A Comparative Study on Melanoma Detection Using Machine Learning Paradigm

Skin is the primary protection for the muscles, bones, and the complete body of a human. Many people today are afflicted with skin cancer. Skin cancer that is malignant melanoma is the deadliest type. Melanoma, a highly dangerous type of cancer compare to other, and the severity of these skin cancers is increasing on a daily basis. Melanoma is easily treatable if detected early. Melanoma is diagnosed manually as well as automatically. Using image-based computer assisted diagnosis methods, there is a lot of potential for early detection of malignant melanoma. Automatically identifying the type of skin cancer from photos can aid in faster diagnosis and increased accuracy while saving valuable time. This essay offers a survey of the field of skin cancer diagnosis through the use of machine learning and image analysis tools. This survey concentrates on the algorithms for automated melanoma detection in dermoscopic images through a full assessment of the methodologies presented in the literature, as well as by looking at related concepts and describing potential future directions through open problems in this field of study. The goal of this bibliographic review is to give researchers who choose to engage with machine learning for cancer diagnosis a thorough understanding of the most recent successes.