The architectural development of the convolution neural network and its uses in the medical field

Abstract

The emergence of neural networking designs with great performance in computer tasks which are vision-related has sparked interest in radiology artificial intelligence (AI). Radiologists could get advantage from a greater understanding the principles of AI as AI-based software systems become more incorporated into the clinical workflow. Machine learning (ML) is becoming increasingly popular in the domains of medical imaging, radiomics, and medical image analysis. Deep learning is a sort of machine learning that originated in the field of computer vision and has since expanded in popularity across a wide-aspect range of sectors. Deep learning has demonstrated outstanding performance in a variety of fields, including picture classification, object detection, and segmentation. This work gives an overall overview of recent achievements in this area by surveying deep learning architectures and DL approaches used to diagnose disease based on medical images.