Convolution Neural Networks for Disease Prediction: Applications and Challenges

Abstract

More people are using Deep Learning techniques in the healthcare field as a result of the quick development in domains like Computer Vision, Graphics Processing Technology, and the accessibility of medical imaging datasets. Convolutional Neural Networks (CNNs), in particular, have quickly emerged as the preferred technique for processing clinical data. CNN-based designs have been embraced by the diagnostic imaging group to assist physicians with disease identification. Since AlexNet's enormous success in 2012, CNNs have indeed been employed more and more in the analysis of medical images to boost the effectiveness of physicians. This article summarises various CNN architectures for predicting medical diseases and their challenges. We examine the utilization of Deep Learning for the prediction of various diseases, including Brain diseases, Diabetic Retinopathy, and Lung cancer. This research also provides a survey of datasets available for analysis.