Department of Medical Ultrasonics, Institute of Diagnostic and Interventional Ultrasound, The First Affiliated Hospital, Sun Yat-sen University, Guangzhou, China.
Clinical Trials Unit, The First Affiliated Hospital, Sun Yat-sen University, Guangzhou, China.
Br J Cancer. 2024 Apr;130(6):951-960. doi: 10.1038/s41416-024-02573-2. Epub 2024 Jan 20.
Accurate estimation of the long-term risk of recurrence in patients with non-metastatic colorectal cancer (CRC) is crucial for clinical management. Histology-based deep learning is expected to provide more abundant information for risk stratification.
We developed and validated a weakly supervised deep-learning model for predicting 5-year relapse-free survival (RFS) to stratify patients with different risks based on histological images from three hospitals of 614 cases with non-metastatic CRC. A deep prognostic factor (DL-RRS) was established to stratify patients into high and low-risk group. The areas under the curve (AUCs) were calculated to evaluate the performances of models.
Our proposed model achieves the AUCs of 0.833 (95% CI: 0.736-0.905) and 0.715 (95% CI: 0.647-0.776) on validation cohort and external test cohort, respectively. The 5-year RFS rate was 45.7% for high DL-RRS patients, and 82.5% for low DL-RRS patients respectively in the external test cohort (HR: 3.89, 95% CI: 2.51-6.03, P < 0.001). Adjuvant chemotherapy was associated with improved RFS in Stage II patients with high DL-RRS (HR: 0.15, 95% CI: 0.06-0.38, P < 0.001).
DL-RRS has a good predictive performance of 5-year recurrence risk in CRC, and will better serve the clinical decision-making.
准确估计非转移性结直肠癌（CRC）患者的长期复发风险对于临床管理至关重要。基于组织学的深度学习有望为风险分层提供更丰富的信息。
我们开发并验证了一种用于预测 5 年无复发生存率（RFS）的弱监督深度学习模型，以根据来自三家医院的 614 例非转移性 CRC 患者的组织学图像对具有不同风险的患者进行分层。建立了一个深度预后因素（DL-RRS），将患者分为高风险和低风险组。计算曲线下面积（AUC）以评估模型的性能。
我们提出的模型在验证队列和外部测试队列中的 AUC 分别为 0.833（95%CI：0.736-0.905）和 0.715（95%CI：0.647-0.776）。在外部测试队列中，高 DL-RRS 患者的 5 年 RFS 率为 45.7%，低 DL-RRS 患者的 5 年 RFS 率为 82.5%（HR：3.89，95%CI：2.51-6.03，P<0.001）。对于高 DL-RRS 分期 II 期患者，辅助化疗与 RFS 改善相关（HR：0.15，95%CI：0.06-0.38，P<0.001）。
DL-RRS 对 CRC 的 5 年复发风险具有良好的预测性能，并将更好地为临床决策服务。
