Classification of Migraine Using Static Functional Connectivity Strength and Dynamic Functional Connectome Patterns: A Resting-State fMRI Study

• Published in: Brain sciences Vol. 13; no. 4; p. 596
• Main Authors: Nie, Weifang, Zeng, Weiming, Yang, Jiajun, Zhao, Le, Shi, Yuhu
• Format: Journal Article
• Language: English
• Published: Switzerland MDPI AG 31.03.2023; MDPI
• Subjects: Age; Algorithms; Biomarkers; Brain mapping; Classification; clustering; Development and progression; Disease; dynamic functional connectome; Functional magnetic resonance imaging; Gender; Headache; Headaches; Magnetic resonance imaging; Medical research; Medicine, Experimental; Mental disorders; Mental illness; Migraine; Neural networks; Neuroimaging; Regions; Reproducibility; sliding window analysis; dynamic functional connectome; clustering; migraine; sliding window analysis; classification
• ISSN: 2076-3425; 2076-3425
• DOI: 10.3390/brainsci13040596

Migraine is a common, chronic dysfunctional disease with recurrent headaches. Its etiology and pathogenesis have not been fully understood and there is a lack of objective diagnostic criteria and biomarkers. Meanwhile, resting-state functional magnetic resonance imaging (RS-fMRI) is increasingly being used in migraine research to classify and diagnose brain disorders. However, the RS-fMRI data is characterized by a large amount of data information and the difficulty of extracting high-dimensional features, which brings great challenges to relevant studies. In this paper, we proposed an automatic recognition framework based on static functional connectivity (sFC) strength features and dynamic functional connectome pattern (DFCP) features of migraine sufferers and normal control subjects, in which we firstly extracted sFC strength and DFCP features and then selected the optimal features using the recursive feature elimination based on the support vector machine (SVM−RFE) algorithm and, finally, trained and tested a classifier with the support vector machine (SVM) algorithm. In addition, we compared the classification performance of only using sFC strength features and DFCP features, respectively. The results showed that the DFCP features significantly outperformed sFC strength features in performance, which indicated that DFCP features had a significant advantage over sFC strength features in classification. In addition, the combination of sFC strength and DFCP features had the optimal performance, which demonstrated that the combination of both features could make full use of their advantage. The experimental results suggested the method had good performance in differentiating migraineurs and our proposed classification framework might be applicable for other mental disorders.