Detecting Abnormal Brain Regions in Schizophrenia Using Structural MRI via Machine Learning

Figure 1

Workflow diagram of the proposed framework. The framework contains three phases: (1) the preprocessing phase, which normalizes the brains of different subjects into the standard MNI space, segments them into gray matter (GM), white matter (WM), and cerebrospinal fluid (CSF), and smoothes voxels to reduce the effects of noise; (2) the feature selection phase, which uses two-sample t-tests and RFE to select discriminative features with a coarse-to-fine approach; and (3) the feature classification phase, which employs the linear SVM to classify features.