Direct prediction of genetic aberrations from pathology images in gastric cancer with swarm learning
Year: 2022
Type: article
Abstract: 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.
Source: Gastric Cancer
Institutions: Universitätsklinikum Aachen, Else Kröner Fresenius Center for Digital Health, Technische Universität Dresden, RWTH Aachen University, University of Leeds, Maastricht University Medical Centre, Maastricht University, University of Bern, Johannes Kepler University of Linz, University Hospital of Bern, Kepler Universitätsklinikum, Technical University of Munich, University Hospital Carl Gustav Carus, University Medical Center of the Johannes Gutenberg University Mainz, Heidelberg University, University Hospital Heidelberg, National Center for Tumor Diseases
Language: English
Topic: AI in cancer detection
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: hybrid
Estimated APC paid: $4,790
Awards: G1569319872, Translationale Nephropathologie, G176063892, Die Rolle von epithelialen CD74 in Nierenerkrankungen, STOP-FSGS - Translationaler Forschungsverbund zur Verbesserung der Diagnostik und Therapie der FSGS, TP 1: Rolle des MIF-Signalwegs bei FSGS, TP 4: Pathogenese und neue therapeutische Ansätze, G260841231, G2888424188, G2937585223, G3688241933, G4712284355, G4785148476, KFO 5011: Integration neuer Methoden zur Verbesserung von translationaler Nierenforschung, G6037373127, G6098565189, AI-augmented, Multiscale Image-based Diagnostics of Chronic Kidney Disease, G8153940597, Verbund PEARL - Prävention von Darmkrebs im jungen und mittleren Erwachsenenalter - Standort Dresden, TRR 219: Mechanismen kardiovaskulärer Komplikationen bei chronischer Niereninsuffizienz, G8808717806, G916432086
OpenAlex ID: W4306914119
