Melanoma Detection using Deep Learning
Jovel Jose · International Journal for Research in Applied Science and Engineering Technology · 2020
There is a lot of scope for automation in health care and health management. Let us consider the dermatology sector, which deals with different types of skin diseases .In which cancer is most difficult for diagnosis different types of cancer like melanoma can be cured if found in the early stages. In this paper we introduce a method to digitize and automate the process of diagnosis of melanoma using deep learning techniques. Deep learning techniques have achieved high accuracy rates in classifying images in various fields. Deep learning is a technique that attempt to teach a computer to gain knowledge through example. Use of deep learning to automatically detect melanomas in dermoscopy images. The system first preprocesses the images by removing unwanted artifacts and it then classifies the images using Convolution Neural Network (CNN). Then the classifier has been tested on preprocessed and unprocessed dermoscopy images to evaluate its effectiveness.