The Impact of Bilateral Cerebellar Transcranial Direct Current Stimulation on Balance Control in Healthy Young Adults.

Cerebellar transcranial direct current stimulation (tDCS) has been shown to influence movement functions, but little is known about the specific effects of stimulation polarity on balance control. This study investigated the impact of bilateral cerebellar tDCS on balance functions as a function of stimulation polarity. In this randomized, controlled trial, thirty-nine healthy young adults were assigned to one of three groups: right anodal/left cathodal cerebellar stimulation (AC group), right cathodal/left anodal cerebellar stimulation (CA group), and a control sham group. Each participant underwent a daily 30-minute session of tDCS at 2 mA for one week. Balance function was assessed pre- and post-intervention and the data were analyzed using generalized estimating equations. The CA group exhibited a significant reduction in sway area when standing on the left leg and on both stable and unstable surfaces with eyes open, compared to both the AC and sham groups. However, there were no significant differences among the groups in terms of sway length, anteroposterior velocity, or mediolateral velocity. Our results indicate the polarity-dependent effects of bilateral cerebellar tDCS on balance functions, with enhanced stability observed only following cathodal tDCS over the right cerebellum paired with anodal tDCS over the left cerebellum. This polarity-specific modulation may have implications for developing cerebellar neuromodulation interventions for movement disorders.

Multi-step framework for glaucoma diagnosis in retinal fundus images using deep learning.

Glaucoma is one of the most common causes of blindness in the world. Screening glaucoma from retinal fundus images based on deep learning is a common method at present. In the diagnosis of glaucoma based on deep learning, the blood vessels within the optic disc interfere with the diagnosis, and there is also some pathological information outside the optic disc in fundus images. Therefore, integrating the original fundus image with the vessel-removed optic disc image can improve diagnostic efficiency. In this paper, we propose a novel multi-step framework named MSGC-CNN that can better diagnose glaucoma. In the framework, (1) we combine glaucoma pathological knowledge with deep learning model, fuse the features of original fundus image and optic disc region in which the interference of blood vessel is specifically removed by U-Net, and make glaucoma diagnosis based on the fused features. (2) Aiming at the characteristics of glaucoma fundus images, such as small amount of data, high resolution, and rich feature information, we design a new feature extraction network RA-ResNet and combined it with transfer learning. In order to verify our method, we conduct binary classification experiments on three public datasets, Drishti-GS, RIM-ONE-R3, and ACRIMA, with accuracy of 92.01%, 93.75%, and 97.87%. The results demonstrate a significant improvement over earlier results.