Summer publications of the CMMI/Special focus: research in image analysis conducted by the DIAPath team of the CMMI

Image analysis is one of the strong points of our digital pathology team DIAPath. In a recent article, our colleagues at DIAPath explain how they used deep learning and data augmentation techniques to automate annotation of histological slide images from colorectal tissue. Their method segments glandular epithelium in images from tissue slides stained with hemaetoxylin & eosin or by immunohistochemistry (IHC). It is robust, outperforms pre-existing methods and concurs highly with manual annotations, thereby enabling the compatimentalization of IHC quantification.

Segmentation of glandular epithelium in colorectal tumours to automatically compartmentalise IHC biomarker quantification: A deep learning approach.
Van Eycke YR, Balsat C, Verset L, Debeir O, Salmon I, Decaestecker C.
Med Image Anal. 2018 Jul 12;49:35-45.