PhD in computer science from Rensselaer Polytechnic Institute in 2005. She is currently Professor of Computer Engineering at Koç University and Associate Director of the KUIS AI Center. Before joining Koç University she was a faculty member in the Department of Computer Engineering at Bilkent University. She is a recipient of the Turkish Academy of Sciences Distinguished Young Scientist Award and the CAREER Award of the Scientific and Technological Research Council of Türkiye.
Abstract
Automated imaging systems are becoming important tools for medical and biological research, as they facilitate rapid analyses with better reproducibility. Segmenting the regions of interest on a medical image is typically one of the first but most critical steps of these systems. In this talk, I will briefly touch on the main challenges of segmentation tasks in medical image analysis and then present examples of dense prediction networks that my research group has designed and implemented to overcome these challenges. In particular, I will talk about our proposed network architectures and loss functions, specifically designed to facilitate better training of segmentation networks.
Date: April 27th, 2021 – 6:00 PM (GMT+3)
Language: English