Classification of skin lesions using ANN

Abstract

Melanoma arises from cancerous growth in pigmented skin lesion and t is the most deadliest form of skin cancer. Melanoma forms 4% from all skin cancer cases and it accounts for 75% of all skin cancer deaths. Even when the expert dermatologists uses the dermoscopy for diagnosis, the accuracy of melanoma diagnosis is estimated to be about 75–84%. The aim of this work classify skin lesions like normally, atypical and melanoma using artificial intelligence techniques and help to decide of the expert dermatologists in diagnosis for melanoma. Decision support system, which will be held improve both the speed and the accuracy of diagnosis. In this study that done for the classification of skin lesions with ANN, were correctly classified 100% normal skin lesions according to data from the data set PH2. Abnormal and melanoma skin cancers are correctly classified %93.3 with neural network that performed. As a result, the findings that were obtained have indicated the decision support system will be help to the dermatologists in the diagnosis of skin lesions.