Recent developments in artificial intelligence (AI), particularly deep
learning (DL) algorithms have demonstrated remarkable progress in image recognition
and prediction tasks. These are now being applied in the field of radiology on medical
images to quantify, characterize, classify as well as monitor various pathologies. Such
DL based quantifications facilitate greater support to the visual assessment of image
characteristics that is performed by the physician. Furthermore it aids in reducing interreader
variability as well as assists in speeding up the radiology workflow. In this
chapter, we provide an insightful motivation for employing DL based framework
followed by an overview of recent applications of DL in radiology and present a
systematic summary of specific DL algorithms pertaining to image perception and
recognition tasks. Finally, we discuss the challenges in clinical implementation of these
algorithms and provide a perspective on how the domain could be advanced in the next
few years.
Keywords: Artificial intelligence, Convolutional neural nets, CT, Deep learning,
MRI, Radiology, X-rays.
