Related Experiment Video
Updated: May 14, 2026
Identification of Disease-related Spatial Covariance Patterns using Neuroimaging Data
Published on: June 26, 2013
[Multivoxel pattern analysis of schizophrenia by resting-state functional magnetic resonance imaging]
Yan Tang1, Fang Cao, Lifeng Wang
1Institute of Mental Health, Second Xiangya Hospital, Central South University, Changsha 410011, China.
Objective:
To investigate the resting-state functional connectivity in patients with schizophrenia and healthy controls using multivoxel pattern analysis, and to find out the abnormal functional connectivity in patients.
Methods:
Twenty two patients with schizophrenia and 22 matched controls were given resting state functional magnetic resonance brain scan. We used the high functional connectivity as features, reduced the dimensionality by 3 methods, and classified the features.
Results:
The principal component analysis achieved the best generalization performance, whose classification rate was 86.4%. Most features were the functional connectivity within or between the visual cortex network and the pre- and post-central and temporal lobe connectivity.
Conclusion:
Patients with schizophrenia can be identified with multivoxel pattern analysis based on the functional magnetic resonance imaging, and visual cortex network may play an important role in physiological explanation of the syndrome of schizophrenia.
