nalysis of Cutaneous Leishmaniasis Hyperspectral Images by Means of an Inverse Modeling Procedure

摘要

Latin America and other places in the world have tropical regions, from which multiple diseases emerge. CutaneousLeishmaniasis (CL) is one of the most common pathologies that attack the populations on these areas,generating an ulcer and leaving marks for life. The difficult access to appropriate medical attention of affectedpopulations raises the need for new instruments and techniques that facilitate the diagnosis and monitoring oftreatments for this disease. This article proposes a methodology of analysis of golden hamster skin with cutaneousulcer caused by leishmaniasis through a three-layer inverse reectance model, genetic algorithms andthe Hyperspectral image acquisition system ASCLEPIOS. As a result, the concentration maps of: thickness ofthe epidermis (epi), epidermis plus thickness of the dermis (epiPder), volumetric fraction of blood (Fblood),diameter of the Collagen particles (Coll), volumetric fraction of collagen (Fcoll), diameter of the Fibroblastparticles (Fibro), volumetric fraction of melanin (Fmel), diameter of Keratynocytes particles (Kera), diameterof Macrophages particles (Macro), and oxygen saturation (OS) were obtained. The ANOVA test on the concentrationmaps was used. In this way, it is observed which variables allow to statistically differentiate healthytissue from nodular tissue and ulcer center, in this way it is observed that fibroblasts and oxygen saturation arethe parameters that statistically differentiate healthy tissue to tissue with nodule. In the case of healthy tissueand ulcer center, the differentiating parameters are fibroblasts and volumetric fraction of melanin.