Skin melanoma detection and classification with deep learning

Abstract

Because of its rapid growth and high mortality rate, melanoma skin cancer is among the most dangerous types of skin cancer. Consequently, melanoma treatment relies heavily on early detection. Based on the U-Net architecture with VGG-16 encoder and semantic segmentation, we present a skin lesion segmentation approach for dermoscopic pictures in this study. Diagnostic imaging systems can assess the characteristics of the segmented skin lesion and assign them a classification based on those aspects. Even on computers without powerful GPUs, the training accuracy is still high enough (over 95%) using the suggested strategy, which uses fewer resources. We use the ISIC dataset, which contains dermoscopy images, to train the model in our trials. We compare the suggested skin lesion segmentation method to others that use deep learning and analyze the Sorensen-Dice and Jaccard scores to determine how well it performs. In terms of skin lesion segmentation, the experimental findings demonstrated that the proposed method outperformed the alternatives.