Automated brain lesion segmentation provides valuable information for the analysis and intervention of patients. In particular, methods that are based on convolutional neural networks (CNNs) have achieved state-of-the-art segmentation performance. However, CNNs usually require a decent amount of annotated data, which may be costly and time-consuming to obtain. Since unannotated data is generally abundant, it is desirable to use unannotated data to improve the segmentation performance for CNNs when limited annotated data is available. In this work, we propose a semi-supervised learning (SSL) approach to brain lesion segmentation, where unannotated data is incorporated into the training of CNNs. We adapt the mean teacher model, which is originally developed for SSL-based image classification, for brain lesion segmentation. Assuming that the network should produce consistent outputs for similar inputs, a loss of segmentation consistency is designed and integrated into a self-ensembling framework. Self-ensembling exploits the information in the intermediate training steps, and the ensemble prediction based on the information can be closer to the correct result than the single latest model. To exploit such information, we build a student model and a teacher model, which share the same CNN architecture for segmentation. The student and teacher models are updated alternately. At each step, the student model learns from the teacher model by minimizing the weighted sum of the segmentation loss computed from annotated data and the segmentation consistency loss between the teacher and student models computed from unannotated data. Then, the teacher model is updated by combining the updated student model with the historical information of teacher models using an exponential moving average strategy. For demonstration, the proposed approach was evaluated on ischemic stroke lesion segmentation. Results indicate that the proposed method improves stroke lesion segmentation with the incorporation of unannotated data and outperforms competing SSL-based methods.

The present study aimed to explore the effect of computerized multi-domain cognitive training (MDCT) on brain gray matter volume and neuropsychological performance in patients with amnestic mild cognitive impairment (amnestic MCI). Twenty-one patients with amnestic MCI participated in a computerized MDCT program. The program targeted a broad set of cognitive domains via programs focused on reasoning, memory, visuospatial, language, calculation, and attention. Seventeen Participants completed the intervention and all completed a battery of neuropsychological tests to evaluate cognitive function while 12 out of 17 underwent 3 T MRI scanning before and after the intervention to measure gray matter (GM) volume. We examined correlations between the changes in neuropsychological scores and GM volumes across participants after the intervention. After training, we observed significant increases in GM volume in the right angular gyrus (AG) and other parietal subareas near the intraparietal sulcus (p < 0.05, FWE-corrected, 10000 permutations). However, we found no significant changes in neuropsychological test scores (p > 0.05). A correlation analysis revealed positive correlations between the changes in GM volume in the right AG and scores in the immediate recall component of the Hopkins Verbal Learning Test-Revised (HVLT-R) (r = 0.64, p = 0.024) and the Brief Visuospatial Memory Test–Revised (BVMT-R) (r = 0.67, p = 0.016). Our findings indicate that a computerized MDCT program may protect patients with amnestic MCI against brain GM volume loss and has potential in preserving general cognition. Thus, our non-pharmacological intervention may slow the rate of disease progression.

No abstract

Dysfunction of brain-derived arginine-vasopressin (AVP) systems may be involved in the etiology of autism spectrum disorder (ASD). Certain regions such as the hypothalamus, amygdala, and hippocampus are known to contain either AVP neurons or terminals and may play an important role in regulating complex social behaviors. The present study was designed to investigate the concomitant changes in autistic behaviors, circulating AVP levels, and the structure and functional connectivity (FC) of specific brain regions in autistic children compared with typically developing children (TDC) aged from 3 to 5 years. The results showed: (1) children with ASD had a significantly increased volume in the left amygdala and left hippocampus, and a significantly decreased volume in the bilateral hypothalamus compared to TDC, and these were positively correlated with plasma AVP level. (2) Autistic children had a negative FC between the left amygdala and the bilateral supramarginal gyri compared to TDC. The degree of the negative FC between amygdala and supramarginal gyrus was associated with a higher score on the clinical autism behavior checklist. (3) The degree of negative FC between left amygdala and left supramarginal gyrus was associated with a lowering of the circulating AVP concentration in boys with ASD. (4) Autistic children showed a higher FC between left hippocampus and right subcortical area compared to TDC. (5) The circulating AVP was negatively correlated with the visual and listening response score of the childhood autism rating scale. These results strongly suggest that changes in structure and FC in brain regions containing AVP may be involved in the etiology of autism.Electronic supplementary materialThe online version of this article (doi:10.1007/s12264-017-0109-2) contains supplementary material, which is available to authorized users.

No abstract