Classification of FTIR Gastric Cancer Data Using Wavelets and SVM

In order to improve the accuracy to diagnose rate earlier stage gastric cancer with Fourier transform infrared spectroscopy (FTIR), a novel method of extraction of FTIR feature using continuous wavelet transform (CWT) analysis and classification using the support vector machine (SVM) was developed. To the FTIR of gastric normal tissue, early carcinoma and advanced gastric carcinoma, 9 feature parameters were extracted with continuous wavelet analysis. With SVM, all spectra were classified into two categories: normal or abnormal, which included early carcinoma and advanced gastric carcinoma. The accurate rate of poly and RBF kernel was high in all kernels. The accurate rate of poly kernel in normal, early carcinoma and advanced carcinoma were 100%, 96% and 100%, respectively. The accurate rate of RBF kernel in normal, early carcinoma and advanced carcinoma were 100%, 96% and 100%, respectively. The research result shows the feasibility of establishing the models with FTIR-CWT-SVM method to identify normal, early carcinoma and advanced gastric carcinoma.