Deep Learning Architiectures For Aided Melanoma Skin Disease Recognition: A Review

Melanoma, a sort of skin disease, in spite of the fact that it represents a little percentage of skin malignancies in the USA, it represents higher than seventy five percent of all skin diseases connected to all fatalities in the USA alone. This motivated researcher to seek automated techniques that facilitates early diagnosis of skin cancer. Skin lesion segmentation using machine learning became one of the best ways used for early detection and treatment of skin cancer. Recently, the researchers used a different deep network architectures, to segment and diagnose skin cancer. In this paper, we introduce a review of existing deep network architectures that have been suggested to segment skin lesions, pre-processing and post-processing methods with the available datasets that can be used for research in this area, also presented a comparison between the results of different methods used for skin lesion segmentation showing the strengths and weaknesses of each method.