TY - JOUR
T1 - Effects of Brain Atlases and Machine Learning Methods on the Discrimination of Schizophrenia Patients
T2 - A Multimodal MRI Study
AU - Zang, Jinyu
AU - Huang, Yuanyuan
AU - Kong, Lingyin
AU - Lei, Bingye
AU - Ke, Pengfei
AU - Li, Hehua
AU - Zhou, Jing
AU - Xiong, Dongsheng
AU - Li, Guixiang
AU - Chen, Jun
AU - Li, Xiaobo
AU - Xiang, Zhiming
AU - Ning, Yuping
AU - Wu, Fengchun
AU - Wu, Kai
N1 - Funding Information:
This work was supported by the National Key Research and Development Program of China (2020YFC2004300, 2020YFC2004301, 2019YFC0118800, 2019YFC0118802, 2019YFC0118804, and 2019YFC0118805), the National Natural Science Foundation of China (31771074 and 81802230), the Key Research and Development Program of Guangdong (2018B030335001, 2020B0101130020, and 2020B0404010002), Guangdong Basic and Applied Basic Research Foundation Outstanding Youth Project (2021B1515020064), the Science and Technology Program of Guangzhou (201807010064, 201803010100, 201903010032, and 202103000032), and Key Laboratory Program of Guangdong Provincial Education Department (2020KSYS001).
Publisher Copyright:
© Copyright © 2021 Zang, Huang, Kong, Lei, Ke, Li, Zhou, Xiong, Li, Chen, Li, Xiang, Ning, Wu and Wu.
PY - 2021/7/27
Y1 - 2021/7/27
N2 - 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.
AB - 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.
KW - brain atlas
KW - classification
KW - machine learning
KW - multimodal MRI
KW - schizophrenia
UR - http://www.scopus.com/inward/record.url?scp=85112145006&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85112145006&partnerID=8YFLogxK
U2 - 10.3389/fnins.2021.697168
DO - 10.3389/fnins.2021.697168
M3 - Article
AN - SCOPUS:85112145006
SN - 1662-4548
VL - 15
JO - Frontiers in Neuroscience
JF - Frontiers in Neuroscience
M1 - 697168
ER -