Life Sciences and Health Arkadiy Dushatskiy, Michelle Sweering

Data variation-aware medical image segmentation

Join Zoom Meeting

Meeting ID: 815 3524 9101
Passcode: 967201

Title:      Data variation-aware medical image segmentation
Speaker:    Arkadiy Dushatskiy
Abstract:   Deep learning algorithms have become the golden standard for segmentation of medical imaging data. In most works, the variability and heterogeneity of real clinical data is acknowledged to still be a problem. One way to automatically overcome this is to capture and exploit this variation explicitly. Here, we propose an approach that improves on our previous work in this area and explain how it potentially can improve clinical acceptance of (semi-)automatic segmentation methods. In experiments with a real clinical dataset of CT scans with prostate segmentations, our approach provides an improvement of several percentage points in terms of Dice and surface Dice coefficients compared to a standard Deep Learning approach. Noticeably, the largest improvement occurs in the upper part of the prostate that is known to be most prone to inter-observer segmentation variation.

Title:      Making de Bruijn Graphs Eulerian via Near-Optimal Algorithms for Connecting and Balancing
Speaker:    Michelle Sweering