Computer-aided Diagnosis of Gastric Carcinoma B ased on Feature Selection and Probability Neural Network
10.3969/j.issn.1673-6273.2008.05.041
- VernacularTitle:基于特征选择和概率神经网络胃癌计算机辅助诊断
- Author:
Jun LIU
1
;
Wen-Li MA
;
Wen-Juan YAO
;
Wen-Ling ZHENG
Author Information
1. 上海大学
- Keywords:
Feature selection;
S2N\SFS;
gastric carcinoma;
PNN
- From:
Progress in Modern Biomedicine
2008;8(5):924-927
- CountryChina
- Language:Chinese
-
Abstract:
Based on signal to noise ratio and probabilistic neural network method associated with experimental data,all analysis model in gastric carcinoma is presented.According to the available information,the samples of gastric carcinoma can be tested and ana.Lyzed.The signal to noise ratio is first calculated．Secondly,records in the database are chosen as a training set to build a probabilistie neural network model and the feature subset is 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.
