Table_2_The Importance of Anti-correlations in Graph Theory Based Classification of Autism Spectrum Disorder.DOCX

With the release of the multi-site Autism Brain Imaging Data Exchange, many researchers have applied machine learning methods to distinguish between healthy subjects and autistic individuals by using features extracted from resting state functional MRI data. An important part of applying machine learning to this problem is extracting these features. Specifically, whether to include negative correlations between brain region activities as relevant features and how best to define these features. For the second question, the graph theoretical properties of the brain network may provide a reasonable answer. In this study, we investigated the first issue by comparing three different approaches. These included using the positive correlation matrix (comprising only the positive values of the original correlation matrix), the absolute value of the correlation matrix, or the anticorrelation matrix (comprising only the negative correlation values) as the starting point for extracting relevant features using graph theory. We then trained a multi-layer perceptron in a leave-one-site out manner in which the data from a single site was left out as testing data and the model was trained on the data from the other sites. Our results show that on average, using graph features extracted from the anti-correlation matrix led to the highest accuracy and AUC scores. This suggests that anti-correlations should not simply be discarded as they may include useful information that would aid the classification task. We also show that adding the PCA transformation of the original correlation matrix to the feature space leads to an increase in accuracy.

随着多中心自闭症脑成像数据交换（Autism Brain Imaging Data Exchange, ABIDE）数据集的发布，诸多研究者已依托静息态功能磁共振成像（resting state functional MRI, fMRI）提取的特征，运用机器学习方法区分健康受试者与自闭症患者。将机器学习应用于该研究问题的关键一环在于特征提取环节，具体涉及两个核心议题：是否应将脑区活动间的负相关纳入有效特征，以及如何最优地定义这类特征。针对后者，脑网络的图论属性可提供合理的解决思路。本研究针对第一个议题展开探究，对比了三种不同的特征提取方案：仅保留原始相关矩阵正值的正相关矩阵、相关矩阵的绝对值形式，以及仅保留负相关值的反相关矩阵，以此作为基于图论提取有效特征的初始输入。随后，我们采用留一站点交叉验证（leave-one-site out）的方式训练多层感知机（multi-layer perceptron, MLP）：将单个站点的数据作为测试集，其余站点的数据用于模型训练。实验结果表明，平均而言，基于反相关矩阵提取的图论特征能够取得最高的分类准确率与曲线下面积（Area Under Curve, AUC）得分。这意味着不应直接舍弃负相关信息，因其可能包含有助于提升分类任务性能的有效特征。本研究同时证实，将原始相关矩阵的主成分分析（Principal Component Analysis, PCA）变换结果加入特征空间，可进一步提升分类准确率。