Deep learning for prediction of colorectal cancer outcome: a discovery and validation study.

By O. Skrede, S. De Raedt, A. Kleppe, T. Hveem, K. Liestøl, J. Maddison, H. Askautrud, M. Pradhan, J. A. Nesheim, F. Albregtsen and 10 more. The Lancet, 2020

492 citations recorded by the source corpus.

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.

Subfields: Artificial Intelligence, Oncology, Radiology, Nuclear Medicine and Imaging

View Paper: https://www.semanticscholar.org/paper/541a46ebc27fd3c706374e6bebee6d8e17f2d77d

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Oncology

In Radiology, Nuclear Medicine and Imaging

Citations in the corpus

Artificial Intelligence in Cancer Research and Precision Medicine (2021, result): “…cancer (AUC, 0.71); multivariate survival analysis between patient groups stratified based on the model’s predictions shows that the patients predicted to have a poor prognosis indeed had poor cancer-specific survival (adjusted HR, 3.04) compared with those with predicted good prognosis (105).”
Scaling Vision Transformers to Gigapixel Images via Hierarchical Self-Supervised Learning (2022, methodology): “In modeling important long-range dependencies between instances using self-attention across various stages of the hierarchy, the Transformer attention in HIPT is able to capture regional perturbations that have been well characterized as portending worse outcome across different cancer types, as fur”
Artificial intelligence in histopathology: enhancing cancer research and clinical oncology (2022, background): “Such approaches can generate accurate risk scores in hepatocellular carcinoma 38 , colorectal cancer 49,50 , mesothelioma 51 and brain tumors 52 among other tumor types.”
Artificial intelligence in drug development (2025, unknown): “Robust validation and responsible data curation will facilitate biomarker identification and application, supporting future drug development and disease treatment.”
A review of deep learning in medical imaging: Imaging traits, technology trends, case studies with progress highlights, and future promises (2020, methodology): “[228] perform a large study of DL involving over 12M pathology image tiles from over 2000 patients to predict cancerspecific survival in early stage colorectal cancer patients.”