Else Kroener Fresenius Center for Digital Health, Technical University Dresden, Dresden, Germany; Department of Medicine III, University Hospital Rheinisch-Westfälische Technische Hochschule Aachen, Aachen, Germany.
Division of Clinical Epidemiology and Ageing Research, German Cancer Research Center, Heidelberg, Germany.
Lancet Digit Health. 2024 Jan;6(1):e33-e43. doi: 10.1016/S2589-7500(23)00208-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% CI 3·33-6·09) for overall survival and 8·35 (5·06-13·78) for disease-specific survival (DSS). We found consistent performance across three large external test sets. In a test set of 1395 patients, the high-risk group had a lower DSS than the low-risk group, with an HR of 3·08 (2·44-3·89). In two additional test sets, the HRs for DSS were 2·23 (1·23-4·04) and 3·07 (1·78-5·3). We showed that the prognostic value of the deep learning-based risk score is independent of established clinical risk factors.
Our findings indicate that attention-based self-supervised deep learning can robustly offer a prognosis on clinical outcomes in patients with colorectal cancer, generalising across different populations and serving as a potentially new prognostic tool in clinical decision making for colorectal cancer management. We release all source codes and trained models under an open-source licence, allowing other researchers to reuse and build upon our work.
The German Federal Ministry of Health, the Max-Eder-Programme of German Cancer Aid, the German Federal Ministry of Education and Research, the German Academic Exchange Service, and the EU.
在结直肠癌患者中进行精确的预后预测（即预测生存）对于个体化治疗和护理至关重要。结直肠癌标本的组织病理切片包含丰富的预后相关信息。然而，现有的研究没有采用真实世界样本处理方案进行多中心外部验证，并且算法尚未广泛应用于临床常规。
在这项回顾性、多中心研究中，我们从澳大利亚、德国和美国的四个组别的接受结直肠癌切除术的患者中收集了组织样本。我们开发并验证了一种基于深度学习的预测系统，用于自动预测接受结直肠癌切除术的患者的总体和癌症特异性生存。我们使用模型预测的风险评分将患者分层为不同的风险组，并比较这些组之间的生存结果。此外，我们还评估了这些风险组在调整既定预后变量后的预后价值。
我们总共对 4428 名患者进行了训练和验证。我们发现，可以根据基于深度学习的风险评分将患者分为高危组和低危组。在内部测试集中，高危组的预后比低危组差，总生存的风险比（HR）为 4.50（95%CI 3.33-6.09），癌症特异性生存（DSS）的 HR 为 8.35（5.06-13.78）。我们在三个大型外部测试集中发现了一致的性能。在包含 1395 名患者的测试集中，高危组的 DSS 低于低危组，HR 为 3.08（2.44-3.89）。在另外两个测试集中，DSS 的 HR 分别为 2.23（1.23-4.04）和 3.07（1.78-5.3）。我们表明，基于深度学习的风险评分的预后价值独立于既定的临床危险因素。
我们的研究结果表明，基于注意力的自监督深度学习可以稳健地为结直肠癌患者的临床结局提供预后，在不同人群中具有良好的通用性，并且可以成为结直肠癌管理中临床决策的潜在新预后工具。我们以开源许可证的形式发布了所有的源代码和训练模型，允许其他研究人员重复使用和进一步开发我们的工作。
德国联邦卫生部、德国癌症援助的马克斯-埃德尔计划、德国联邦教育部和研究部、德国学术交流服务处以及欧盟。
