In Vivo Cancer Detection in Animal Model Using Hyperspectral Image Classification with Wavelet Feature Extraction

摘要

Hyperspectral imaging (HSI) is a promising optical imaging technique for cancer detection. However, quantitative methodsneed to be developed in order to utilize the rich spectral information and subtle spectral variation in such images. In thisstudy, we explore the feasibility of using wavelet-based features from in vivo hyperspectral images for head and neckcancer detection. Hyperspectral reflectance data were collected from 12 mice bearing head and neck cancer. Catenation of5-level wavelet decomposition outputs of hyperspectral images was used as a feature for tumor discrimination. A supportvector machine (SVM) was utilized as the classifier. Seven types of mother wavelets were tested to select the one with thebest performance. Classifications with raw reflectance spectra, 1-level wavelet decomposition output, and 2-level waveletdecomposition output, as well as the proposed feature were carried out for comparison. Our results show that the proposedwavelet-based feature yields better classification accuracy, and that using different type and order of mother waveletachieves different classification results. The wavelet-based classification method provides a new approach for HSIdetection of head and neck cancer in the animal model.