The modified CNN architecture was able to provide joint information of multiple modalities for the DLR analysis. The performance of multiple modalities was evaluated using the dataset of the first cohort with both T2 flair images and T1 contrast images. Two evaluation methods were used: leave-one-out cross-validation and validation based on time of diagnosis. The evaluation parameters of the prediction results based on leave-one-out cross-validation are shown in Table 2(b), and a comparison of the ROC curves is presented in Fig. 3(b). 解释

这段话主要说明了一个修改过的卷积神经网络(CNN)架构可以提供多个模态的联合信息进行 DLR(深度学习诊断)分析，并使用第一组数据集中的T2 FLAIR图像和T1对比图像来评估多个模态的性能。作者使用了两种评估方法：留一交叉验证和基于诊断时间的验证。文章给出了留一交叉验证的预测结果的评估参数，表格2(b)中列出了这些参数，同时也提供了 ROC 曲线的比较，如图3(b)所示。