1
|
Skrede OJ, De Raedt S, Kleppe A, Hveem TS, Liestøl K, Maddison J, Askautrud HA, Pradhan M, Nesheim JA, Albregtsen F, Farstad IN, Domingo E, Church DN, Nesbakken A, Shepherd NA, Tomlinson I, Kerr R, Novelli M, Kerr DJ, Danielsen HE. Deep learning for prediction of colorectal cancer outcome: a discovery and validation study. Lancet 2020; 395:350-360. [PMID: 32007170 DOI: 10.1016/s0140-6736(19)32998-8] [Citation(s) in RCA: 275] [Impact Index Per Article: 68.8] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 06/15/2019] [Revised: 10/28/2019] [Accepted: 11/11/2019] [Indexed: 02/07/2023]
Abstract
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.
Collapse
Affiliation(s)
- Ole-Johan Skrede
- Institute for Cancer Genetics and Informatics, Oslo University Hospital, Oslo, Norway; Department of Informatics, University of Oslo, Oslo, Norway
| | - Sepp De Raedt
- Institute for Cancer Genetics and Informatics, Oslo University Hospital, Oslo, Norway; Department of Informatics, University of Oslo, Oslo, Norway
| | - Andreas Kleppe
- Institute for Cancer Genetics and Informatics, Oslo University Hospital, Oslo, Norway; Department of Informatics, University of Oslo, Oslo, Norway
| | - Tarjei S Hveem
- Institute for Cancer Genetics and Informatics, Oslo University Hospital, Oslo, Norway
| | - Knut Liestøl
- Institute for Cancer Genetics and Informatics, Oslo University Hospital, Oslo, Norway; Department of Informatics, University of Oslo, Oslo, Norway
| | - John Maddison
- Institute for Cancer Genetics and Informatics, Oslo University Hospital, Oslo, Norway
| | - Hanne A Askautrud
- Institute for Cancer Genetics and Informatics, Oslo University Hospital, Oslo, Norway
| | - Manohar Pradhan
- Institute for Cancer Genetics and Informatics, Oslo University Hospital, Oslo, Norway
| | - John Arne Nesheim
- Institute for Cancer Genetics and Informatics, Oslo University Hospital, Oslo, Norway
| | - Fritz Albregtsen
- Institute for Cancer Genetics and Informatics, Oslo University Hospital, Oslo, Norway; Department of Informatics, University of Oslo, Oslo, Norway
| | - Inger Nina Farstad
- Department of Pathology, Division of Laboratory Medicine, Oslo University Hospital, Oslo, Norway; Institute of Clinical Medicine, University of Oslo, Oslo, Norway
| | - Enric Domingo
- Department of Oncology, University of Oxford, Oxford, UK
| | - David N Church
- Wellcome Centre for Human Genetics, University of Oxford, Oxford, UK; National Institute of Health Research Oxford Biomedical Research Centre, Oxford University Hospitals NHS Foundation Trust, John Radcliffe Hospital, Oxford, UK
| | - Arild Nesbakken
- Department of Gastrointestinal Surgery, Oslo University Hospital, Oslo, Norway; Institute of Clinical Medicine, University of Oslo, Oslo, Norway; KG Jebsen Colorectal Cancer Research Centre, Oslo, Norway
| | - Neil A Shepherd
- Gloucestershire Cellular Pathology Laboratory, Cheltenham General Hospital, Cheltenham, UK
| | - Ian Tomlinson
- Institute for Cancer Genetics and Informatics, Oslo University Hospital, Oslo, Norway; Edinburgh Cancer Research Centre, University of Edinburgh, Edinburgh, UK
| | - Rachel Kerr
- Department of Oncology, University of Oxford, Oxford, UK
| | - Marco Novelli
- Institute for Cancer Genetics and Informatics, Oslo University Hospital, Oslo, Norway; Department of Informatics, University of Oslo, Oslo, Norway; Research Department of Pathology, University College London Medical School, London, UK
| | - David J Kerr
- Nuffield Division of Clinical Laboratory Sciences, University of Oxford, Oxford, UK
| | - Håvard E Danielsen
- Institute for Cancer Genetics and Informatics, Oslo University Hospital, Oslo, Norway; Department of Informatics, University of Oslo, Oslo, Norway; Nuffield Division of Clinical Laboratory Sciences, University of Oxford, Oxford, UK.
| |
Collapse
|
2
|
Shivapurkar N, Weiner LM, Marshall JL, Madhavan S, Deslattes Mays A, Juhl H, Wellstein A. Recurrence of early stage colon cancer predicted by expression pattern of circulating microRNAs. PLoS One 2014; 9:e84686. [PMID: 24400111 PMCID: PMC3882238 DOI: 10.1371/journal.pone.0084686] [Citation(s) in RCA: 45] [Impact Index Per Article: 4.5] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/19/2013] [Accepted: 11/18/2013] [Indexed: 02/06/2023] Open
Abstract
Systemic treatment of patients with early-stage cancers attempts to eradicate occult metastatic disease to prevent recurrence and increased morbidity. However, prediction of recurrence from an analysis of the primary tumor is limited because disseminated cancer cells only represent a small subset of the primary lesion. Here we analyze the expression of circulating microRNAs (miRs) in serum obtained pre-surgically from patients with early stage colorectal cancers. Groups of five patients with and without disease recurrence were used to identify an informative panel of circulating miRs using quantitative PCR of genome-wide miR expression as well as a set of published candidate miRs. A panel of six informative miRs (miR-15a, mir-103, miR-148a, miR-320a, miR-451, miR-596) was derived from this analysis and evaluated in a separate validation set of thirty patients. Hierarchical clustering of the expression levels of these six circulating miRs and Kaplan-Meier analysis showed that the risk of disease recurrence of early stage colon cancer can be predicted by this panel of miRs that are measurable in the circulation at the time of diagnosis (P = 0.0026; Hazard Ratio 5.4; 95% CI of 1.9 to 15).
Collapse
Affiliation(s)
- Narayan Shivapurkar
- Lombardi Cancer Center, Georgetown University, Washington, District of Columbia, United States of America
- * E-mail: (NS); (AW)
| | - Louis M. Weiner
- Lombardi Cancer Center, Georgetown University, Washington, District of Columbia, United States of America
| | - John L. Marshall
- Lombardi Cancer Center, Georgetown University, Washington, District of Columbia, United States of America
| | - Subha Madhavan
- Lombardi Cancer Center, Georgetown University, Washington, District of Columbia, United States of America
| | - Anne Deslattes Mays
- Lombardi Cancer Center, Georgetown University, Washington, District of Columbia, United States of America
| | - Hartmut Juhl
- Lombardi Cancer Center, Georgetown University, Washington, District of Columbia, United States of America
- Indivumed GmbH, Hamburg, Germany
| | - Anton Wellstein
- Lombardi Cancer Center, Georgetown University, Washington, District of Columbia, United States of America
- * E-mail: (NS); (AW)
| |
Collapse
|