Cognitive evaluation model and high-resolution medical images in sports injury rehabilitation under bone density changes

In the study of bone density changes and sports injury rehabilitation, traditional image processing technology lacks accuracy in analysis, rehabilitation assessment methods lack quantitative and systematic analysis, and interdisciplinary comprehensive evaluation is lacking. This paper constructs an innovative cognitive assessment model that combines bone density changes, sports injury rehabilitation, and high-resolution medical image analysis. It uses high-resolution CT (Computed Tomography) images and X-ray images to extract bone density data. It uses image processing technology to remove noise, enhance, and standardize, providing accurate bone density values for subsequent input. GCN (Graph Convolutional Network) can be used to automatically identify and classify images of sports injury sites, extract features of the injured area, record and analyze the patient's physical activities during the rehabilitation stage, and evaluate the recovery process of sports injuries in real time. Combining bone density data with sports injury imaging features, XGBoost (Extreme Gradient Boosting) is used to build a cognitive evaluation model, which conducts a comprehensive analysis of multi-dimensional data and provides personalized rehabilitation evaluation. It can integrate technologies from fields such as medicine, engineering, and computer science to establish an interdisciplinary comprehensive evaluation system, achieve multi-angle and multi-dimensional analysis, and ensure the comprehensiveness and accuracy of the model. The experimental results show that the MAE (Mean Absolute Error) of the GCN in this paper is 0.131 in 10 different injury sites, and the average MSE (Mean Squared Error) is about 0.032, which has higher image analysis accuracy. The average accuracy and R² of XGBoost in six different samples are about 0.87 and 0.91, respectively, and the prediction effect of the cognitive evaluation model is apparent.