Melanoma Recognition Using Negative Selection

Melanoma is the deadliest form of skin cancer and the most dangerous type. It is curable if detected earlier. The problem occurred when the current diagnosis biopsy method consumed much time and pain. Based on the proposed technique, the image of melanoma will be used. Corresponding features will be extracted based on the asymmetry, border, colour, and diameter (ABCD) rule of dermoscopy with Negative Selection Algorithm to classify melanoma skin cancer and benign mole. The accuracy of the proposed technique is 60%, specificity gained 75%, and sensitivity of 50% was recorded for the algorithm evaluation.