Department of of Otolaryngology-Head and Neck Surgery, Renmin Hospital of Wuhan University, 238 Jie-Fang Road, Wuhan, Hubei 430060, PR China.
Department of of Radiology, Renmin Hospital of Wuhan University, 238 Jie-Fang Road, Wuhan, Hubei 430060, PR China.
Comput Methods Programs Biomed. 2022 Jun;219:106785. doi: 10.1016/j.cmpb.2022.106785. Epub 2022 Mar 31.
We aimed to predict the prognosis of advanced nasopharyngeal carcinoma (stage Ⅲ-Ⅳa) using Pre- and Post-treatment MR images based on deep learning (DL).
A total of 206 patients with primary nasopharyngeal carcinoma who were diagnosed and treated at the Renmin Hospital of Wuhan University between June 2012 and January 2018 were retrospectively selected. A rectangular region of interest (ROI), which included the tumor area, surrounding tissues and organs, was delineated on each Pre- and Post-treatment MR image. Two Inception-Resnet-V2 based transfer learning models, named Pre-model and Post-model, were trained with the Pre-treatment images and the Post-treatment images, respectively. In addition, an ensemble learning model based on the Pre-model and Post-models was established. The three established models were evaluated by receiver operating characteristic curve (ROC), confusion matrix, and Harrell's concordance indices (C-index). High-risk-related gradient-weighted class activation mapping (Grad-CAM) images were developed according to the DL models.
The Pre-model, Post-model, and ensemble model displayed a C-index of 0.717 (95% CI: 0.639 to 0.795), 0.811 (95% CI: 0.745-0.877), 0.830 (95% CI: 0.767-0.893), and AUC of 0.741 (95% CI: 0.584-0.900), 0.806 (95% CI: 0.670-0.942), and 0.842 (95% CI: 0.718-0.967) for the test cohort, respectively. In comparison with the models, the performance of Post-model was better than the performance of Pre-model, which indicated the importance of Post-treatment images for prognosis prediction. All three DL models performed better than the TNM staging system (0.723, 95% CI: 0.567-0.879). The captured features presented on Grad-CAM images suggested that the areas around the tumor and lymph nodes were related to the prognosis of the tumor.
The three established DL models based on Pre- and Post-treatment MR images have a better performance than TNM staging. Post-treatment MR images are of great significance for prognosis prediction and could contribute to clinical decision-making.
我们旨在使用基于深度学习（DL）的治疗前后磁共振成像（MR）预测晚期鼻咽癌（Ⅲ-Ⅳa 期）的预后。
回顾性选择 2012 年 6 月至 2018 年 1 月在武汉大学人民医院诊断和治疗的 206 例初治鼻咽癌患者。在每个治疗前后的 MR 图像上勾勒出包括肿瘤区域、周围组织和器官的矩形感兴趣区域（ROI）。使用预处理图像和后处理图像分别训练两个基于 Inception-Resnet-V2 的迁移学习模型，分别命名为 Pre 模型和 Post 模型。此外，还基于 Pre 模型和 Post 模型建立了一个集成学习模型。通过受试者工作特征曲线（ROC）、混淆矩阵和哈雷尔一致性指数（C 指数）评估三个建立的模型。根据 DL 模型生成高风险相关梯度加权类激活映射（Grad-CAM）图像。
Pre 模型、Post 模型和集成模型在测试队列中显示出 0.717（95%CI：0.639-0.795）、0.811（95%CI：0.745-0.877）、0.830（95%CI：0.767-0.893）的 C 指数和 0.741（95%CI：0.584-0.900）、0.806（95%CI：0.670-0.942）、0.842（95%CI：0.718-0.967）的 AUC，而 TNM 分期系统的表现为 0.723（95%CI：0.567-0.879）。与模型相比，Post 模型的性能优于 Pre 模型，这表明后处理图像对预后预测的重要性。三个基于治疗前后 MR 图像的 DL 模型的性能均优于 TNM 分期系统。在 Grad-CAM 图像上捕捉到的特征表明，肿瘤和淋巴结周围的区域与肿瘤的预后有关。
基于治疗前后磁共振成像的三个建立的 DL 模型的性能优于 TNM 分期。后处理 MR 图像对预后预测具有重要意义，并有助于临床决策。
