Study on the early detection of gastric cancer based on discrete wavelet transformation feature extraction of FT-IR spectra combined with probability neural network. Issue 3 (2011)

• Record Type: Journal Article
• Authors: Hu, Tao; Lu, Yu-Hui; Cheng, Cun-Gui; Sun, Xiao-Chen
• Is Part Of: Spectroscopy. Volume 26:Issue 3(2011)
• Page Start: 155
• Page End: 165
• Publication Date: 2011
• Subjects: HATR–FT-IR -- discrete wavelet transformation -- probability neural network -- earlier stage of gastric cancer -- diagnose
• DOI: 10.3233/SPE-2011-0535
• Languages: English
• ISSNs: 0712-4813

Abstract

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.