The healing process of chronic wounds is complex, and the complete pathogenesis is not known. Diagnosis is currently based on visual inspection, biopsies and collection of samples from the wound surface. This is often time consuming, expensive and to some extent subjective procedures. Hyperspectral imaging has been shown to be a promising modality for optical diagnostics. The main objective of this study was to identify a suitable technique for reproducible classification of hyperspectral data from a wound and the surrounding tissue. Two statistical classification methods have been tested and compared to the performance of a dermatologist. Hyperspectral images (400-1000 nm) were collected from patients with venous leg ulcers using a pushbroom-scanning camera (VNIR 1600, Norsk Elektro Optikk AS).Wounds were examined regularly over 4 - 6 weeks. The patients were evaluated by a dermatologist at every appointment. One patient has been selected for presentation in this paper (female, age 53 years). The oxygen saturation of the wound area was determined by wavelength ratio metrics. Spectral angle mapping (SAM) and k-means clustering were used for classification. Automatic extraction of endmember spectra was employed to minimize human interaction. A comparison of the methods shows that k-means clustering is the most stable method over time, and shows the best overlap with the dermatologist’s assessment of the wound border. The results are assumed to be affected by the data preprocessing and chosen endmember extraction algorithm. Results indicate that it is possible to develop an automated method for reliable classification of wounds based on hyperspectral data.

Date Published: 8 March 2013
PDF: 14 pages
Proc. SPIE 8565, Photonic Therapeutics and Diagnostics IX, 85650N (8 March 2013); doi: 10.1117/12.2001087

Published in SPIE Proceedings Vol. 8565:
Photonic Therapeutics and Diagnostics IX
Andreas Mandelis; Brian Jet-Fei Wong; Anita Mahadevan-Jansen; Henry Hirschberg M.D.; Hyun Wook Kang; Nikiforos Kollias; Melissa J. Suter; Kenton W. Gregory M.D.; Guillermo J. Tearney M.D.; Stephen Lam; Bernard Choi; Steen J. Madsen; Bodo E. Knudsen M.D.; E. Duco Jansen; Justus F. Ilgner M.D.; Haishan Zeng; Matthew Brenner; Laura Marcu, Editor(s)