Detection and Classification of Skin Cancer Using Binary Classifier, Residual Network, and Convolutional Neural Network

Skin cancer is a very dangerous form of cancer as it transfers from one part of the body to the other part. It can occur in any age group but is very common in old people. For effective treatment and the best possible outcome, early detection of skin cancer is necessary. Traditional techniques are sometimes not able to detect properly due to the lack of expertise. These methods also cause discomfort, and risk of compilation, and require more recovery time compared to the traditional methods. In the work, the authors proposed a hybrid model for skin cancer detection and classification using a Binary Classifier, Residual Network, and Convolutional Network. The research work first uses a binary classifier to distinguish between malignant and benign cancer. Then, Residual Network is used to understand its deep architecture and skip connections, for retrieving features from input images. Finally, the Convolution Neural Network (CNN) is used specifically to detect skin cancer, leveraging its architectural design and training strategies. The publicly available Kaggle dataset is utilized for the research work. For assessment of the work accuracy and time have been calculated. The experimental results authenticate the effectiveness of the model in precisely detecting and classifying skin cancer.