West China School of Medicine, Sichuan University, No. 17 People's South Road, 610041, Chengdu, Sichuan, China.
West China Hospital, Sichuan University, Guoxue Road 37, 610041, Chengdu, China.
Strahlenther Onkol. 2022 Feb;198(2):183-193. doi: 10.1007/s00066-021-01874-2. Epub 2021 Nov 24.
Deep learning methods have great potential to predict treatment response. The objective of this study was to evaluate and validate the predictive performance of the computed tomography (CT)-based model using deep learning features for identification of responders and nonresponders to induction chemotherapy (IC) in nasopharyngeal carcinoma (NPC).
All eligible patients were included retrospectively between January 2012 and December 2018, and assigned to the training (n = 208) or the testing cohort (n = 89). We extracted deep learning features of six pretrained convolutional neural networks (CNNs) via transfer learning method, and handcrafted radiomics features manually. Support vector machine (SVM) was adopted as the classifier. All predictive models were evaluated using the area under the receiver operating characteristics curve (AUC), by which an optimal model was selected. We also built clinical and clinical-radiological models for comparison.
The model with features extracted from ResNet50 (RN-SVM) had optimal performance among all models with features extracted from pretrained CNNs with an AUC of 0.811, accuracy of 68.54%, sensitivity of 61.54%, specificity of 87.50%, positive predictive value (PPV) of 93.02%, and negative predictive value (NPV) of 45.65% in the testing cohort. The handcrafted radiomics model was slightly inferior to the RN-SVM model with an AUC of 0.663 and accuracy of 60.67% in the testing cohort. All the imaging-derived models had better predictive performance than the clinical model.
The noninvasive deep learning method could provide efficient prediction of treatment response to IC in locally advanced NPC and might be a practicable approach in therapeutic strategy decision-making.
深度学习方法在预测治疗反应方面具有巨大潜力。本研究的目的是评估和验证基于计算机断层扫描（CT）的模型使用深度学习特征来识别鼻咽癌（NPC）诱导化疗（IC）应答者和无应答者的预测性能。
所有符合条件的患者均于 2012 年 1 月至 2018 年 12 月间被回顾性纳入，并被分配到训练（n=208）或测试队列（n=89）。我们通过转移学习方法提取了六个预先训练的卷积神经网络（CNN）的深度学习特征，并手动提取了放射组学特征。支持向量机（SVM）被用作分类器。所有预测模型均通过接受者操作特征曲线（ROC）下的面积（AUC）进行评估，选择最佳模型。我们还构建了临床和临床放射学模型进行比较。
从 ResNet50 中提取特征的模型（RN-SVM）在从预先训练的 CNN 中提取特征的所有模型中表现最佳，在测试队列中的 AUC 为 0.811、准确率为 68.54%、敏感度为 61.54%、特异度为 87.50%、阳性预测值（PPV）为 93.02%和阴性预测值（NPV）为 45.65%。手工提取的放射组学模型在测试队列中的 AUC 为 0.663，准确率为 60.67%，略逊于 RN-SVM 模型。所有影像学衍生模型的预测性能均优于临床模型。
非侵入性深度学习方法可有效预测局部晚期 NPC 对 IC 的治疗反应，可能是治疗策略决策中的一种可行方法。
