Building on the databases of images of melanocytic lesions and certain methodological developments from the SKINAN and DIAMELA projects of the French National Agency for Research (ANR), it is proposed to build a computer-assisted melanoma diagnostics tool based on the presentation in real time of similar images of the case studied by the dermatologist and whose histology is known. The project aims to segment in both a supervised and semi-supervised manner, the image databases into groups having a perceived similarity. Approaches using pairwise and structured classifier types coupled notably with an extraction of characteristics through deep learning will be implemented. This original approach will be evaluated in the concrete framework of routine dermatological consultations. We expect to have a noticeable improvement in the quality of the diagnosis of melanocytic lesions, especially for suspicious lesions, responsible for a great deal of unnecessary excisional biopsies.