%0 Journal Article
%A Jiang, Xiaofeng
%A Hoffmeister, Michael
%A Brenner, Hermann
%A Muti, Hannah Sophie
%A Yuan, Tanwei
%A Foersch, Sebastian
%A West, Nicholas P
%A Brobeil, Alexander
%A Jonnagaddala, Jitendra
%A Hawkins, Nicholas
%A Ward, Robyn L
%A Brinker, Titus
%A Saldanha, Oliver Lester
%A Ke, Jia
%A Müller, Wolfram
%A Grabsch, Heike I
%A Quirke, Philip
%A Truhn, Daniel
%A Kather, Jakob Nikolas
%T End-to-end prognostication in colorectal cancer by deep learning: a retrospective, multicentre study.
%J The lancet / Digital health
%V 6
%N 1
%@ 2589-7500
%C London
%I The Lancet
%M DKFZ-2023-02779
%P e33 - e43
%D 2023
%X Precise prognosis prediction in patients with colorectal cancer (ie, forecasting survival) is pivotal for individualised treatment and care. Histopathological tissue slides of colorectal cancer specimens contain rich prognostically relevant information. However, existing studies do not have multicentre external validation with real-world sample processing protocols, and algorithms are not yet widely used in clinical routine.In this retrospective, multicentre study, we collected tissue samples from four groups of patients with resected colorectal cancer from Australia, Germany, and the USA. We developed and externally validated a deep learning-based prognostic-stratification system for automatic prediction of overall and cancer-specific survival in patients with resected colorectal cancer. We used the model-predicted risk scores to stratify patients into different risk groups and compared survival outcomes between these groups. Additionally, we evaluated the prognostic value of these risk groups after adjusting for established prognostic variables.We trained and validated our model on a total of 4428 patients. We found that patients could be divided into high-risk and low-risk groups on the basis of the deep learning-based risk score. On the internal test set, the group with a high-risk score had a worse prognosis than the group with a low-risk score, as reflected by a hazard ratio (HR) of 4·50 (95
%F PUB:(DE-HGF)16
%9 Journal Article
%$ pmid:38123254
%R 10.1016/S2589-7500(23)00208-X
%U https://inrepo02.dkfz.de/record/286376