Abstract

This paper deals with multi-classification of skin precancerous stages based on bimodal spectroscopy combining AutoFluorescence (AF) and Diffuse Reflectance (DR) measurements. The proposed data processing method is based on Discrete Cosine Transform (DCT) to extract discriminant spectral features and on Support Vector Machine to classify. Results show that DCT gives better results for AF spectra than for DR spectra. This study shows that bimodality and monitoring spectral resolution together allow an increase in diagnostic accuracy. The choice of an adequate spectral resolution always implies an increase in diagnostic accuracy. This accuracy can get as high as 79.0% when combining different distances between collecting and exciting optical fibers.

© 2011 OSA/SPIE