Structural abnormalities in Schizophrenia(SZ)patients have been well documented with structural magnetic resonance imaging(MRI).In this study,we first applied voxel-based morphometry(VBM)method to compare gray matter volume(GMV)and white matter volume(WMV)between 41 SZ patients and 42 age and sex matched normal controls(NC).We found that SZ patients showed gray and white matter abnormalities in a variety of brain structures primarily in the parietal and occipital lobes.Moreover,the method of support vector machine(SVM)combined with recursive feature elimination(RFE)was used to discriminate SZ patients from NC subjects by using the significant group differences in both GMV and WMV.Our results achieved the high values of accuracy(84.4%),sensitivity(92.49%),and specificity(75.6%)in the automatic classification between SZ and NC.Distinct neuroanatomical profiles associated with SZ patients may provide a potential biomarker for disease diagnosis.