10 December 2013 Statistical analysis of spectral data: a methodology for designing an intelligent monitoring system for the diabetic foot
Author Affiliations +
J. of Biomedical Optics, 18(12), 126004 (2013). doi:10.1117/1.JBO.18.12.126004
Abstract
Early detection of (pre-)signs of ulceration on a diabetic foot is valuable for clinical practice. Hyperspectral imaging is a promising technique for detection and classification of such (pre-)signs. However, the number of the spectral bands should be limited to avoid overfitting, which is critical for pixel classification with hyperspectral image data. The goal was to design a detector/classifier based on spectral imaging (SI) with a small number of optical bandpass filters. The performance and stability of the design were also investigated. The selection of the bandpass filters boils down to a feature selection problem. A dataset was built, containing reflectance spectra of 227 skin spots from 64 patients, measured with a spectrometer. Each skin spot was annotated manually by clinicians as “healthy” or a specific (pre-)sign of ulceration. Statistical analysis on the data set showed the number of required filters is between 3 and 7, depending on additional constraints on the filter set. The stability analysis revealed that shot noise was the most critical factor affecting the classification performance. It indicated that this impact could be avoided in future SI systems with a camera sensor whose saturation level is higher than 106 , or by postimage processing.
© 2013 Society of Photo-Optical Instrumentation Engineers (SPIE)
Chanjuan Liu, Jaap J. van Netten, Marvin E. Klein, Jeff G. van Baal, Sicco A. Bus, Ferdi van der Heijden, "Statistical analysis of spectral data: a methodology for designing an intelligent monitoring system for the diabetic foot," Journal of Biomedical Optics 18(12), 126004 (10 December 2013). http://dx.doi.org/10.1117/1.JBO.18.12.126004
JOURNAL ARTICLE
12 PAGES


SHARE
KEYWORDS
Optical filters

Skin

Statistical analysis

Intelligence systems

Error analysis

Linear filtering

Principal component analysis

RELATED CONTENT


Back to Top