Study on the early detection of gastric cancer based on discrete wavelet transformation feature extraction of FT-IR spectra combined with probability neural network
Affiliations: Faculty of Life Science and Chemical Engineering, Huaiyin Institute of Technology, Huaian, China | National Special Superfine Powder Engineering Center, Nanjing University of Science and Technology, Nanjing, China | The First College of Clinic Medicine, Zhejiang Chinese Medical University, Hangzhou, China | Department of Chemistry, Zhejiang Normal University, Jinhua, China | Department of Physics, Zhejiang Normal University, Jinhua, China
Note: [] Corresponding author: Tao Hu, Faculty of Life Science and Chemical Engineering, Huaiyin Institute of Technology, Huaian 223003, China. Tel.: +86 517 8359 1044; E-mail: [email protected].
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.
Keywords: HATR–FT-IR, discrete wavelet transformation, probability neural network, earlier stage of gastric cancer, diagnose
DOI: 10.3233/SPE-2011-0535
Journal: Spectroscopy, vol. 26, no. 3, pp. 155-165, 2011
