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。

相关问题

Deep learning-based radiomics (DLR) was developed to extract deep information from multiple modalities of magnetic resonance (MR) images. The performance of DLR for predicting the mutation status of isocitrate dehydrogenase 1 (IDH1) was validated in a dataset of 151 patients with low-grade glioma. A modified convolutional neural network (CNN) structure with 6 convolutional layers and a fully connected layer with 4096 neurons was used to segment tumors. Instead of calculating image features from segmented images, as typically performed for normal radiomics approaches, image features were obtained by normalizing the information of the last convolutional layers of the CNN. Fisher vector was used to encode the CNN features from image slices of different sizes. High-throughput features with dimensionality greater than 1.6*104 were obtained from the CNN. Paired t-tests and F-scores were used to select CNN features that were able to discriminate IDH1. With the same dataset, the area under the operating characteristic curve (AUC) of the normal radiomics method was 86% for IDH1 estimation, whereas for DLR the AUC was 92%. The AUC of IDH1 estimation was further improved to 95% using DLR based on multiple-modality MR images. DLR could be a powerful way to extract deep information from medical images. 解释

这段文本介绍了一种基于深度学习的影像分析方法，即Deep learning-based radiomics (DLR)。该方法使用了修改后的卷积神经网络(CNN)结构，通过对磁共振(MR)影像进行多模态分析，提取更深层次的信息。该研究使用了151例低级别胶质瘤患者的数据集，通过对肿瘤进行分割，得到CNN的最后卷积层信息，再利用Fisher向量进行编码，得到维度高达1.6*104的高通量特征。该研究表明，相比于传统的放射学方法，DLR方法在预测异柠酸脱氢酶1(IDH1)突变状态时，具有更高的准确性，其AUC值达到了92%~95%。这些发现表明，DLR方法可以有效地从医学影像中提取更深层次的信息，对肿瘤的诊断和治疗具有潜在的帮助。

Two individual features achieved log-rank P values of 0.003 and P value <0.001 respectively in the validation data set. The other four individual features failed to stratify patients into high-risk and low-risk groups in the val- idation data set. The multi-feature signature was successful to predict the OS of patients in the validation data set and performed better than any individual feature. From the statistical perspective, nonsignificant association with survival does not mean less importance. On the other hand, multivariate model is statistically robust in survival analysis26. Moreover, the intra-tumor genetic heterogeneity suggests that tumor subregions could be genetically different and may comprise multiple subclones. This could be better reflected by multiple high-order deep fea- tures extracted from multi-subregions in multi-modalities rather than individual feature. Similar to the genomic studies of exploring biomarkers from high-throughput genomic data, it is also regarded as a common“-omics” approach to construct a multi-factor radiomics signature for outcome prediction. 解释

这段话介绍了一项研究，该研究使用了多个特征来预测患者的生存期，其中有两个特征在验证数据集中获得了显著的统计学结果，但其他四个特征则没有。然而，使用多个特征的组合可以更准确地预测患者的生存期，比单个特征更有效。此外，研究者指出，即使在单个特征的分析中没有发现显著的生存期关联，也不能说明该特征不重要。从统计学角度来看，使用多元模型可以更加稳健地进行生存分析。此外，肿瘤内部的遗传异质性意味着肿瘤不同部位的遗传信息可能不同，因此使用多种模态的多个高阶深度特征可以更好地反映肿瘤的内部异质性。与高通量基因组学研究探索生物标志物类似，构建多因素放射组学签名也是一种常见的“组学”方法，可用于预测患者的生存期。