A Knowledge Based System for Early Melanoma Diagnosis Support

Melanoma is the most dangerous skin cancer and early diagnosis is the key factor in its successful treatment. Experienced dermatologists with specific training make the diagnosis by clinical inspection and they reach 80% level of both sensitivity and specificity. In this paper, we present MEDS (MElanoma Diagnosis System): a knowledge-based system for supporting the early diagnosis of melanoma, which combines image-processing techniques with machine learning techniques. MEDS acquires a digital image of the skin lesion and extracts a set of geometric and colorimetric features. It then yields a diagnosis based on a voting schema integrating the outputs of three different classifiers: discriminant analysis, k-nearest neighbor and decision tree. The system is trained and validated on a set of 152 skin images acquired via D-ELM. The diagnostic results of MEDS are then compared with the diagnostic decision of a group of expert dermatologists.