Automated content based image retrieval technology (CBIR) and ITS application on dermoscopic images of pigmented skin lesions

Abstract

Dermoscopy (dermatoscopy, epiluminescence microscopy) is a non-invasive diagnostic technique for the in vivo observation of pigmented skin lesions (PSLs). This diagnostic tool permits the recognition of morphological structures not visible to the naked eye, thereby providing a new dimension to the analysis of the clinical morphologic features of PSLs. Due to the difficulty and variability of human interpretation, computerized analysis of dermoscopy images has become an important area of research and Numerous systems designed to provide computer-aided analysis of digital images have recently been reported in literature. Contentbased image retrieval systems (CBIR) technology exploits the visual content in image data. It proposes to benefit the management of increasingly large biomedical image collections as well as to aid clinical medicine, research and education. The goal of this article is to describe the application of CBIR systems for dermoscopic images, describing in detail the FIDE model created in our laboratory. FIDE's function is to document the image analysis side of the diagnostic process, focusing on accompanying and aiding it, and on providing efficient digital atlas navigation by providing precision (cases most similar to the one under analysis) and clarifying context (similar cases in different categories). The FIDE system is effective in retrieving PSL images with known pathology visually similar to the image under evaluation, giving a valuable and intuitive aid to the clinician in the decision making process. FIDE represents, indeed, the first CBIR system successfully applied to dermoscopic images. The real impact of this system in clinical practice will be revealed only by its application in a wide clinical setting.