Graph-based classification of intestinal glands in colorectal cancer tissue images

Studer, Linda (DIVA Research Group, University of Fribourg, Fribourg, Switzerland ; School of Engineering and Architecture (HEIA-FR), HES-SO // University of Applied Sciences Western Switzerland) ; Toneyan, Shushan (Institute of Pathology, University of Bern, Bern, Switzerland) ; Zlobec, Inti (Institute of Pathology, University of Bern, Bern Switzerland) ; Dawson, Heather (Institute of Pathology, University of Bern, Bern, Switzerland) ; Fischer, Andreas (DIVA Research Group, University of Fribourg, Fribourg, Switzerland ; School of Engineering and Architecture (HEIA-FR), HES-SO // University of Applied Sciences Western Switzerland)

Pathologists study tissue morphology in order to correctly diagnose diseases such as colorectal cancer. This task can be very time consuming, and automated systems can greatly improve the precision and speed with which a diagnosis is established. Explainable algorithms and results are key to successful implementation of these methods into routine diagnostics in the medical field. In this paper, we propose a graphbased approach for intestinal gland classification. It leverages the high representational power of graphs for describing geometrical and topological properties of the glands. A novel, publicly available image and graph dataset is introduced based on cell segmentation of healthy and dysplastic H&E stained intestinal glands from pT1 colorectal cancer. The graphs are compared using an approximate graph edit distance and are classified using the k-nearest neighbours algorithm. With this method, we achieve a classification accuracy of 83.3%.


Keywords:
Conference Type:
full paper
Faculty:
Ingénierie et Architecture
School:
HEIA-FR
Institute:
iCoSys - Institut des systèmes complexes
Publisher:
Shenzhen, China, 13-17 October 2019
Date:
2019-10
Shenzhen, China
13-17 October 2019
Pagination:
8 p.
Published in:
Proceedings of MICCAI 2019, 13-17 October 2019, Shenzhen, China
Appears in Collection:



 Record created 2020-01-17, last modified 2020-01-21

Fulltext:
Download fulltext
PDF

Rate this document:

Rate this document:
1
2
3
 
(Not yet reviewed)