Study on the early detection of gastric cancer based on discrete wavelet transformation feature extraction of FT-IR spectra combined with probability neural network

Abstract

This paper introduces a new method for the early detection of gastric cancer using a combination of feature extraction based on discrete wavelet transformation (DWT) for horizontal attenuated total reflectance–Fourier transform infrared spectroscopy (HATR–FT-IR) and classification using probability neural network (PNN). 344 FT-IR spectra were collected from 172 pairs of fresh normal and abnormal stomach tissue᾽s samples. After preprocessing, 5 features were extracted with DWT analysis. Based on the PNN classification, all FT-IR spectra were classified into three categories. The accuracy of identifying normal gastric tissue, early gastric cancer tissue and gastric cancer tissue samples were 100.00, 97.56 and 100.00%, respectively. This result indicated that FT-IR with DWT and PNN could effectively and easily diagnose gastric cancer in its early stages.