Application of AI for CT image identification

Based on the full investigation of medical diagnose method, this article brings up a new perspective based on CBR to research and implement Medical Diagnosis Expert System against the shortcomings of RBR System. Analyzed the content and method of image cases representation Uses frame to represent image cases, puts case ID, case Category, case features, diagnosis result, treatment, auxiliary property into cases. Made a detailed analysis and design of case-base' structure and organization. Used two-level-structure to organize case-base:typical case-base and specific sub-case-base. Adopted maximum-similarity-method to classify the original case-base to construct each specific sub-case-base; used calculating "max sum among cases" to search the typical case in each sub-case-base. Designed a method to calculate case symptom weight. The key technologies of the system have been discussed comprehensively, which contains: case retrieving, modifying, learning and case-base maintaining. Among those key technologies, case retrieving is the core step. The system used phasic-nearest-neighbor strategy to retrieve cases in case-base. This strategy combining with two-level-structure highly reduced retrieving times, so that improved the efficiency of search.