Research On Data Classification And Its Application In Medical Image Recognition Based On Rough Set

Diagnosis by medical image is one of the main methods of none wound diagnosis. Medical image has already been an important clinic diagnosis standard for disease diagnosis, decision-making before surgery, surgery navigation and random visiting after surgery. Research on medical image diagnosis is a cross science between physic and computer fields and an important research direction. Data mining and computer technology are used to analyze, compute and process medical images; abundant feature information and rules are mined from medical images, which can aid doctors to diagnose and has upper academic value and broad application foreground.Rough sets theory, proposed by Professor Pawlak in early 1980's, has been proved to be an excellent mathematical tool dealing with uncertain and vague description of objects, whose basic idea is to derive classification rules of conception by knowledge reduction with the ability of classifition unchanged.It may find the hiding and potential rules from the data without any preliminary or additional information.In recent years, as an important part of soft computing method, rough sets theory and its applications have played an important role, especially in the areas of pattern recognition, machine learning, decision analysis, knowledge discovery and knowledge acquisition etc.The study begins with the characteristics of medical data, summarize the general steps, key techniques and rough set theory in the medical data mining field, and the data preprocessing method is sumed up according to the need of this research. On the besis of the deep study of the discretization of continuous attributes and attribute reduction, aimed at the shortage of existing attribute reduction algorithm and combined with the characteristic of rough set theory, genetic algorithm and decision table, an efficient algorithm of attribute reduction in decision table is presented based on improved heuristic genetic Algorithm , it is proved to be effective by experiments.In the field of classification of knowledge, the characteristic of rough set and decision trees are analyzed respectively in the study, the possibility of the combination of the two data mining technique are also discussed, an new method of medical image classification based on the combination of rough sets and SLIQ decision trees is proposed, which improves classification efficiency in large data sets.This method is proved effetive and reliable too in medical image classification field by experiments.These algorithms mentioned in the paper are realized in the VC++ 6.0 environment and derive results in a medical data sets.