Wavelength selection by genetic algorithms in near infrared spectra for melanoma diagnosis
2005 (English)In: IFMBE Proceedings, Volume 11, 3rd European Medical & Biological Engineering Conference (EMBEC’05) in Prague (Czech Republic), 2005Conference paper (Refereed)
Early, reliable and fast diagnosis of melanoma is particularly important as the number of cases is increasing. In this paper, the potential of using near infrared spectroscopy for melanoma diagnosis is studied. The classification task is complicated by a low signal-to-noise ratio and the high dimensionality of the spectral data. Thus pre-selection of wavelength variables is required. Atypical naevi samples of patients were clinically classified, using the ABCD rule, and their near infrared spectra recorded. A nonlinear clustering model for spectral based classification was calibrated to the spectra and pathologist?s classification using a genetic algorithm. The genetic algorithm optimized the spectral based classification by selecting wavelengths correlated to melanoma. Some wavelength selections allowed correct classification of all samples in our dataset. The small size of the dataset and uncertainty in the clinical classification, however, limit the conclusions that can be drawn. Evidence for the existence of spectral regions that contain information needed for melanoma diagnosis is presented.
Place, publisher, year, edition, pages
Feature selection, Genetic Algorithms, Melanoma, Near-infrared spectrum, Variable selection
Medical Laboratory and Measurements Technologies
IdentifiersURN: urn:nbn:se:kth:diva-80739OAI: oai:DiVA.org:kth-80739DiVA: diva2:496839
3rd European Medical & Biological Engineering Conference (EMBEC’05)