Frontiers in Neuroscience (Jul 2021)
Effects of Brain Atlases and Machine Learning Methods on the Discrimination of Schizophrenia Patients: A Multimodal MRI Study
- Jinyu Zang,
- Jinyu Zang,
- Jinyu Zang,
- Yuanyuan Huang,
- Yuanyuan Huang,
- Lingyin Kong,
- Lingyin Kong,
- Lingyin Kong,
- Bingye Lei,
- Bingye Lei,
- Bingye Lei,
- Pengfei Ke,
- Pengfei Ke,
- Pengfei Ke,
- Hehua Li,
- Jing Zhou,
- Jing Zhou,
- Jing Zhou,
- Dongsheng Xiong,
- Dongsheng Xiong,
- Dongsheng Xiong,
- Guixiang Li,
- Guixiang Li,
- Jun Chen,
- Jun Chen,
- Xiaobo Li,
- Zhiming Xiang,
- Zhiming Xiang,
- Yuping Ning,
- Yuping Ning,
- Fengchun Wu,
- Kai Wu,
- Kai Wu,
- Kai Wu,
- Kai Wu,
- Kai Wu,
- Kai Wu,
- Kai Wu,
- Kai Wu
Affiliations
- Jinyu Zang
- Department of Biomedical Engineering, School of Material Science and Engineering, South China University of Technology, Guangzhou, China
- Jinyu Zang
- Guangdong Engineering Technology Research Center for Translational Medicine of Mental Disorders, Guangzhou, China
- Jinyu Zang
- National Engineering Research Center for Tissue Restoration and Reconstruction, South China University of Technology, Guangzhou, China
- Yuanyuan Huang
- Guangdong Engineering Technology Research Center for Translational Medicine of Mental Disorders, Guangzhou, China
- Yuanyuan Huang
- The Affiliated Brain Hospital of Guangzhou Medical University, Guangzhou Huiai Hospital, Guangzhou, China
- Lingyin Kong
- Department of Biomedical Engineering, School of Material Science and Engineering, South China University of Technology, Guangzhou, China
- Lingyin Kong
- Guangdong Engineering Technology Research Center for Translational Medicine of Mental Disorders, Guangzhou, China
- Lingyin Kong
- National Engineering Research Center for Tissue Restoration and Reconstruction, South China University of Technology, Guangzhou, China
- Bingye Lei
- Department of Biomedical Engineering, School of Material Science and Engineering, South China University of Technology, Guangzhou, China
- Bingye Lei
- Guangdong Engineering Technology Research Center for Translational Medicine of Mental Disorders, Guangzhou, China
- Bingye Lei
- National Engineering Research Center for Tissue Restoration and Reconstruction, South China University of Technology, Guangzhou, China
- Pengfei Ke
- Department of Biomedical Engineering, School of Material Science and Engineering, South China University of Technology, Guangzhou, China
- Pengfei Ke
- Guangdong Engineering Technology Research Center for Translational Medicine of Mental Disorders, Guangzhou, China
- Pengfei Ke
- National Engineering Research Center for Tissue Restoration and Reconstruction, South China University of Technology, Guangzhou, China
- Hehua Li
- The Affiliated Brain Hospital of Guangzhou Medical University, Guangzhou Huiai Hospital, Guangzhou, China
- Jing Zhou
- Department of Biomedical Engineering, School of Material Science and Engineering, South China University of Technology, Guangzhou, China
- Jing Zhou
- Guangdong Engineering Technology Research Center for Translational Medicine of Mental Disorders, Guangzhou, China
- Jing Zhou
- National Engineering Research Center for Tissue Restoration and Reconstruction, South China University of Technology, Guangzhou, China
- Dongsheng Xiong
- Department of Biomedical Engineering, School of Material Science and Engineering, South China University of Technology, Guangzhou, China
- Dongsheng Xiong
- Guangdong Engineering Technology Research Center for Translational Medicine of Mental Disorders, Guangzhou, China
- Dongsheng Xiong
- National Engineering Research Center for Tissue Restoration and Reconstruction, South China University of Technology, Guangzhou, China
- Guixiang Li
- Guangdong Engineering Technology Research Center for Diagnosis and Rehabilitation of Dementia, Guangzhou, China
- Guixiang Li
- National Engineering Research Center for Healthcare Devices, Guangzhou, China
- Jun Chen
- Guangdong Engineering Technology Research Center for Diagnosis and Rehabilitation of Dementia, Guangzhou, China
- Jun Chen
- National Engineering Research Center for Healthcare Devices, Guangzhou, China
- Xiaobo Li
- Department of Biomedical Engineering, New Jersey Institute of Technology, Newark, NJ, United States
- Zhiming Xiang
- Guangdong Engineering Technology Research Center for Diagnosis and Rehabilitation of Dementia, Guangzhou, China
- Zhiming Xiang
- Department of Radiology, Panyu Central Hospital of Guangzhou, Guangzhou, China
- Yuping Ning
- Guangdong Engineering Technology Research Center for Translational Medicine of Mental Disorders, Guangzhou, China
- Yuping Ning
- The Affiliated Brain Hospital of Guangzhou Medical University, Guangzhou Huiai Hospital, Guangzhou, China
- Fengchun Wu
- The Affiliated Brain Hospital of Guangzhou Medical University, Guangzhou Huiai Hospital, Guangzhou, China
- Kai Wu
- Department of Biomedical Engineering, School of Material Science and Engineering, South China University of Technology, Guangzhou, China
- Kai Wu
- Guangdong Engineering Technology Research Center for Translational Medicine of Mental Disorders, Guangzhou, China
- Kai Wu
- National Engineering Research Center for Tissue Restoration and Reconstruction, South China University of Technology, Guangzhou, China
- Kai Wu
- The Affiliated Brain Hospital of Guangzhou Medical University, Guangzhou Huiai Hospital, Guangzhou, China
- Kai Wu
- Guangdong Engineering Technology Research Center for Diagnosis and Rehabilitation of Dementia, Guangzhou, China
- Kai Wu
- National Engineering Research Center for Healthcare Devices, Guangzhou, China
- Kai Wu
- Key Laboratory of Biomedical Engineering of Guangdong Province, South China University of Technology, Guangzhou, China
- Kai Wu
- 0Department of Nuclear Medicine and Radiology, Institute of Development, Aging and Cancer, Tohoku University, Sendai, Japan
- DOI
- https://doi.org/10.3389/fnins.2021.697168
- Journal volume & issue
-
Vol. 15
Abstract
Recently, machine learning techniques have been widely applied in discriminative studies of schizophrenia (SZ) patients with multimodal magnetic resonance imaging (MRI); however, the effects of brain atlases and machine learning methods remain largely unknown. In this study, we collected MRI data for 61 first-episode SZ patients (FESZ), 79 chronic SZ patients (CSZ) and 205 normal controls (NC) and calculated 4 MRI measurements, including regional gray matter volume (GMV), regional homogeneity (ReHo), amplitude of low-frequency fluctuation and degree centrality. We systematically analyzed the performance of two classifications (SZ vs NC; FESZ vs CSZ) based on the combinations of three brain atlases, five classifiers, two cross validation methods and 3 dimensionality reduction algorithms. Our results showed that the groupwise whole-brain atlas with 268 ROIs outperformed the other two brain atlases. In addition, the leave-one-out cross validation was the best cross validation method to select the best hyperparameter set, but the classification performances by different classifiers and dimensionality reduction algorithms were quite similar. Importantly, the contributions of input features to both classifications were higher with the GMV and ReHo features of brain regions in the prefrontal and temporal gyri. Furthermore, an ensemble learning method was performed to establish an integrated model, in which classification performance was improved. Taken together, these findings indicated the effects of these factors in constructing effective classifiers for psychiatric diseases and showed that the integrated model has the potential to improve the clinical diagnosis and treatment evaluation of SZ.
Keywords
