Self-supervised learning reveals clinically relevant histomorphological patterns for therapeutic strategies in colon cancer
Nature Communications, vol. 16, pp. 2328
Abstract
Self-supervised learning (SSL) automates the extraction and interpretation of histopathology features on unannotated hematoxylin-and-eosin-stained whole-slide images (WSIs). We trained an SSL Barlow Twins-encoder on 435 TCGA colon adenocarcinoma WSIs to extract features from small image patches. Leiden community detection then grouped tiles into histomorphological phenotype clusters (HPCs). HPC reproducibility and predictive ability for overall survival was confirmed in an independent clinical trial cohort (N=1213 WSIs). This unbiased atlas resulted in 47 HPCs displaying unique and sharing clinically significant histomorphological traits, highlighting tissue type, quantity, and architecture, especially in the context of tumor stroma. Through in-depth analysis of these HPCs, including immune landscape and gene set enrichment analysis, and association to clinical outcomes, we shed light on the factors influencing survival and responses to treatments like standard adjuvant chemotherapy and experimental therapies. Further exploration of HPCs may unveil new insights and aid decision-making and personalized treatments for colon cancer patients.
Authors 13
-
Karolinska Institutet · New York University
Affiliation as printed
Applied Bioinformatics Laboratories, New York University Grossman School of Medicine, New York, NY, USA
Department of Medical Epidemiology and Biostatistics, Karolinska Institutet, Karolinska, Sweden
-
Leiden University Medical Center
Affiliation as printed
Department of Surgery, Leiden University Medical Center, Leiden, The Netherlands
-
Affiliation as printed
Applied Bioinformatics Laboratories, New York University Grossman School of Medicine, New York, NY, USA
Department of Cell Biology, New York University Grossman School of Medicine, New York, NY, USA
-
Affiliation as printed
Department of Computing Science, University of Glasgow, Glasgow, United Kingdom
-
Affiliation as printed
Applied Bioinformatics Laboratories, New York University Grossman School of Medicine, New York, NY, USA
-
Affiliation as printed
Applied Bioinformatics Laboratories, New York University Grossman School of Medicine, New York, NY, USA
-
Affiliation as printed
Department of Pathology, New York University Grossman School of Medicine, New York, NY, USA
-
Leiden University Medical Center
Affiliation as printed
Department of Pathology, Leiden University Medical Center, Leiden, The Netherlands
-
Radboud University Medical Center
Affiliation as printed
Department of Pathology, Radboud University Medical Center, Nijmegen, The Netherlands
-
Affiliation as printed
Department of Computing Science, University of Glasgow, Glasgow, United Kingdom
School of Cancer Sciences, University of Glasgow, Glasgow, Scotland, UK
-
Leiden University Medical Center
Affiliation as printed
Department of Surgery, Leiden University Medical Center, Leiden, The Netherlands
-
Leiden University Medical Center
Affiliation as printed
Department of Surgery, Leiden University Medical Center, Leiden, The Netherlands
-
Aristotelis Tsirigos corresponding
NYU Langone Health · New York University
Affiliation as printed
Applied Bioinformatics Laboratories, New York University Grossman School of Medicine, New York, NY, USA. Aristotelis.Tsirigos@nyulangone.org
Department of Pathology, New York University Grossman School of Medicine, New York, NY, USA. Aristotelis.Tsirigos@nyulangone.org
Applied Bioinformatics Laboratories, New York University Grossman School of Medicine, New York, NY, USA
Department of Pathology, New York University Grossman School of Medicine, New York, NY, USA
Cited by 24 stored of 24
No patents citing this paper on Lens.org (checked 2026-10-11).