Journal Article

DKFZ-2023-00592

http://join2-wiki.gsi.de/foswiki/pub/Main/Artwork/join2_logo100x88.png Generalizable biomarker prediction from cancer pathology slides with self-supervised deep learning: A retrospective multi-centric study.

Niehues, J. M. ; Quirke, P. ; West, N. P. ; Grabsch, H. I. ; van Treeck, M. ; Schirris, Y. ; Veldhuizen, G. P. ; Hutchins, G. G. A. ; Richman, S. D. ; Foersch, S. ; Brinker, T.DKFZ* ; Fukuoka, J. ; Bychkov, A. ; Uegami, W. ; Truhn, D. ; Brenner, H.DKFZ* ; Brobeil, A. ; Hoffmeister, M.DKFZ* ; Kather, J. N.

2023
Elsevier Maryland Heights, MO

This record in other databases:  

Please use a persistent id in citations: doi:10.1016/j.xcrm.2023.100980

Abstract: 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.

Keyword(s): artificial intelligence ; attention heatmaps ; attention-based multiple-instance learning ; biomarker ; colorectal cancer ; computational pathology ; multi-input models ; oncogenic mutation ; self-supervised learning

---

Contributing Institute(s):

1. NWG Digitale Biomarker in der Onkologie (C140)
2. C070 Klinische Epidemiologie und Alternf. (C070)
3. Präventive Onkologie (C120)
4. DKTK HD zentral (HD01)

Research Program(s):

1. 313 - Krebsrisikofaktoren und Prävention (POF4-313) (POF4-313)

Appears in the scientific report 2023

---

Database coverage:
; ; Article Processing Charges ; BIOSIS Previews ; Biological Abstracts ; Clarivate Analytics Master Journal List ; Current Contents - Clinical Medicine ; Current Contents - Life Sciences ; DOAJ Seal ; Essential Science Indicators ; Fees ; IF >= 10 ; JCR ; PubMed Central ; SCOPUS ; Science Citation Index Expanded ; Web of Science Core Collection

---