Digital Pathology

Pathologists study tissue morphology in order to correctly diagnose diseases such as colorectal cancer. They look at slices of tissue on glas slides under a microscope. Nowadays these slides are also digitized and used for medical image analysis. All sorts of computer vision and machine learning methods are being developped to support the diagnostic process.


We apply novel graph-based and deep learning methods to colorectal cancer images to provide methods for computer-aided diagnostics and to better understand tumor bud and T-Lymphocyte interactions.

This graph captures the interaction of lymphocytes and tumor buds 



Intestinal Gland Classification using Graph Edit Distance (GED) 



Projects involving Digital Pathology

BTS Project