3D and multispectral imaging technology to aid in the diagnosis of skin cancer

Abstract

Skin cancer is one of the most frequent cancers in humans. The most important risk factor is UV radiation due to excessive sun. Melanoma is the most aggressive skin cancer and its incidence increases every year. Early detection increases the probability of overcoming cancer but clinical examinations and biopsies behind are a slow, expensive and painful process. The application of technologies based on optics and photonics has been of great interest for the early detection of skin cancer over other technologies for being non-invasive. Multispectral imaging in the visible range and the analysis of the morphology of lesions by means of 3D topography have been recently proposed to achieve this goal. Accordingly, this thesis aims at studying the outputs of a multispectral imaging system and a 3D scanner to perform a statistical analysis in order to identify new relevant parameters that can allow the classification of different skin lesions with the aim of being used in the future for the early detection of skin cancer.