Deep Learning in Medical Image Analysis: A Survey
D A Agneya, Mogaveera Sahil Shekar, Ajay Bharadwaj, Nandhini Vineeth, Medikonda Neelima
Abstract
Deep learning has emerged as one of the main study areas in recent years because of its wide range of applications. One of the major applications of deep learning is image processing, which, when integrated with the data received from medical imaging, has the ability to improve the diagnostic process by reducing analysis time and providing accurate results. The field of deep learning can provide scope for affordable diagnosis, proper medication assistance, and the tracking of disease progression. This survey article presents an overview of the numerous deep learning models that have been suggested for medical image analysis, highlighting the various designs of convolutional neural networks, datasets, and a brief description of the neural network layers that are utilized to produce extremely accurate findings. Since image processing is classified as supervised learning because of domain specificity, the application of a model proposed for the diagnosis of one disorder may not be applicable for the diagnosis of another. The high progress of research in this field can lead to an accurate, unsupervised image processing technology soon. This paper contrasts the accuracies of multiple algorithms and provides a brief overview of current research and development on this topic, including data pertaining to various CNN designs and layers.