Classification of autism spectrum disorder by combining brain connectivity and deep neural network classifier
Classification of autism spectrum disorder by combining brain connectivity and deep neural network classifier
复制标题
DOI：
10.1016/j.neucom.2018.04.080
复制
发表时间：
2019-01-09
期刊：
影响因子：
6
通讯作者：
Liu, Jin
中科院分区：
文献类型：
--
作者：
Kong, Yazhou;Gao, Jianliang;Liu, Jin
自闭症谱系障碍（ASD）是一种常见的神经发育障碍，严重影响患者的沟通和社交能力。从典型对照（TC）中准确识别ASD患者是至关重要的。传统的ASD/TC分类方法主要是在不同的兴趣区域（roi）上独立提取形态学特征，很少考虑这些兴趣区域之间的连通性。在本研究中，我们构建了个体脑网络作为特征表示，并使用深度神经网络（DNN）分类器进行ASD/TC分类。首先，我们为每个被试构建一个单独的大脑网络，提取每对roi之间的连通性特征。其次，使用F-score对连接特征进行降序排序，选择排名靠前的特征；最后，选择的3000个顶级特征通过DNN分类器进行ASD/TC分类。使用来自自闭症脑成像数据交换I （ABIDE I）的t1加权MRI图像，通过十倍交叉验证对所提出的方法进行了评估。实验结果表明，该方法对ASD/TC分类的准确率为90.39%，受试者工作特征曲线下面积（AUC）为0.9738。实验结果表明，本文提出的方法在ASD/TC分类中优于一些最先进的方法。(C) 2018 Elsevier B.V.版权所有
Autism spectrum disorder (ASD) is a common neurodevelopmental disorder that seriously affects communication and sociality of patients. It is crucial to accurately identify patients with ASD from typical controls (TC). Conventional methods for the classification of ASD/TC mainly extract morphological features independently at different regions of interest (ROIs), rarely considering the connectivity between these ROIs. In this study, we construct an individual brain network as feature representation, and use a deep neural network (DNN) classifier to perform ASD/TC classification. Firstly, we construct an individual brain network for each subject, and extract connectivity features between each pair of ROIs. Secondly, the connectivity features are ranked in descending order using F-score, and the top ranked features are selected. Finally, the selected 3000 top features are used to perform ASD/TC classification via a DNN classifier. An evaluation of the proposed method has been conducted with T1-weighted MRI images from the Autism Brain Imaging Data Exchange I (ABIDE I) by using ten-fold cross validation. Experimental results show that our proposed method can achieve the accuracy of 90.39% and the area under receiver operating characteristic curve (AUC) of 0.9738 for ASD/TC classification. Comparison of experimental results illustrates that our proposed method outperforms some state-of-the-art methods in ASD/TC classification. (C) 2018 Elsevier B.V. All rights reserved.