1. Visible and extended near-infrared multispectral imaging for skin cancer diagnosis
- Author
-
Meritxell Vilaseca, Santiago Royo, Josep Malvehy, Miguel Ares, Laura Rey-Barroso, Francisco J. Burgos-Fernández, Xana Delpueyo, Susana Puig, Universitat Politècnica de Catalunya. Departament d'Òptica i Optometria, and Universitat Politècnica de Catalunya. GREO - Grup de Recerca en Enginyeria Òptica
- Subjects
Skin Neoplasms ,Light ,Infrared ,Multispectral image ,01 natural sciences ,Biochemistry ,Analytical Chemistry ,Multispectral imaging ,030207 dermatology & venereal diseases ,0302 clinical medicine ,multispectral imaging ,Image Processing, Computer-Assisted ,Skin cancer ,Instrumentation ,Melanoma ,skin cancer ,Imatges infraroges ,Optical Imaging ,Detectors ,Atomic and Molecular Physics, and Optics ,Skin diseases ,Diagnòstic per la imatge ,infrared ,Principal component analysis ,Diagnostic imaging ,Skin lesion ,Algorithms ,Infrared detectors ,Materials science ,Infrared Rays ,Article ,010309 optics ,InGaAs camera ,03 medical and health sciences ,Optics ,Skin--Cancer ,0103 physical sciences ,melanoma ,medicine ,Humans ,Electrical and Electronic Engineering ,Càncer de pell ,business.industry ,Near-infrared spectroscopy ,Enginyeria de la telecomunicació::Processament del senyal::Processament de la imatge i del senyal vídeo [Àrees temàtiques de la UPC] ,medicine.disease ,Support vector machine ,Ciències de la salut::Medicina::Dermatologia [Àrees temàtiques de la UPC] ,Malalties de la pell ,Pell -- Càncer ,Classification methods ,business ,Detectors de raigs infraroigs - Abstract
With the goal of diagnosing skin cancer in an early and noninvasive way, an extended near infrared multispectral imaging system based on an InGaAs sensor with sensitivity from 995 nm to 1613 nm was built to evaluate deeper skin layers thanks to the higher penetration of photons at these wavelengths. The outcomes of this device were combined with those of a previously developed multispectral system that works in the visible and near infrared range (414 nm–995 nm). Both provide spectral and spatial information from skin lesions. A classification method to discriminate between melanomas and nevi was developed based on the analysis of first-order statistics descriptors, principal component analysis, and support vector machine tools. The system provided a sensitivity of 78.6% and a specificity of 84.6%, the latter one being improved with respect to that offered by silicon sensors.