Human-machine interaction and computational neuroscience have brought unprecedented application prospects to the field of medical rehabilitation, especially for the elderly population, where the decline and recovery of hand function have become a significant concern. Responding to the special needs under the context of normalized epidemic prevention and control and the aging trend of the population, this research proposes a method based on a 3D deep learning model to process laser sensor point cloud data, aiming to achieve non-contact gesture surface feature analysis for application in the field of intelligent rehabilitation of human-machine interaction hand functions. By integrating key technologies such as the collection of hand surface point clouds, local feature extraction, and abstraction and enhancement of dimensional information, this research has constructed an accurate gesture surface feature analysis system. In terms of experimental results, this research validated the superior performance of the proposed model in recognizing hand surface point clouds, with an average accuracy of 88.72%. The research findings are of significant importance for promoting the development of non-contact intelligent rehabilitation technology for hand functions and enhancing the safe and comfortable interaction methods for the elderly and rehabilitation patients.

In the assessment of three-dimensional features of adolescent idiopathic scoliosis, the plane of maximum curvature was compared with the coronal Cobb angle. To investigate the intrarater reliability, variability, and difference of the prone plane of maximum curvature measurements taken from computed tomography using the constrained and unconstrained Cobb methods; to assess the difference and correlation between the prone plane of maximum curvature measurements obtained using the constrained and unconstrained Cobb methods; and to examine differences and correlation between the prone plane of maximum curvature Cobb angle and coronal Cobb angle measurements. Retrospective study. Records of 29 subjects with adolescent idiopathic scoliosis aged 15.8 ± 3.5 years were reviewed (25 thoracic and 24 thoracolumbar/lumbar curves). An experienced rater measured the plane of maximum curvature using the constrained and unconstrained Cobb methods, and the coronal Cobb angles using the conventional Cobb method on computed tomography images 3 times each with 1-week interval. The intraclass correlation coefficient (2,1), Pearson correlation coefficient (r), one-way repeated measures analysis of variance, and paired t test were applied for various analyses. The intraclass correlation coefficients for all intrarater reliability assessments were greater than 0.87. The plane of maximum curvature measurements of the two Cobb methods were excellently correlated (r ⩾ 0.97) with no significant difference (P > 0.05). The mean plane of maximum curvature Cobb angle was moderately correlated with (r > 0.72) but significantly greater (P < 0.001) than the mean coronal Cobb angle. The plane of maximum curvature measurements obtained from computed tomography were found to be reliable while the plane of maximum curvature measurements of the two Cobb methods were comparable. The mean plane of maximum curvature Cobb angle was moderately correlated with but significantly greater than the mean coronal Cobb angle. The plane of maximum curvature measurements taken from computed tomography was found to be reliable, hence it could be used as a supplement to the coronal Cobb angle in the assessment and management of adolescent idiopathic scoliosis. With technological advancement, the radiation dose of computed tomography can be further reduced to a safer level for a broader range of cases.