SKIN CANCER DETECTION USING CONVOLUTIONAL NEURAL NETWORK

Skin Cancer Detection Using Convolutional Neural Network

Dharaneesh S, Gowtham R, Sridhar S, Vindhiya R

Bachelor Of Technology

Department Of Information Technology
SNS College Of Technology,Coimbatore-35

ABSTRACT

The project is entitled “Skin Cancer Detection using CNN”. The main objective of this project is to detect the cancer cells at an early stage to prevent the cancer deaths.Skin cancer is a type of cancer that grows in the skin tissue, which can cause damage to the surrounding tissue, disability, and even death.The accuracy of diagnosis and the early proper treatment can minimize and control the harmful effects of skin cancer. In the proposed system the cancer cells are identified and classified using Convolutional Neural Network(CNN). In this method Adam optimizer is used with a learning rate of 0.01. Adam optimizer provides the best performance with an accuracy value of 89%. Three different types of skin cancers are classified in this system namely, Melanoma, Squamous Cell Carcinoma(SCC) and Basal Cell Carcinoma(BCC). Finally it is converted into a website for easy access to the user. The proposed approach not only learns a global map for skin lesions, but also acquires the local contextual information, such as lesion boundary. It can, therefore, accurately segment lesions within a given skin image, even in the presence of fuzzy boundaries and complex textures.