Deep learning for prediction of colorectal cancer outcome: a discovery and validation study. Issue 10221 (1st February 2020)

• Record Type: Journal Article
• Authors: Skrede, Ole-Johan; De Raedt, Sepp; Kleppe, Andreas; Hveem, Tarjei S; Liestøl, Knut; Maddison, John; Askautrud, Hanne A; Pradhan, Manohar; Nesheim, John Arne; Albregtsen, Fritz; Farstad, Inger Nina; Domingo, Enric; Church, David N; Nesbakken, Arild; Shepherd, Neil A; Tomlinson, Ian; Kerr, Rachel; Novelli, Marco; Kerr, David J; Danielsen, Håvard E
• Is Part Of: Lancet. Volume 395:Issue 10221(2019)
• Page Start: 350
• Page End: 360
• Publication Date: 2020-02-01
• Subjects: Medicine -- Periodicals; Medicine -- Periodicals; Medicine; Medicine; Electronic journals; Periodicals; 610.5
• DOI: 10.1016/S0140-6736(19)32998-8
• Languages: English
• ISSNs: 0140-6736

Abstract

Summary: Background: Improved markers of prognosis are needed to stratify patients with early-stage colorectal cancer to refine selection of adjuvant therapy. The aim of the present study was to develop a biomarker of patient outcome after primary colorectal cancer resection by directly analysing scanned conventional haematoxylin and eosin stained sections using deep learning. Methods: More than 12 000 000 image tiles from patients with a distinctly good or poor disease outcome from four cohorts were used to train a total of ten convolutional neural networks, purpose-built for classifying supersized heterogeneous images. A prognostic biomarker integrating the ten networks was determined using patients with a non-distinct outcome. The marker was tested on 920 patients with slides prepared in the UK, and then independently validated according to a predefined protocol in 1122 patients treated with single-agent capecitabine using slides prepared in Norway. All cohorts included only patients with resectable tumours, and a formalin-fixed, paraffin-embedded tumour tissue block available for analysis. The primary outcome was cancer-specific survival. Findings: 828 patients from four cohorts had a distinct outcome and were used as a training cohort to obtain clear ground truth. 1645 patients had a non-distinct outcome and were used for tuning. The biomarker provided a hazard ratio for poor versus good prognosis of 3·84 (95% CI 2·72–5·43; p<0·0001) in the primary analysis of the validation cohort, and 3·04 (2·07–4·47; p<0·0001) after adjusting for established prognostic markers significant in univariable analyses of the same cohort, which were pN stage, pT stage, lymphatic invasion, and venous vascular invasion. Interpretation: A clinically useful prognostic marker was developed using deep learning allied to digital scanning of conventional haematoxylin and eosin stained tumour tissue sections. The assay has been extensively evaluated in large, independent patient populations, correlates with and outperforms established molecular and morphological prognostic markers, and gives consistent results across tumour and nodal stage. The biomarker stratified stage II and III patients into sufficiently distinct prognostic groups that potentially could be used to guide selection of adjuvant treatment by avoiding therapy in very low risk groups and identifying patients who would benefit from more intensive treatment regimes. Funding: The Research Council of Norway.