Identification of schizophrenia by applying interpretable radiomics modeling with structural magnetic resonance imaging of the cerebellum.

AIMS: The cerebellum is involved in higher-order mental processing as well as sensorimotor functions. Although structural abnormalities in the cerebellum have been demonstrated in schizophrenia, neuroimaging techniques are not yet applicable to identify them given the lack of biomarkers. We aimed to develop a robust diagnostic model for schizophrenia using radiomic features from T1-weighted magnetic resonance imaging (T1-MRI) of the cerebellum. METHODS: A total of 336 participants (174 schizophrenia; 162 healthy controls [HCs]) were allocated to training (122 schizophrenia; 115 HCs) and test (52 schizophrenia; 47 HCs) cohorts. We obtained 2568 radiomic features from T1-MRI of the cerebellar subregions. After feature selection, a light gradient boosting machine classifier was trained. The discrimination and calibration of the model were evaluated. SHapley Additive exPlanations (SHAP) was applied to determine model interpretability. RESULTS: We identified 17 radiomic features to differentiate participants with schizophrenia from HCs. In the test cohort, the radiomics model had an area under the curve, accuracy, sensitivity, and specificity of 0.89 (95% confidence interval: 0.82-0.95), 78.8%, 88.5%, and 75.4%, respectively. The model explanation by SHAP suggested that the second-order size zone non-uniformity feature from the right lobule IX and first-order energy feature from the right lobules V and VI were highly associated with the risk of schizophrenia. CONCLUSION: The radiomics model focused on the cerebellum demonstrates robustness in diagnosing schizophrenia. Our results suggest that microcircuit disruption in the posterior cerebellum is a disease-defining feature of schizophrenia, and radiomics modeling has potential for supporting biomarker-based decision-making in clinical practice.

Status of primary liver cancer found through routine health check-up.

This study aimed to investigate the status of primary liver cancers found through a routine health check-up. The data of subjects who were diagnosed with primary liver cancer for the first time through a routine health check-up during a period of 8-yr were analyzed. Primary liver cancers were detected for the first time in 34 subjects among 91,219 routine health check-up subjects. Only 11.8% of primary liver cancer subjects had been under previous surveillance. Of them, 55.8% were positive for HBsAg, 17.7% were positive for anti-HCV, and 8.8% were heavy alcohol comsumers. However, 17.7% of the subjects were neither heavy alcohol consumers nor positive for both HBsAg and anti-HCV. Of the subjects, 50.0% had a single nodular tumor, 23.5% had multi-nodular tumors, and 26.5% had an infiltrative tumor. A routine health check-up may provide beneficial opportunities to detect a liver cancer in a very early stage. It is beneficial to start surveillance in high-risk subjects for liver cancer or to detect any liver cancer in subjects without risk factors of chronic viral hepatitis or heavy alcohol consumption.

Transient ischemic attacks presenting as hemiballism.

Hemiballism is continuous, nonpatterned involuntary movement characterized by irregular, coarse, flinging movement involving the limbs on one side. Hemiballism is most commonly caused by stroke. However, very rarely a transient ischemic attack (TIA) presents as hemiballism. We describe 2 such patients with hemiballism presenting as TIA.