Lesion Boundary Segmentation With Artifacts Removal and Melanoma Detection in Skin Lesion Images

Abstract

Melanoma is a severe form of skin cancer characterized by the rapid multiplication of pigment-producing cells. A problem on analysis of these images is interesting because of the existence of artifacts that produces noise such as hair, veins, water residue, illuminations, and light reflections. An important step in the diagnosis of melanoma is the removal and reduction of these artifacts that can inhibit the examination to accurately segment the skin lesion from the surrounding skin area. A simple method for artifacts removal for extracting skin lesion is implemented based on image enhancement and morphological operators. This is used for training together with some augmentation techniques on images for melanoma detection. The experimental results show that artifact removal and lesion segmentation in skin lesion images performed a true detection rate of 95.37% for melanoma skin lesion segmentation, and as high as 92.5% accuracy for melanoma detection using both GoogLeNet and Resnet50.