Diagnosis of Melanocytic Lesions Using The K-Nearest Neighbors Classification Technique

Melanoma is a type of skin cancer that originates whenmelanocytes (the cells that give skin its tan or brown color) begin to grow out of control. Cells from almost any part of the body can develop into cancer and can then spread to other areas of the body. Currently there is no tool to assist the medical professional in the rapid diagnosis of melanoma. In this work we propose a methodology that provides support to the dermatologist in the diagnosis of melanoma. This methodology is composed of 4 modules: Preprocessing, Segmentation, Feature Extraction and Classification. Image preprocessing consists of hair removal. Segmentation consists of isolating the object of interest (the lesion). The features extracted for classification are: asymmetry, border, color and dermoscopic structures. Finally, the K-nearest neighbor (K-NN) classification method is used to classify benign and malignant moles.\newline The final results of the methodology show 91.67\% accuracy, 92.50% sensitivity and 100% specificity. Since the results look promising, this technique could be the basis for more sophisticated tools useful to clinicians in the diagnosis of melanoma.