Altered intrinsic cerebellar-cerebral functional connectivity is related to negative symptoms in patients with first-episode psychosis.

BACKGROUND: Negative symptoms in schizophrenia include cognitive and affective dysfunction, such as diminished expression and amotivation. Although the cerebellar posterior hemisphere and vermis are involved in cognitive and affective functioning, previous studies on the neural mechanism of negative symptoms have mostly been confined to the cerebral cortex. This study aimed to investigate whether resting-state cerebellar-cerebral functional connectivity (FC) is altered in first-episode psychosis (FEP) patients and whether this connectivity is related to negative symptoms. METHODS: Resting-state functional magnetic resonance images were obtained from 38 FEP patients and 100 healthy controls (HCs). Using the posterior hemisphere and vermis of the cerebellum as seeds, whole-brain FC was compared between FEP patients and HCs. As cerebellar-parietal cortex connectivity is associated with negative symptoms and sociocognitive dysfunctions in schizophrenia patients, its correlation with negative symptoms was explored in FEP patients. RESULTS: FEP patients showed hyperconnectivity between the cerebellum and bilateral frontal pole (FP), occipital pole, fusiform gyrus, right lingual gyrus, central opercular cortex, anterior middle temporal gyrus, precuneus, and subcallosal cortex. Hypoconnectivity was found between the cerebellum and left FP, right anterior supramarginal gyrus (aSMG), and cerebellum crus I. FC between the left crus II and right aSMG was negatively correlated with the severity of negative symptoms and diminished expression. CONCLUSIONS: Altered FC between the cerebellum and cerebral regions related to cognitive, affective, and sensory processing was found in FEP patients and was connected to negative symptoms. These results suggest that the cerebellum plays a role in the pathophysiology of negative symptoms in schizophrenia.

Evaluation of a deep learning-based computer-aided detection algorithm on chest radiographs: Case-control study.

ABSTRACT: Along with recent developments in deep learning techniques, computer-aided diagnosis (CAD) has been growing rapidly in the medical imaging field. In this work, we evaluate the deep learning-based CAD algorithm (DCAD) for detecting and localizing 3 major thoracic abnormalities visible on chest radiographs (CR) and to compare the performance of physicians with and without the assistance of the algorithm. A subset of 244 subjects (60% abnormal CRs) was evaluated. Abnormal findings included mass/nodules (55%), consolidation (21%), and pneumothorax (24%). Observer performance tests were conducted to assess whether the performance of physicians could be enhanced with the algorithm. The area under the receiver operating characteristic (ROC) curve (AUC) and the area under the jackknife alternative free-response ROC (JAFROC) were measured to evaluate the performance of the algorithm and physicians in image classification and lesion detection, respectively. The AUCs for nodule/mass, consolidation, and pneumothorax were 0.9883, 1.000, and 0.9997, respectively. For the image classification, the overall AUC of the pooled physicians was 0.8679 without DCAD and 0.9112 with DCAD. Regarding lesion detection, the pooled observers exhibited a weighted JAFROC figure of merit (FOM) of 0.8426 without DCAD and 0.9112 with DCAD. DCAD for CRs could enhance physicians' performance in the detection of 3 major thoracic abnormalities.