Comparison of Incidental Findings of Brain Magnetic Resonance Imaging of Schizophrenia Patients, First-Episode Psychosis Patients and Healthy Controls.

BACKGROUND: It has been emphasized for a long time that neurodevelopmental and neurodegenerative processes play an important role in the etiology of schizophrenia. SUBJECTS AND METHODS: In this study, brain magnetic resonance imaging (MRI) of 97 patients with schizophrenia (SCH), 42 first-episode psychosis (FEP) patients, and 70 healthy controls (HC) were analyzed, and abnormal findings on brain MRI were recorded. Participant's age, gender, and brain MRI findings were recorded retrospectively. Fazekas grades evaluated the distribution of white matter hyperintensities in the brain. RESULTS: The mean ages of FEP, SCH, and HC were 24.8±6.3, 36.9±11.5, and 36±10.5, respectively. Generalized cerebral atrophy was higher in SCH and HC than in FEP groups, and frontoparietal atrophy was higher in the SCH group than in HC and FEP groups (p<0.001). The percentage of Fazekas Grade-1 was higher in the SCH group than HC and FEP groups (p=0.006). Additionally, the cavum veli interpositi (CVI) rate was higher in FEP and SCH groups than in the HC group (p=0.042). CONCLUSION: Although there was no significant age difference between the SCH and HC groups, the higher prevalence of generalized cerebral atrophy in the SCH group may indicate the neurodegenerative process of schizophrenia. The fact that CVI, a congenital brain anomaly, was detected more frequently in the FEP and SCH groups may suggest that schizophrenia may be associated with neurodevelopmental process.

A novel diagnosis method for schizophrenia based on globus pallidus data.

This research aims to diagnose schizophrenia with machine learning-based algorithms. Bayesian neural network, logistic regression, decision tree, k-nearest neighbor, and gaussian kernel classification techniques are investigated to diagnose schizophrenia with data from 125 persons. This study showed that left lateral ventricles and left globus pallidus volumes and their percentages in the brain were significantly lower than HCs in FEP patients. Using brain volumes, we were able to diagnose FEP with an accuracy of 73.6 % via logistic regression and with an accuracy of 86.4 % using the SVM kernel classifier method. Therefore, brain volumes can be used to diagnose FEP with the SVM kernel classifier method.