Article

Diagnóstico de lesiones en la piel a partir de espectros de reflexión difusa empleando algoritmos computacionales: un estudio preliminar

Instituto Nacional de Astrofísica Óptica y Electrónica, C.P 72000, Puebla, México; Facultad Expe-rimental de Ciencia y Tecnología, Depto. de Física, Universidad de Carabobo, C.P.2005, Valencia, Venezuela; Centro de Aplicaciones Tecnológicas y Desarrollo Nuclear, CEADEN-CITMA, Física, Cuba
66 Rev. Cub. Física 01/2010; 27(27):66-69.

ABSTRACT Sumario. La determinación del espectro de reflexión difusa de la piel humana en el rango espectral de 400 nm-1000 nm empleando espectrómetros de fibras ópticas es una técnica no invasiva ampliamente usada para estudiar los parámetros ópticos de este órgano, brinda información sobre las propiedades de absorción y de esparcimiento de la luz que pueden ser empleadas para estudiar la morfología y fisiología del tejido y poder detectar y diagnosticar enfermedades de la piel en su etapa inicial. En este trabajo se propone un algoritmo computacional para la selección de los atributos más rele-vantes de los espectros de reflexión difusa en la piel humana obtenidos con un sistema experimental que consta básica-mente de un espectrómetro, una fuente de luz blanca y una sonda de fibra óptica bifurcada que permite enviar y colectar la luz. Para clasificar la señal espectral se ha diseñado una interfaz gráfica en Matlab2006© que hace uso de las máqui-nas de soporte vectorial y se ha utilizado un algoritmo de selección de atributos que permite alcanzar una sensibilidad y especificidad superior al 80% y una exactitud en la clasificación del 85%. Abstract. The determination of diffuse reflection spectrum on human skin in the spectral range from 400nm-1000nm using an optical fiber spectrometers is a non-invasive technique widely used to study the optical parameters of this tis-sue, provides information about the absorption and scattering properties of light that can be employed to study the mor-phology and physiology of the tissue and to detect and diagnose skin diseases in early stages. In this paper a computa-tional algorithm for the selection of the most important attributes of diffuse reflection spectra of human skin obtained with an experimental system that basically consists of a spectrometer, a white light source and bifurcated fiber optic probe that allows send and collect light. To classify the spectral signal was designed a Matlab2006© graphical interface which use support vector machines and algorithm for selecting attributes that allows to achieve a sensitivity and speci-ficity exceeding 80% and 85% of accuracy in the classification.

1 Bookmark
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: Optical technologies, in particular fluorescence spectroscopy, have shown the potential to provide improved detection methods for cervical neoplasia that are sensitive and cost effective through accurate, objective, instantaneous point-of-care diagnostic tools. The specific goals of this study were to analyze reflectance spectra of normal and neoplastic cervical tissue in vivo and to evaluate the data for use in diagnostic algorithm development. Spectroscopic measurements were obtained at four distinct source-detector separations from 324 sites in 161 patients. As the source-detector separation increases, greater tissue depth is probed. The average spectra of each diagnostic class differed at all source-detector separations, with the greatest differences occurring at the smallest source-detector separations. Algorithms, based on principal-component analysis and Mahalanobis distance classification, were developed and evaluated for all combinations of source-detector separations relative to the gold standard of colposcopically directed biopsy. The diagnostic combination of squamous normal versus high-grade squamous intraepithelial lesions gave good discrimination with a sensitivity of 72% and a specificity of 81%; discrimination of columnar normal versus high-grade squamous intraepithelial lesions also was good, with sensitivity of 72% and specificity of 83%. Thus, reflectance spectroscopy appears promising for in vivo detection of cervical precancer. Strategies that combine fluorescence and reflectance spectroscopy may enhance the discrimination capabilities.
    Journal of Biomedical Optics 11/2002; 7(4):587-94. · 2.88 Impact Factor
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: We review the application of fluorescence spectroscopy and elastic-scattering spectroscopy, over the ultraviolet-to-visible wavelength range, to minimally invasive medical diagnostics. The promises and hopes, as well as the difficulties, of these developing techniques are discussed.
    Physics in Medicine and Biology 06/1997; 42(5):803-14. · 2.70 Impact Factor
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: Incremental search reuses information from previous searches to find solutions to a series of similar search prob-lems potentially faster than is possible by solving each search problem from scratch. This is important since many artificial intelligence systems have to adapt their plans con-tinuously to changes in (their knowledge of) the world. In this article, we therefore give an overview of incremental search, focusing on Lifelong Planning A*, and outline some of its possible applications in artificial intelligence.
    Ai Magazine - AIM. 01/2004;

Full-text

View
Available from