Improved Squirrel Optimization based Generative Adversarial Network for Skin Cancer Classification

Cancer is one of the most severe threats to global health in today's world and it cannot be fully cured. Thus, the early detection of the disease helps to reduce the risk and enhances the lifetime of the patient. There are several automatic methods for the detection of skin cancer, wherein accurate classification with minimal computation burden is more challenging task. Hence, this research introduces a novel optimized deep learning technique for the classification of skin cancer using Improved Squirrel based Generative Adversarial Network (ImSq-GAN). The performance of the proposed method is evaluated using Accuracy, F-Score, MSE, Precision, Recall, and Specificity and acquired the values of 0.96, 0.97, 0.04, 0.99, 0.97, and 0.99 respectively.