Direct prediction of genetic aberrations from pathology images in gastric cancer with swarm learning

Oliver Lester Saldanha, Hannah Sophie Muti, Heike I Grabsch, Rupert Langer, Bastian Dislich, Meike Kohlruss, Gisela Keller, Marko van Treeck, Katherine Jane Hewitt, Fiona R Kolbinger, Gregory Patrick Veldhuizen, Peter Boor, Sebastian Foersch, Daniel Truhn, Jakob Nikolas Kather*

*Corresponding author for this work

Research output: Contribution to journalArticleAcademicpeer-review


BACKGROUND: Computational pathology uses deep learning (DL) to extract biomarkers from routine pathology slides. Large multicentric datasets improve performance, but such datasets are scarce for gastric cancer. This limitation could be overcome by Swarm Learning (SL).

METHODS: Here, we report the results of a multicentric retrospective study of SL for prediction of molecular biomarkers in gastric cancer. We collected tissue samples with known microsatellite instability (MSI) and Epstein-Barr Virus (EBV) status from four patient cohorts from Switzerland, Germany, the UK and the USA, storing each dataset on a physically separate computer.

RESULTS: On an external validation cohort, the SL-based classifier reached an area under the receiver operating curve (AUROC) of 0.8092 (± 0.0132) for MSI prediction and 0.8372 (± 0.0179) for EBV prediction. The centralized model, which was trained on all datasets on a single computer, reached a similar performance.

CONCLUSIONS: Our findings demonstrate the feasibility of SL-based molecular biomarkers in gastric cancer. In the future, SL could be used for collaborative training and, thus, improve the performance of these biomarkers. This may ultimately result in clinical-grade performance and generalizability.

Original languageEnglish
Pages (from-to)264-274
Number of pages11
JournalGastric Cancer
Issue number2
Early online date20 Oct 2022
Publication statusPublished - Mar 2023


Dive into the research topics of 'Direct prediction of genetic aberrations from pathology images in gastric cancer with swarm learning'. Together they form a unique fingerprint.

Cite this