{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,2]],"date-time":"2026-06-02T04:05:45Z","timestamp":1780373145724,"version":"3.54.1"},"reference-count":57,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2021,4,19]],"date-time":"2021-04-19T00:00:00Z","timestamp":1618790400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2021,4,19]],"date-time":"2021-04-19T00:00:00Z","timestamp":1618790400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/100006785","name":"Google","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100006785","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["npj Digit. Med."],"abstract":"<jats:title>Abstract<\/jats:title><jats:p>Deriving interpretable prognostic features from deep-learning-based prognostic histopathology models remains a challenge. In this study, we developed a deep learning system (DLS) for predicting disease-specific survival for stage II and III colorectal cancer using 3652 cases (27,300 slides). When evaluated on two validation datasets containing 1239 cases (9340 slides) and 738 cases (7140 slides), respectively, the DLS achieved a 5-year disease-specific survival AUC of 0.70 (95% CI: 0.66\u20130.73) and 0.69 (95% CI: 0.64\u20130.72), and added significant predictive value to a set of nine clinicopathologic features. To interpret the DLS, we explored the ability of different human-interpretable features to explain the variance in DLS scores. We observed that clinicopathologic features such as T-category, N-category, and grade explained a small fraction of the variance in DLS scores (<jats:italic>R<\/jats:italic><jats:sup>2<\/jats:sup>\u2009=\u200918% in both validation sets). Next, we generated human-interpretable histologic features by clustering embeddings from a deep-learning-based image-similarity model and showed that they explained the majority of the variance (<jats:italic>R<\/jats:italic><jats:sup>2<\/jats:sup>of 73\u201380%). Furthermore, the clustering-derived feature most strongly associated with high DLS scores was also highly prognostic in isolation. With a distinct visual appearance (poorly differentiated tumor cell clusters adjacent to adipose tissue), this feature was identified by annotators with 87.0\u201395.5% accuracy. Our approach can be used to explain predictions from a prognostic deep learning model and uncover potentially-novel prognostic features that can be reliably identified by people for future validation studies.<\/jats:p>","DOI":"10.1038\/s41746-021-00427-2","type":"journal-article","created":{"date-parts":[[2021,4,19]],"date-time":"2021-04-19T10:04:56Z","timestamp":1618826696000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":203,"title":["Interpretable survival prediction for colorectal cancer using deep learning"],"prefix":"10.1038","volume":"4","author":[{"given":"Ellery","family":"Wulczyn","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"David F.","family":"Steiner","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Melissa","family":"Moran","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2718-7648","authenticated-orcid":false,"given":"Markus","family":"Plass","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8439-3689","authenticated-orcid":false,"given":"Robert","family":"Reihs","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fraser","family":"Tan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Isabelle","family":"Flament-Auvigne","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Trissia","family":"Brown","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1371-1595","authenticated-orcid":false,"given":"Peter","family":"Regitnig","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0083-4991","authenticated-orcid":false,"given":"Po-Hsuan Cameron","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Narayan","family":"Hegde","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Apaar","family":"Sadhwani","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Robert","family":"MacDonald","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Benny","family":"Ayalew","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Greg S.","family":"Corrado","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lily H.","family":"Peng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5315-8539","authenticated-orcid":false,"given":"Daniel","family":"Tse","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9691-4872","authenticated-orcid":false,"given":"Heimo","family":"M\u00fcller","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhaoyang","family":"Xu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4079-8275","authenticated-orcid":false,"given":"Yun","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1402-6749","authenticated-orcid":false,"given":"Martin C.","family":"Stumpe","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5299-7218","authenticated-orcid":false,"given":"Kurt","family":"Zatloukal","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0816-3395","authenticated-orcid":false,"given":"Craig H.","family":"Mermel","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2021,4,19]]},"reference":[{"key":"427_CR1","doi-asserted-by":"crossref","first-page":"93","DOI":"10.3322\/caac.21388","volume":"67","author":"MB Amin","year":"2017","unstructured":"Amin, M. B. et al. The Eighth Edition AJCC Cancer Staging Manual: Continuing to build a bridge from a population-based to a more \u201cpersonalized\u2019\u2018 approach to cancer staging. CA Cancer J. Clin. 67, 93\u201399 (2017).","journal-title":"CA Cancer J. Clin."},{"key":"427_CR2","first-page":"291","volume":"6","author":"NI Schneider","year":"2014","unstructured":"Schneider, N. I. & Langner, C. Prognostic stratification of colorectal cancer patients: current perspectives. Cancer Manag. Res. 6, 291\u2013300 (2014).","journal-title":"Cancer Manag. Res."},{"key":"427_CR3","doi-asserted-by":"crossref","first-page":"380","DOI":"10.1200\/JCO.2007.14.1291","volume":"26","author":"MR Weiser","year":"2008","unstructured":"Weiser, M. R. et al. Individualized prediction of colon cancer recurrence using a nomogram. J. Clin. Oncol. 26, 380\u2013385 (2008).","journal-title":"J. Clin. Oncol."},{"key":"427_CR4","doi-asserted-by":"crossref","first-page":"350","DOI":"10.1016\/S0140-6736(19)32998-8","volume":"395","author":"O-J Skrede","year":"2020","unstructured":"Skrede, O.-J. et al. Deep learning for prediction of colorectal cancer outcome: a discovery and validation study. Lancet 395, 350\u2013360 (2020).","journal-title":"Lancet"},{"key":"427_CR5","doi-asserted-by":"crossref","first-page":"e1002730","DOI":"10.1371\/journal.pmed.1002730","volume":"16","author":"JN Kather","year":"2019","unstructured":"Kather, J. N. et al. Predicting survival from colorectal cancer histology slides using deep learning: a retrospective multicenter study. PLoS Med. 16, e1002730 (2019).","journal-title":"PLoS Med."},{"key":"427_CR6","doi-asserted-by":"crossref","DOI":"10.1038\/s41598-018-21758-3","volume":"8","author":"D Bychkov","year":"2018","unstructured":"Bychkov, D. et al. Deep learning based tissue analysis predicts outcome in colorectal cancer. Sci. Rep. 8, 3395 (2018).","journal-title":"Sci. Rep."},{"key":"427_CR7","volume":"7","author":"K-H Yu","year":"2016","unstructured":"Yu, K.-H. et al. Predicting non-small cell lung cancer prognosis by fully automated microscopic pathology image features. Nat. Commun. 7, 12474 (2016).","journal-title":"Nat. Commun."},{"key":"427_CR8","first-page":"108ra113","volume":"3","author":"AH Beck","year":"2011","unstructured":"Beck, A. H. et al. Systematic analysis of breast cancer morphology uncovers stromal features associated with survival. Sci. Transl. Med. 3, 108ra113 (2011).","journal-title":"Sci. Transl. Med."},{"key":"427_CR9","doi-asserted-by":"crossref","first-page":"394","DOI":"10.3322\/caac.21492","volume":"68","author":"F Bray","year":"2018","unstructured":"Bray, F. et al. Global cancer statistics 2018: GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries. CA Cancer J. Clin. 68, 394\u2013424 (2018).","journal-title":"CA Cancer J. Clin."},{"key":"427_CR10","doi-asserted-by":"crossref","first-page":"2020","DOI":"10.1016\/S0140-6736(07)61866-2","volume":"370","author":"QUASAR Collaborative Group.","year":"2007","unstructured":"QUASAR Collaborative Group. Adjuvant chemotherapy versus observation in patients with colorectal cancer: a randomised study. Lancet 370, 2020\u20132029 (2007).","journal-title":"Lancet"},{"key":"427_CR11","doi-asserted-by":"crossref","first-page":"233","DOI":"10.1200\/JOP.2016.017210","volume":"13","author":"J Kannarkatt","year":"2017","unstructured":"Kannarkatt, J., Joseph, J., Kurniali, P. C., Al-Janadi, A. & Hrinczenko, B. Adjuvant chemotherapy for stage II colon cancer: a clinical dilemma. J. Oncol. Pract. 13, 233\u2013241 (2017).","journal-title":"J. Oncol. Pract."},{"key":"427_CR12","doi-asserted-by":"crossref","first-page":"3768","DOI":"10.1200\/JCO.2011.36.4539","volume":"29","author":"G Yothers","year":"2011","unstructured":"Yothers, G. et al. Oxaliplatin as adjuvant therapy for colon cancer: updated results of NSABP C-07 trial, including survival and subset analyses. J. Clin. Oncol. 29, 3768\u20133774 (2011).","journal-title":"J. Clin. Oncol."},{"key":"427_CR13","doi-asserted-by":"crossref","first-page":"837","DOI":"10.5858\/134.6.837","volume":"134","author":"G Puppa","year":"2010","unstructured":"Puppa, G., Sonzogni, A., Colombari, R. & Pelosi, G. TNM staging system of colorectal carcinoma: a critical appraisal of challenging issues. Arch. Pathol. Lab. Med. 134, 837\u2013852 (2010).","journal-title":"Arch. Pathol. Lab. Med."},{"key":"427_CR14","doi-asserted-by":"crossref","first-page":"189","DOI":"10.1007\/s00428-018-2341-1","volume":"473","author":"B Martin","year":"2018","unstructured":"Martin, B. et al. Interobserver variability in the H&E-based assessment of tumor budding in pT3\/4 colon cancer: does it affect the prognostic relevance? Virchows Arch. 473, 189\u2013197 (2018).","journal-title":"Virchows Arch."},{"key":"427_CR15","doi-asserted-by":"crossref","first-page":"1816","DOI":"10.1097\/PAS.0b013e3181816083","volume":"32","author":"EI Harris","year":"2008","unstructured":"Harris, E. I. et al. Lymphovascular invasion in colorectal cancer: an interobserver variability study. Am. J. Surg. Pathol. 32, 1816\u20131821 (2008).","journal-title":"Am. J. Surg. Pathol."},{"key":"427_CR16","doi-asserted-by":"crossref","first-page":"703","DOI":"10.1038\/s41571-019-0252-y","volume":"16","author":"K Bera","year":"2019","unstructured":"Bera, K., Schalper, K. A., Rimm, D. L., Velcheti, V. & Madabhushi, A. Artificial intelligence in digital pathology\u2014new tools for diagnosis and precision oncology. Nat. Rev. Clin. Oncol. 16, 703\u2013715 (2019).","journal-title":"Nat. Rev. Clin. Oncol."},{"key":"427_CR17","doi-asserted-by":"crossref","DOI":"10.1186\/gb-2006-7-10-r100","volume":"7","author":"AE Carpenter","year":"2006","unstructured":"Carpenter, A. E. et al. CellProfiler: image analysis software for identifying and quantifying cell phenotypes. Genome Biol. 7, R100 (2006).","journal-title":"Genome Biol."},{"key":"427_CR18","doi-asserted-by":"crossref","first-page":"1179","DOI":"10.1093\/bioinformatics\/btr095","volume":"27","author":"L Kamentsky","year":"2011","unstructured":"Kamentsky, L. et al. Improved structure, function and compatibility for CellProfiler: modular high-throughput image analysis software. Bioinformatics 27, 1179\u20131180 (2011).","journal-title":"Bioinformatics"},{"key":"427_CR19","doi-asserted-by":"crossref","first-page":"1438","DOI":"10.1038\/s41374-018-0095-7","volume":"98","author":"C Lu","year":"2018","unstructured":"Lu, C. et al. Nuclear shape and orientation features from H&E images predict survival in early-stage estrogen receptor-positive breast cancers. Lab. Investig. 98, 1438\u20131448 (2018).","journal-title":"Lab. Investig."},{"key":"427_CR20","doi-asserted-by":"crossref","first-page":"52","DOI":"10.1038\/s41746-018-0057-x","volume":"1","author":"N Dimitriou","year":"2018","unstructured":"Dimitriou, N., Arandjelovi\u0107, O., Harrison, D. J. & Caie, P. D. A principled machine learning framework improves accuracy of stage II colorectal cancer prognosis. NPJ Digit. Med. 1, 52 (2018).","journal-title":"NPJ Digit. Med."},{"key":"427_CR21","doi-asserted-by":"crossref","first-page":"1519","DOI":"10.1038\/s41591-019-0583-3","volume":"25","author":"P Courtiol","year":"2019","unstructured":"Courtiol, P. et al. Deep learning-based classification of mesothelioma improves prediction of patient outcome. Nat. Med. 25, 1519\u20131525 (2019).","journal-title":"Nat. Med."},{"key":"427_CR22","doi-asserted-by":"crossref","first-page":"E2970","DOI":"10.1073\/pnas.1717139115","volume":"115","author":"P Mobadersany","year":"2018","unstructured":"Mobadersany, P. et al. Predicting cancer outcomes from histology and genomics using convolutional networks. Proc. Natl Acad. Sci. USA 115, E2970\u2013E2979 (2018).","journal-title":"Proc. Natl Acad. Sci. USA"},{"key":"427_CR23","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1038\/s41467-018-07882-8","volume":"10","author":"Y Yamamoto","year":"2019","unstructured":"Yamamoto, Y. et al. Automated acquisition of explainable knowledge from unannotated histopathology images. Nat. Commun. 10, 1\u20139 (2019).","journal-title":"Nat. Commun."},{"key":"427_CR24","unstructured":"Simonyan, K., Vedaldi, A. & Zisserman, A. Deep inside convolutional networks: visualising image classification models and saliency maps. https:\/\/www.robots.ox.ac.uk\/~vgg\/publications\/2014\/Simonyan14a\/ (2013)."},{"key":"427_CR25","doi-asserted-by":"crossref","first-page":"56","DOI":"10.1038\/s41746-019-0131-z","volume":"2","author":"N Hegde","year":"2019","unstructured":"Hegde, N. et al. Similar image search for histopathology: SMILY. NPJ Digit. Med. 2, 56 (2019).","journal-title":"NPJ Digit. Med."},{"key":"427_CR26","doi-asserted-by":"publisher","unstructured":"Juan, D.-C. et al. Ultra Fine-Grained Image Semantic Embedding. In Proceedings of the 13th International Conference on Web Search and Data Mining. https:\/\/doi.org\/10.1145\/3336191.3371784 pp 277\u2013285 (Association for Computing Machinery, New York, NY, USA, 2020).","DOI":"10.1145\/3336191.3371784"},{"key":"427_CR27","doi-asserted-by":"crossref","first-page":"1420","DOI":"10.1093\/jnci\/djh275","volume":"96","author":"JB O\u2019Connell","year":"2004","unstructured":"O\u2019Connell, J. B., Maggard, M. A. & Ko, C. Y. Colon cancer survival rates with the new American Joint Committee on Cancer sixth edition staging. J. Natl Cancer Inst. 96, 1420\u20131425 (2004).","journal-title":"J. Natl Cancer Inst."},{"key":"427_CR28","doi-asserted-by":"crossref","first-page":"2936","DOI":"10.1200\/JCO.1995.13.12.2936","volume":"13","author":"CG Moertel","year":"1995","unstructured":"Moertel, C. G. et al. Intergroup study of fluorouracil plus levamisole as adjuvant therapy for stage II\/Dukes\u2019 B2 colon cancer. J. Clin. Oncol. 13, 2936\u20132943 (1995).","journal-title":"J. Clin. Oncol."},{"key":"427_CR29","doi-asserted-by":"crossref","first-page":"5131","DOI":"10.1200\/JCO.2009.22.4949","volume":"27","author":"C Liebig","year":"2009","unstructured":"Liebig, C. et al. Perineural invasion is an independent predictor of outcome in colorectal cancer. J. Clin. Oncol. 27, 5131\u20135137 (2009).","journal-title":"J. Clin. Oncol."},{"key":"427_CR30","doi-asserted-by":"crossref","first-page":"2128","DOI":"10.1016\/S0140-6736(18)30789-X","volume":"391","author":"F Pag\u00e8s","year":"2018","unstructured":"Pag\u00e8s, F. et al. International validation of the consensus Immunoscore for the classification of colon cancer: a prognostic and accuracy study. Lancet 391, 2128\u20132139 (2018).","journal-title":"Lancet"},{"key":"427_CR31","doi-asserted-by":"crossref","first-page":"1506","DOI":"10.1097\/PAS.0000000000000946","volume":"41","author":"H Ueno","year":"2017","unstructured":"Ueno, H. et al. Desmoplastic pattern at the tumor front defines poor-prognosis subtypes of colorectal cancer. Am. J. Surg. Pathol. 41, 1506\u20131512 (2017).","journal-title":"Am. J. Surg. Pathol."},{"key":"427_CR32","doi-asserted-by":"crossref","first-page":"781","DOI":"10.2214\/ajr.181.3.1810781","volume":"181","author":"MG Harisinghani","year":"2003","unstructured":"Harisinghani, M. G. et al. Bowel wall fat halo sign in patients without intestinal disease. AJR Am. J. Roentgenol. 181, 781\u2013784 (2003).","journal-title":"AJR Am. J. Roentgenol."},{"key":"427_CR33","doi-asserted-by":"crossref","first-page":"399","DOI":"10.1148\/radiographics.20.2.g00mc15399","volume":"20","author":"KM Horton","year":"2000","unstructured":"Horton, K. M., Corl, F. M. & Fishman, E. K. CT evaluation of the colon: inflammatory disease. Radiographics 20, 399\u2013418 (2000).","journal-title":"Radiographics"},{"key":"427_CR34","doi-asserted-by":"crossref","first-page":"341","DOI":"10.1136\/gut.2009.188946","volume":"59","author":"B Guiu","year":"2010","unstructured":"Guiu, B. et al. Visceral fat area is an independent predictive biomarker of outcome after first-line bevacizumab-based treatment in metastatic colorectal cancer. Gut 59, 341\u2013347 (2010).","journal-title":"Gut"},{"key":"427_CR35","doi-asserted-by":"crossref","first-page":"2455","DOI":"10.1158\/0008-5472.CAN-10-3323","volume":"71","author":"B Dirat","year":"2011","unstructured":"Dirat, B. et al. Cancer-associated adipocytes exhibit an activated phenotype and contribute to breast cancer invasion. Cancer Res. 71, 2455\u20132465 (2011).","journal-title":"Cancer Res."},{"key":"427_CR36","doi-asserted-by":"crossref","first-page":"494","DOI":"10.1158\/1940-6207.CAPR-16-0322","volume":"10","author":"C Himbert","year":"2017","unstructured":"Himbert, C. et al. Signals from the adipose microenvironment and the obesity\u2014cancer link-a systematic review. Cancer Prev. Res. 10, 494\u2013506 (2017).","journal-title":"Cancer Prev. Res."},{"key":"427_CR37","first-page":"29","volume":"4","author":"VH Koelzer","year":"2014","unstructured":"Koelzer, V. H. & Lugli, A. The tumor border configuration of colorectal cancer as a histomorphological prognostic indicator. Front. Oncol. 4, 29 (2014).","journal-title":"Front. Oncol."},{"key":"427_CR38","doi-asserted-by":"crossref","first-page":"1170","DOI":"10.1007\/BF02055162","volume":"40","author":"F Cianchi","year":"1997","unstructured":"Cianchi, F. et al. Character of the invasive margin in colorectal cancer: does it improve prognostic information of Dukes staging? Dis. Colon Rectum 40, 1170\u20135 (1997). discussion 1175\u20136.","journal-title":"Dis. Colon Rectum"},{"key":"427_CR39","doi-asserted-by":"crossref","first-page":"599","DOI":"10.1038\/modpathol.2016.198","volume":"30","author":"J Shia","year":"2017","unstructured":"Shia, J. et al. Morphological characterization of colorectal cancers in The Cancer Genome Atlas reveals distinct morphology\u2013molecular associations: clinical and biological implications. Mod. Pathol. 30, 599\u2013609 (2017).","journal-title":"Mod. Pathol."},{"key":"427_CR40","doi-asserted-by":"crossref","first-page":"952","DOI":"10.5858\/arpa.2018-0082-RA","volume":"142","author":"S-J Cho","year":"2018","unstructured":"Cho, S.-J. & Kakar, S. Tumor budding in colorectal carcinoma: translating a morphologic score into clinically meaningful results. Arch. Pathol. Lab. Med. 142, 952\u2013957 (2018).","journal-title":"Arch. Pathol. Lab. Med."},{"key":"427_CR41","doi-asserted-by":"crossref","first-page":"366","DOI":"10.5334\/ojb.20","volume":"3","author":"B Huppertz","year":"2016","unstructured":"Huppertz, B., Bayer, M., Macheiner, T. & Sargsyan, K. Biobank Graz: the hub for innovative biomedical research. Open J. Bioresour. 3, 366 (2016).","journal-title":"Open J. Bioresour."},{"key":"427_CR42","doi-asserted-by":"crossref","first-page":"5944","DOI":"10.1200\/JCO.2008.19.6147","volume":"27","author":"F Pag\u00e8s","year":"2009","unstructured":"Pag\u00e8s, F. et al. In situ cytotoxic and memory T cells predict outcome in patients with early-stage colorectal cancer. J. Clin. Oncol. 27, 5944\u20135951 (2009).","journal-title":"J. Clin. Oncol."},{"key":"427_CR43","doi-asserted-by":"crossref","first-page":"160","DOI":"10.1007\/s00428-004-1051-z","volume":"445","author":"C Lackner","year":"2004","unstructured":"Lackner, C. et al. Prognostic relevance of tumour-associated macrophages and von Willebrand factor-positive microvessels in colorectal cancer. Virchows Arch. 445, 160\u2013167 (2004).","journal-title":"Virchows Arch."},{"key":"427_CR44","doi-asserted-by":"publisher","unstructured":"Reihs, R., Pohn, B., Zatloukal, K., Holzinger, A. & M\u00fcller, H. NLP for the Generation of Training Data Sets for Ontology-Guided Weakly-Supervised Machine Learning in Digital Pathology. in Fourth International Workshop on ICT Solutions for Health (ICTS4eHealth\u201919). https:\/\/doi.org\/10.1109\/ISCC47284.2019.8969703 (2019).","DOI":"10.1109\/ISCC47284.2019.8969703"},{"key":"427_CR45","doi-asserted-by":"crossref","unstructured":"Holzinger, A. et al. Machine Learning and Knowledge Extraction in Digital Pathology Needs an Integrative Approach. in Towards Integrative Machine Learning and Knowledge Extraction (eds Holzinger, A., Goebel, R., Ferri, M. & Palade, V.) vol. 10344 13\u201350 (Springer International Publishing, 2017).","DOI":"10.1007\/978-3-319-69775-8_2"},{"key":"427_CR46","doi-asserted-by":"publisher","DOI":"10.5858\/arpa.2018-0147-OA","author":"Y Liu","year":"2018","unstructured":"Liu, Y. et al. Artificial intelligence-based breast cancer nodal metastasis detection. Arch. Pathol. Lab. Med. https:\/\/doi.org\/10.5858\/arpa.2018-0147-OA (2018).","journal-title":"Arch. Pathol. Lab. Med."},{"key":"427_CR47","doi-asserted-by":"publisher","unstructured":"Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J. & Wojna, Z. Rethinking the inception architecture for computer vision. In 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (Las Vegas, NV, USA, 2016) pp 2818\u20132826, https:\/\/doi.org\/10.1109\/CVPR.2016.308.","DOI":"10.1109\/CVPR.2016.308"},{"key":"427_CR48","doi-asserted-by":"crossref","first-page":"e0233678","DOI":"10.1371\/journal.pone.0233678","volume":"15","author":"E Wulczyn","year":"2020","unstructured":"Wulczyn, E. et al. Deep learning-based survival prediction for multiple cancer types using histopathology images. PLoS ONE 15, e0233678 (2020).","journal-title":"PLoS ONE"},{"key":"427_CR49","unstructured":"Howard, A. G. et al. MobileNets: efficient convolutional neural networks for mobile vision applications. Preprint at https:\/\/arxiv.org\/abs\/1704.04861 (2017)."},{"key":"427_CR50","first-page":"281","volume":"13","author":"J Bergstra","year":"2012","unstructured":"Bergstra, J. & Bengio, Y. Random search for hyper-parameter optimization. J. Mach. Learn. Res. 13, 281\u2013305 (2012).","journal-title":"J. Mach. Learn. Res."},{"key":"427_CR51","doi-asserted-by":"crossref","first-page":"269","DOI":"10.1093\/biomet\/62.2.269","volume":"62","author":"DR Cox","year":"1975","unstructured":"Cox, D. R. Partial likelihood. Biometrika 62, 269 (1975).","journal-title":"Biometrika"},{"key":"427_CR52","doi-asserted-by":"crossref","first-page":"89","DOI":"10.2307\/2529620","volume":"30","author":"N Breslow","year":"1974","unstructured":"Breslow, N. Covariance analysis of censored survival data. Biometrics 30, 89 (1974).","journal-title":"Biometrics"},{"key":"427_CR53","unstructured":"Kingma, D. P. & Ba, J. Adam: a method for stochastic optimization. In 3rd International Conference on Learning Representations Preprint at https:\/\/arxiv.org\/abs\/1412.6980 (ICLR, San Diego, CA, USA, 2015) http:\/\/arxiv.org\/abs\/1412.6980."},{"key":"427_CR54","doi-asserted-by":"crossref","first-page":"187","DOI":"10.1111\/j.2517-6161.1972.tb00899.x","volume":"34","author":"DR Cox","year":"1972","unstructured":"Cox, D. R. Regression models and life-tables. J. R. Stat. Soc. Ser. B Stat. Methodol. 34, 187\u2013220 (1972).","journal-title":"J. R. Stat. Soc. Ser. B Stat. Methodol."},{"key":"427_CR55","doi-asserted-by":"crossref","first-page":"2543","DOI":"10.1001\/jama.1982.03320430047030","volume":"247","author":"FE Harrell","year":"1982","unstructured":"Harrell, F. E. Evaluating the yield of medical tests. J. Am. Med. Assoc. 247, 2543\u20132546 (1982).","journal-title":"J. Am. Med. Assoc."},{"key":"427_CR56","doi-asserted-by":"publisher","unstructured":"Davidson-Pilon, C. et al. CamDavidsonPilon\/lifelines: v0.21.3. https:\/\/doi.org\/10.5281\/zenodo.3240536 (2019).","DOI":"10.5281\/zenodo.3240536"},{"key":"427_CR57","doi-asserted-by":"crossref","first-page":"1504","DOI":"10.1245\/s10434-014-4149-9","volume":"22","author":"H Ueno","year":"2015","unstructured":"Ueno, H. et al. Histologic categorization of desmoplastic reaction: its relevance to the colorectal cancer microenvironment and prognosis. Ann. Surg. Oncol. 22, 1504\u20131512 (2015).","journal-title":"Ann. Surg. Oncol."}],"container-title":["npj Digital Medicine"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41746-021-00427-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41746-021-00427-2","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41746-021-00427-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,28]],"date-time":"2024-08-28T18:22:10Z","timestamp":1724869330000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41746-021-00427-2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,4,19]]},"references-count":57,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2021,12]]}},"alternative-id":["427"],"URL":"https:\/\/doi.org\/10.1038\/s41746-021-00427-2","relation":{},"ISSN":["2398-6352"],"issn-type":[{"value":"2398-6352","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,4,19]]},"assertion":[{"value":"31 July 2020","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"26 February 2021","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"19 April 2021","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"10 May 2021","order":4,"name":"change_date","label":"Change Date","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"Update","order":5,"name":"change_type","label":"Change Type","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The original version of this Article was updated after publication, because the github hyperlink in the Code Availability contained a typographical error. The error with the link has now been fixed in the Code Availability statement on the HTML and PDF version of the Article.","order":6,"name":"change_details","label":"Change Details","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"E.W., D.F.S., M.M., F.T., P.-H.C.C., N.H., A.S., R.M., B.A., G.S.C., L.H.P., D.T., Z.X., Y.L., M.C.S., and C.H.M. are current or past employees of Google LLC and own Alphabet stock. I.F.-A. and T.B. are consultants of Google LLC. M.P., R.R., P.R., H.M., and K.Z. are employees of the Medical University of Graz.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"71"}}