Buchumschlag

Generalizable biomarker prediction from cancer pathology slides with self-supervised deep learning: a retrospective multi-centric study

Deep learning (DL) can predict microsatellite instability (MSI) from routine histopathology slides of colorectal cancer (CRC). However, it is unclear whether DL can also predict other biomarkers with high performance and whether DL predictions generalize to external patient populations. Here, we acq...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Niehues, Jan Moritz (VerfasserIn) , Quirke, Philip (VerfasserIn) , West, Nicholas P. (VerfasserIn) , Grabsch, Heike I. (VerfasserIn) , van Treeck, Marko (VerfasserIn) , Schirris, Yoni (VerfasserIn) , Veldhuizen, Gregory P. (VerfasserIn) , Hutchins, Gordon G. A. (VerfasserIn) , Richman, Susan D. (VerfasserIn) , Foersch, Sebastian (VerfasserIn) , Brinker, Titus Josef (VerfasserIn) , Fukuoka, Junya (VerfasserIn) , Bychkov, Andrey (VerfasserIn) , Uegami, Wataru (VerfasserIn) , Truhn, Daniel (VerfasserIn) , Brenner, Hermann (VerfasserIn) , Brobeil, Alexander (VerfasserIn) , Hoffmeister, Michael (VerfasserIn) , Kather, Jakob Nikolas (VerfasserIn)
Dokumenttyp: Article (Journal)
Sprache:Englisch
Veröffentlicht: 18 April 2023
In: Cell reports. Medicine
Year: 2023, Jahrgang: 4, Heft: 4, Pages: 1-16
ISSN:2666-3791
DOI:10.1016/j.xcrm.2023.100980
Online-Zugang:Verlag, lizenzpflichtig, Volltext: https://doi.org/10.1016/j.xcrm.2023.100980
Verlag, lizenzpflichtig, Volltext: https://www.sciencedirect.com/science/article/pii/S2666379123000861
Volltext
Verfasserangaben:Jan Moritz Niehues, Philip Quirke, Nicholas P. West, Heike I. Grabsch, Marko van Treeck, Yoni Schirris, Gregory P. Veldhuizen, Gordon G.A. Hutchins, Susan D. Richman, Sebastian Foersch, Titus J. Brinker, Junya Fukuoka, Andrey Bychkov, Wataru Uegami, Daniel Truhn, Hermann Brenner, Alexander Brobeil, Michael Hoffmeister, and Jakob Nikolas Kather
Beschreibung
Zusammenfassung:Deep learning (DL) can predict microsatellite instability (MSI) from routine histopathology slides of colorectal cancer (CRC). However, it is unclear whether DL can also predict other biomarkers with high performance and whether DL predictions generalize to external patient populations. Here, we acquire CRC tissue samples from two large multi-centric studies. We systematically compare six different state-of-the-art DL architectures to predict biomarkers from pathology slides, including MSI and mutations in BRAF, KRAS, NRAS, and PIK3CA. Using a large external validation cohort to provide a realistic evaluation setting, we show that models using self-supervised, attention-based multiple-instance learning consistently outperform previous approaches while offering explainable visualizations of the indicative regions and morphologies. While the prediction of MSI and BRAF mutations reaches a clinical-grade performance, mutation prediction of PIK3CA, KRAS, and NRAS was clinically insufficient.
Beschreibung: Online verfügbar 22 March 2023, Version des Artikels 18 April 2023
Gesehen am 09.08.2023
Beschreibung:Online Resource
ISSN:2666-3791
DOI:10.1016/j.xcrm.2023.100980

Ähnliche Einträge