Multimodal classification of drug-naïve first-episode schizophrenia combining anatomical, diffusion and resting state functional resonance imaging. (13th July 2019)

• Record Type: Journal Article
• Authors: Zhuang, Huixiang; Liu, Ruihao; Wu, Chaowei; Meng, Ziyu; Wang, Danni; Liu, Dengtang; Liu, Manhua; Li, Yao
• Is Part Of: Neuroscience letters. Volume 705(2019)
• Page Start: 87
• Page End: 93
• Publication Date: 2019-07-13
• Subjects: Schizophrenia -- Multimodal MRI -- Classification -- Multi-kernel -- Linear SVM -- Sparse coding; Neurology -- Periodicals; Neurology -- Periodicals; Research -- Periodicals; Neurologie -- Périodiques; Neuroanatomie -- Périodiques; Neuropharmacologie -- Périodiques; Neurophysiologie -- Périodiques; Neurology; Periodicals; Electronic journals; 617.48
• DOI: 10.1016/j.neulet.2019.04.039
• Languages: English
• ISSNs: 0304-3940

Abstract

Highlights: It is the first study to classify drug-naïve first-episode schizophrenia patients from healthy controls with combined structural MRI, DTI and resting state-functional MRI data. To reduce the feature dimension of multimodal data, sparse coding is applied for feature selection and multi-kernel support vector machine is applied for feature combination and classification. The best classification performance was achieved when all modality data were combined, reaching an accuracy rate at above 84%. Abstract: The accurate diagnosis in the early stage of schizophrenia (SZ) is of great importance yet remains challenging. The classification between SZ and control groups based on magnetic resonance imaging (MRI) data using machine learning method could be helpful for SZ diagnosis. Increasing evidence showed that the combination of multimodal MRI data might further improve the classification performance However, medication effect has a profound influence on patients' anatomical and functional features and may reduce the classification efficiency. In this paper, we proposed a multimodal classification method to discriminate drug-naïve first-episode schizophrenia patients from healthy controls (HCs) by a combined structural MRI, diffusion tensor imaging (DTI) and resting state-functional MRI data. To reduce the feature dimension of multimodal data, we applied sparse coding (SC) for feature selection and multi-kernel support vector machine (SVM) for feature combination and classification. The best classification performance with the classification accuracy of 84.29% and area under the receiver operating characteristic (ROC) curve (AUC) of 81.64% was achieved when all modality data were combined. Interestingly, the identified functional markers were mainly found in default mode network (DMN) and cerebellar connections, while the structural markers were within limbic system and prefrontal–thalamo–hippocampal circuit.