This paper outlines the development of artificial intelligence （AI） and its applications in traditional Chinese medicine （TCM） research， and elucidates the roles and advantages of large language models， knowledge graphs， and natural language processing in advancing syndrome identification， prescription generation， and mechanism exploration. Using spleen-stomach diseases as an example， it demonstrates the empowering effects of AI in classical literature mining， precise clinical syndrome differentiation， efficacy and safety prediction， and intelligent education， highlighting an upgraded research paradigm that evolves from data-driven and knowledge-driven approaches to intelligence-driven models. To address challenges related to privacy protection and regulatory compliance in cross-institutional data collaboration， a "trusted federated evidence-based analysis platform for TCM spleen-stomach diseases" is proposed， integrating blockchain-based smart contracts， federated learning， and secure multi-party computation. The deep integration of AI with privacy-preserving computing is reshaping research and clinical practice in TCM spleen-stomach diseases， providing feasible pathways and a technical framework for building a high-quality， trustworthy TCM big-data ecosystem and achieving precision syndrome differentiation.

Objective:A new algorithm based on Hough transform (HT) was proposed to improve the accuracy and stability of the film image analysis of Automatic Quality Assurance (AQA) test, and to explore the influence of the resolution of film image on the test results.Methods:Nine pairs of films were obtained for AQA modules in this study. Firstly, the median filter was used to preprocess the grayed-out film image to remove noise interference. Then, a global threshold was utilized to binarize the image. The images were edge-detected and the film edge line was extracted by Hough transform. The film image was transformed to the correct position. Finally, the edge of the field shadow circle and the shadow circle of the tungsten ball were extracted by the edge detection method and Hough transform. The radial error was finally obtained by analyzing the concentricity.Results:There was no significant difference in the accuracy between the test results yielded by the HT method and the AQA software ( P>0.05). The difference in the standard deviation of the test results was statistically significant ( P=0.027), indicating that the algorithm increased the stability while ensuring the accuracy of film analysis. Increasing the resolution of film scanning failed to significantly improve the accuracy and stability of film analysis in both two methods. Conclusions:The algorithm used in this study can eliminate the human error caused by film scanning placement while ensuring the accuracy of film analysis, providing a more stable way for the AQA test of the CyberKnife system.