Share Email Print

Journal of Biomedical Optics

Statistical analysis of spectral data: a methodology for designing an intelligent monitoring system for the diabetic foot
Author(s): Chanjuan Liu; Jaap J. van Netten; Marvin E. Klein; Jeff G. van Baal; Sicco A. Bus; Ferdi van der Heijden
Format Member Price Non-Member Price
PDF $20.00 $25.00

Paper 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.

Paper Details

Date Published: 10 December 2013
PDF: 12 pages
J. Biomed. Opt. 18(12) 126004 doi: 10.1117/1.JBO.18.12.126004
Published in: Journal of Biomedical Optics Volume 18, Issue 12
Show Author Affiliations
Chanjuan Liu, Univ. Twente (Netherlands)
Jaap J. van Netten, Hospital Group Twente (Netherlands)
Marvin E. Klein, DEMCON Advanced Mechatronics BV (Netherlands)
Jeff G. van Baal, Univ. Twente (Netherlands)
Sicco A. Bus, Hospital Group Twente (Netherlands)
Ferdi van der Heijden, Univ. Twente (Netherlands)

© SPIE. Terms of Use
Back to Top