Computer-Aided Diagnosis of Gastric Carcinoma Based on Feature Selection and Probability Neural Network
Jun Liu, Wenli Ma, Zheng Wen-ling · 2009
Based on signal to noise ratio and probabilistic neural network method associated with experimental data, an analysis model in gastric carcinoma is presented. According to the available information, the samples of gastric carcinoma can be tested and analyzed. The signal to noise ratio is first calculated. Secondly, records in the database are chosen as a training set to build a probabilistic neural network model and the feature subset was selected according to accuracy. Finally, test set is to test accuracy of model. The model is implemented using MATLAB, and it can be generalized and applied to similar disease auxiliary diagnosis region.