Support vector machine (SVM)‐based multivariate pattern analysis (MVPA) has delivered promising performance in decoding specific task states based on functional magnetic resonance imaging (fMRI) of the human brain. Conventionally, the SVM‐MVPA requires careful feature selection/extraction according to expert knowledge. In this study, we propose a deep neural network (DNN) for directly decoding multiple brain task states from fMRI signals of the brain without any burden for feature handcrafts. We trained and tested the DNN classifier using task fMRI data from the Human Connectome Project's S1200 dataset (N = 1,034). In tests to verify its performance, the proposed classification method identified seven tasks with an average accuracy of 93.7%. We also showed the general applicability of the DNN for transfer learning to small datasets (N = 43), a situation encountered in typical neuroscience research. The proposed method achieved an average accuracy of 89.0 and 94.7% on a working memory task and a motor classification task, respectively, higher than the accuracy of 69.2 and 68.6% obtained by the SVM‐MVPA. A network visualization analysis showed that the DNN automatically detected features from areas of the brain related to each task. Without incurring the burden of handcrafting the features, the proposed deep decoding method can classify brain task states highly accurately, and is a powerful tool for fMRI researchers.

Purpose: The pathological mechanisms of constant exotropia (XT) are still not understood. This study aimed to critically investigate whether patients with XT express neuronal activity changes after the critical period of visual development and further explore how these alterations are associated with behavioral performance. Materials and methods: Fourteen patients with XT and 16 healthy controls (HCs) underwent resting-state functional magnetic resonance imaging (fMRI). The regional homogeneity (ReHo) method was used to evaluate spontaneous brain activities. The association between significantly altered mean ReHo values and behavioral performance was assessed using Pearson’s correlation analysis. Results: Compared with HCs, the right secondary visual cortex (V2) in patients with XT exhibited increased ReHo values, whereas the left Brodmann area 47 (BA47) demonstrated decreased spontaneous ReHo values. In patients with XT, the correlation between the left BA47’s mean ReHo value and duration of strabismus was positively significant. Conclusions: These findings indicate that patients with XT have severe neural dysfunction in the right V2 and left BA47, and pathological severity in the left BA47 is likely influenced by duration of ongoing strabismus. Therefore, these results may provide clinically important information toward understanding the underlying pathological mechanisms of XT and thus can be fundamental in future XT research.

Previous studies have focused on global cerebral alterations observed in cirrhosis. However, little was known about the specific abnormalities of vision-related brain regions in cirrhotic patients. In this study, we sought to explore neurological alterations of vision-related regions by measuring brain resting-state network connectivity, based on the structural investigation in cirrhotic patients without clinical sign of hepatic encephalopathy (HE).