期刊
SPECTROSCOPY-BIOMEDICAL APPLICATIONS
卷 26, 期 3, 页码 155-165出版社
IOS PRESS
DOI: 10.1155/2011/946783
关键词
HATR-FT-IR; discrete wavelet transformation; probability neural network; earlier stage of gastric cancer; diagnose
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.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据