A network clustering based feature selection strategy for classifying autism spectrum disorder

Abstract

BackgroundAdvanced non-invasive neuroimaging techniques offer new approaches to study functions and structures of human brains. Whole-brain functional networks obtained from resting state functional magnetic resonance imaging has been widely used to study brain diseases like autism spectrum disorder (ASD). Auto-classification of ASD has become an important issue. Existing classification methods for ASD are based on features extracted from the whole-brain functional networks, which may be not discriminant enough for good performance.MethodsIn this study, we propose a network clustering based feature selection strategy for classifying ASD. In our proposed method, we first apply symmetric non-negative matrix factorization to divide brain networks into four modules. Then we extract features from one of four modules called default mode network (DMN) and use them to train several classifiers for ASD classification.ResultsThe computational experiments show that our proposed method achieves better performances than those trained with features extracted from the whole brain network.ConclusionIt is a good strategy to train the classifiers for ASD based on features from the default mode subnetwork.

Role of Artificial Intelligence for Autism Diagnosis Using DTI and fMRI: A Survey

“…The detection was by linear kernel SVM. Tang et al [97] used extracted features from ROI-based FC from DMN and the whole brain with joint symmetrical non-negative matrix factorization (JSNMF). An SVM classifier was used to classify ASD and HC subjects.…”

Diagnosis of ASD from rs-fMRI Images Based on Brain Dynamic Networks

“…Lingkai Tang presented a new feature selection strategy which extracts features from functional modules instead of from the whole brain networks. As a result, feature dimensions are reduced and the performances of auto-classifications of ASD has been improved [81].…”

“…Lingkai Tang [81] proposed to extract features from two functional modules instead of the whole brain networks, which enlightened me to design a representative module selection method aiming to reduce the dimensionality of features. Meanwhile, in the thesis of Sakib Mostafa [52], the centrality measures were incorporated in the features of the brain network, which illuminated me to utilize centrality measures to find important ROIs of the brain network, and further to discover the representative module of the brain network.…”