Skin Cancer Prediction using Convolutional Neural Network

Abstract

Skin cancer is a highly death-dealing and life-threatening disease. It mostly appears in the form of melanoma (malignant) and benign tumours; diagnosing these in the early stages necessitates the use of an efficient algorithm that can be predicted employing an enormous data set that has been trained. The goal of this study is to predict skin cancer using Keras classification model and CNN which uses machine learning algorithms to accurately diagnose and predict the type of skin cancer. We are utilising an optimizer defined for expressing the loss and hyper parameters that have a substantial impact on the model's performance. Our Results show that the suggested approach performs better than the other options, with an accuracy of around 92%.Therefore as an outcome, the goal of this paper is to develop an accurate Keras classification model and CNN model with Optimizers to detect skin cancer with greater than 80% accuracy and a false predictively rate of less than 10%, as well as to visualize skin lesion images from the ISIC dataset.