NEURAL-NETWORK DIAGNOSIS OF MALIGNANT-MELANOMA FROM COLOR IMAGES

Malignant melanoma is the deadliest form of all skin cancers. Approxim ately 32,000 new cases of malignant melanoma were diagnosed in 1991 in the United States, with approximately 80% of patients expected to sur vive five years [1]. Fortunately, if detected early, even malignant me lanoma may be treated successfully. Thus, in recent years, there has b een rising interest in the automated detection and diagnosis of skin c ancer, particularly malignant melanoma [2]. In this paper, we present a novel neural network approach for the automated separation of melano ma from three benign categories of tumors which exhibit melanoma-like characteristics. Our approach uses discriminant features, based on tum or shape and relative tumor color, that are supplied to an artificial neural network for classification of tumor images as malignant or beni gn. With this approach, for reasonably balanced training/testing sets, we are able to obtain above 80% correct classification of the maligna nt and benign tumors on real skin tumor images.