Share Email Print

Journal of Biomedical Optics

Adaptive spectral window sizes for extraction of diagnostic features from optical spectra
Author(s): Chih-Wen Kan; Andy Y. Lee; Linda T. Nieman; Konstantin V. Sokolov; Mia K. Markey
Format Member Price Non-Member Price
PDF $20.00 $25.00

Paper Abstract

We present an approach to adaptively adjust the spectral window sizes for optical spectra feature extraction. Previous studies extracted features from spectral windows of a fixed width. In our algorithm, piecewise linear regression is used to adaptively adjust the window sizes to find the maximum window size with reasonable linear fit with the spectrum. This adaptive windowing technique ensures the signal linearity in defined windows; hence, the adaptive windowing technique retains more diagnostic information while using fewer windows. This method was tested on a data set of diffuse reflectance spectra of oral mucosa lesions. Eight features were extracted from each window. We performed classifications using linear discriminant analysis with cross-validation. Using windowing techniques results in better classification performance than not using windowing. The area under the receiver-operating-characteristics curve for windowing techniques was greater than a nonwindowing technique for both normal versus mild dysplasia (MD) plus severe high-grade dysplasia or carcinama (SD) (MD+SD) and benign versus MD+SD. Although adaptive and fixed-size windowing perform similarly, adaptive windowing utilizes significantly fewer windows than fixed-size windows (number of windows per spectrum: 8 versus 16). Because adaptive windows retain most diagnostic information while reducing the number of windows needed for feature extraction, our results suggest that it isolates unique diagnostic features in optical spectra.

Paper Details

Date Published: 1 July 2010
PDF: 12 pages
J. Biomed. Opt. 15(4) 047012 doi: 10.1117/1.3481143
Published in: Journal of Biomedical Optics Volume 15, Issue 4
Show Author Affiliations
Chih-Wen Kan, The Univ. of Texas at Austin (United States)
Andy Y. Lee, The Univ. of Texas M.D. Anderson Cancer Ctr. (United States)
The Univ. of Texas Health Science Ctr. at Houston (United States)
Linda T. Nieman, The Univ. of Texas M.D. Anderson Cancer Ctr. (United States)
Sandia National Labs. (United States)
Konstantin V. Sokolov, The Univ. of Texas M.D. Anderson Cancer Ctr. (United States)
Mia K. Markey, The Univ. of Texas at Austin (United States)

© SPIE. Terms of Use
Back to Top