Department of Radiology, National Cancer Center/National Clinical Research Center for Cancer/Cancer Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College, #17 Panjiayuan Nanli, Chaoyang District, Beijing, 100021, China.
Department of Pharmaceutical Diagnosis, GE Healthcare, Life Sciences, #1 Tongji South Road, Beijing, 100176, China.
Eur Radiol. 2023 May;33(5):3638-3646. doi: 10.1007/s00330-023-09450-1. Epub 2023 Mar 11.
This study aimed to investigate whether a deep learning (DL) model based on preoperative MR images of primary tumors can predict lymph node metastasis (LNM) in patients with stage T1-2 rectal cancer.
In this retrospective study, patients with stage T1-2 rectal cancer who underwent preoperative MRI between October 2013 and March 2021 were included and assigned to the training, validation, and test sets. Four two-dimensional and three-dimensional (3D) residual networks (ResNet18, ResNet50, ResNet101, and ResNet152) were trained and tested on T2-weighted images to identify patients with LNM. Three radiologists independently assessed LN status on MRI, and diagnostic outcomes were compared with the DL model. Predictive performance was assessed with AUC and compared using the Delong method.
In total, 611 patients were evaluated (444 training, 81 validation, and 86 test). The AUCs of the eight DL models ranged from 0.80 (95% confidence interval [CI]: 0.75, 0.85) to 0.89 (95% CI: 0.85, 0.92) in the training set and from 0.77 (95% CI: 0.62, 0.92) to 0.89 (95% CI: 0.76, 1.00) in the validation set. The ResNet101 model based on 3D network architecture achieved the best performance in predicting LNM in the test set, with an AUC of 0.79 (95% CI: 0.70, 0.89) that was significantly greater than that of the pooled readers (AUC, 0.54 [95% CI: 0.48, 0.60]; p < 0.001).
The DL model based on preoperative MR images of primary tumors outperformed radiologists in predicting LNM in patients with stage T1-2 rectal cancer.
• Deep learning (DL) models with different network frameworks showed different diagnostic performance for predicting lymph node metastasis (LNM) in patients with stage T1-2 rectal cancer. • The ResNet101 model based on 3D network architecture achieved the best performance in predicting LNM in the test set. • The DL model based on preoperative MR images outperformed radiologists in predicting LNM in patients with stage T1-2 rectal cancer.
本研究旨在探讨基于原发性肿瘤术前磁共振成像的深度学习（DL）模型是否可以预测 T1-2 期直肠癌患者的淋巴结转移（LNM）。
本回顾性研究纳入了 2013 年 10 月至 2021 年 3 月期间接受术前 MRI 检查的 T1-2 期直肠癌患者，并将其分为训练集、验证集和测试集。对 T2 加权图像上的四个二维和三维（3D）残差网络（ResNet18、ResNet50、ResNet101 和 ResNet152）进行训练和测试，以识别 LNM 患者。三位放射科医生独立对 MRI 上的 LN 状态进行评估，并将诊断结果与 DL 模型进行比较。使用 AUC 评估预测性能，并使用 Delong 方法进行比较。
共有 611 例患者接受评估（444 例训练，81 例验证，86 例测试）。在训练集中，八个 DL 模型的 AUC 范围为 0.80（95%置信区间 [CI]：0.75，0.85）至 0.89（95% CI：0.85，0.92），在验证集中为 0.77（95% CI：0.62，0.92）至 0.89（95% CI：0.76，1.00）。基于 3D 网络架构的 ResNet101 模型在测试集中预测 LNM 的表现最佳，AUC 为 0.79（95% CI：0.70，0.89），明显优于汇总读者（AUC，0.54 [95% CI：0.48，0.60]；p<0.001）。
基于原发性肿瘤术前 MRI 的 DL 模型在预测 T1-2 期直肠癌患者的 LNM 方面优于放射科医生。
• 具有不同网络框架的深度学习（DL）模型在预测 T1-2 期直肠癌患者的淋巴结转移（LNM）方面表现出不同的诊断性能。• 基于 3D 网络架构的 ResNet101 模型在测试集中预测 LNM 的表现最佳。• 基于术前 MRI 的 DL 模型在预测 T1-2 期直肠癌患者的 LNM 方面优于放射科医生。
