Long Dan, Zhang Mengda, Yu Jing, Zhu Qi, Chen Fengnong, Li Fangyin
Zhejiang Cancer Hospital, Institute of Basic Medicine and Cancer (IBMC), Chinese Academy of Sciences, Hangzhou, Zhejiang, China.
School of Automation, Hangzhou Dianzi University, Hangzhou, China.
Front Neurosci. 2023 Mar 16;17:1126865. doi: 10.3389/fnins.2023.1126865. eCollection 2023.
Resting-state brain network with physiological and pathological basis has always been the ideal data for intelligent diagnosis of major depression disease (MDD). Brain networks are divided into low-order networks and high-order networks. Most of the studies only use a single-level network to classify while ignoring that the brain works cooperatively with different levels of networks. This study hopes to find out whether varying levels of networks will provide complementary information in the process of intelligent diagnosis and what impact will be made on the final classification results by combining the characteristics of different networks.
Our data are from the REST-meta-MDD project. After the screening, 1,160 subjects from ten sites were included in this study (597 MDD and 563 normal controls). For each subject, we constructed three different levels of networks according to the brain atlas: the traditional low-order network based on Pearson's correlation (low-order functional connectivity, LOFC), the high-order network based on topographical profile similarity (topographical information-based high-order functional connectivity, tHOFC) and the associated network between them (aHOFC). Two sample -test is used for feature selection, and then features from different sources are fused. Finally, the classifier is trained by a multi-layer perceptron or support vector machine. The performance of the classifier was evaluated using the leave-one-site cross-validation method.
The classification ability of LOFC is the highest among the three networks. The classification accuracy of the three networks combined is similar to the LOFC network. These are seven features chosen in all networks. In the aHOFC classification, six features were selected in each round but not seen in other classifications. In the tHOFC classification, five features were selected in each round but were unique. These new features have crucial pathological significance and are essential supplements to LOFC.
A high-order network can provide auxiliary information for low-order networks but cannot improve classification accuracy.
具有生理和病理基础的静息态脑网络一直是重度抑郁症（MDD）智能诊断的理想数据。脑网络分为低阶网络和高阶网络。大多数研究仅使用单一层级网络进行分类，而忽略了大脑是与不同层级的网络协同工作的。本研究希望找出不同层级的网络在智能诊断过程中是否会提供互补信息，以及结合不同网络的特征会对最终分类结果产生何种影响。
我们的数据来自REST-meta-MDD项目。经过筛选，本研究纳入了来自十个站点的1160名受试者（597名MDD患者和563名正常对照）。对于每个受试者，我们根据脑图谱构建了三种不同层级的网络：基于皮尔逊相关性的传统低阶网络（低阶功能连接，LOFC）、基于地形轮廓相似性的高阶网络（基于地形信息的高阶功能连接，tHOFC）以及它们之间的关联网络（aHOFC）。使用两样本检验进行特征选择，然后融合来自不同来源的特征。最后，通过多层感知器或支持向量机训练分类器。使用留一站点交叉验证方法评估分类器的性能。
在三个网络中，LOFC的分类能力最高。三个网络组合的分类准确率与LOFC网络相似。在所有网络中共同选择了七个特征。在aHOFC分类中，每轮选择了六个特征，但在其他分类中未见。在tHOFC分类中，每轮选择了五个特征且是独特的。这些新特征具有关键的病理意义，是LOFC的重要补充。
高阶网络可以为低阶网络提供辅助信息，但不能提高分类准确率。
