Deep learning for multi-class semantic segmentation enables colorectal cancer detection and classification in digital pathology images

Scientific Reports, vol. 13, pp. 8398

Abstract

In colorectal cancer (CRC), artificial intelligence (AI) can alleviate the laborious task of characterization and reporting on resected biopsies, including polyps, the numbers of which are increasing as a result of CRC population screening programs ongoing in many countries all around the globe. Here, we present an approach to address two major challenges in the automated assessment of CRC histopathology whole-slide images. We present an AI-based method to segment multiple ([Formula: see text]) tissue compartments in the H &E-stained whole-slide image, which provides a different, more perceptible picture of tissue morphology and composition. We test and compare a panel of state-of-the-art loss functions available for segmentation models, and provide indications about their use in histopathology image segmentation, based on the analysis of (a) a multi-centric cohort of CRC cases from five medical centers in the Netherlands and Germany, and (b) two publicly available datasets on segmentation in CRC. We used the best performing AI model as the basis for a computer-aided diagnosis system that classifies colon biopsies into four main categories that are relevant pathologically. We report the performance of this system on an independent cohort of more than 1000 patients. The results show that with a good segmentation network as a base, a tool can be developed which can support pathologists in the risk stratification of colorectal cancer patients, among other possible uses. We have made the segmentation model available for research use on https://grand-challenge.org/algorithms/colon-tissue-segmentation/ .

Authors 8

1. John‐Melle Bokhorst corresponding

   Radboud University Nijmegen · Radboud University Medical Center

   Affiliation as printed

   Department of pathology, Radboud University Medical Center, Nijmegen, The Netherlands. john-melle.bokhorst@radboudumc.nl

   Department of pathology, Radboud University Medical Center, Nijmegen, The Netherlands

2. Irıs D. Nagtegaal

   Radboud University Nijmegen · Radboud University Medical Center

   Affiliation as printed

   Department of pathology, Radboud University Medical Center, Nijmegen, The Netherlands

3. Filippo Fraggetta
   Affiliation as printed

   Pathology Unit Gravina Hospital, Gravina Hospital, Caltagirone, Italy

4. Simona Vatrano
   Affiliation as printed

   Pathology Unit Gravina Hospital, Gravina Hospital, Caltagirone, Italy

5. Wilma E. Mesker Aachen

   Leiden University Medical Center

   Affiliation as printed

   Leids Universitair Medisch Centrum, Leiden, The Netherlands

6. Michael Vieth

   Friedrich-Alexander-Universität Erlangen-Nürnberg · Bayreuth Medical Center

   Affiliation as printed

   Klinikum Bayreuth, Friedrich-Alexander-University Erlangen-Nuremberg, Bayreuth, Germany

7. Jeroen van der Laak

   Linköping University · Radboud University Nijmegen · Radboud University Medical Center

   Affiliation as printed

   Center for Medical Image Science and Visualization, Linköping University, Linköping, Sweden

   Department of pathology, Radboud University Medical Center, Nijmegen, The Netherlands

8. Francesco Ciompi

   Radboud University Nijmegen · Radboud University Medical Center

   Affiliation as printed

   Department of pathology, Radboud University Medical Center, Nijmegen, The Netherlands