Detection and Diagnosing of Skin Cancer Using Machine Learning and Deep Learning Techniques: A Comprehensive Review

Abstract

The most fatal condition affecting people nowadays is skin disease. According to the WHO, there are approximately 2 to 3 million skin cancer patients each year. Hence, research in this field is emerging in the present era. The exceedingly difficult challenge for experts in this area is to distinguish between the many forms of skin lesions because they are so similar to one another. Deep learning and machine learning techniques have evolved into powerful tools for dealing with such issues. Deep learning is a multiple-layer architecture model in which the layers learn to represent data at different amorphous levels and can be trained on large databases semantically at a high level, hence why it has been previously proposed in various medical applications. Motivated by this, the present work is a review of previously reported work on using machine learning and deep learning in the detection of skin cancer. The proposed review will be of great interest to the scientific groups working in this area to understand where to use which technique for better results.