Prospects of deep learning for medical imaging

Abstract

Machine learning techniques are essential components of medical imaging research. Recently, a highly flexible machine learning approach known as deep learning has emerged as a disruptive technology to enhance the performance of existing machine learning techniques and to solve previously intractable problems. Medical imaging has been identified as one of the key research fields where deep learning can contribute significantly. This review article aims to survey deep learning literature in medical imaging and describe its potential for future medical imaging research. First, an overview of how traditional machine learning evolved to deep learning is provided. Second, a survey of the application of deep learning in medical imaging research is given. Third, wellknown software tools for deep learning are reviewed. Finally, conclusions with limitations and future directions of deep learning in medical imaging are provided.

Image registration in dynamic renal MRI—current status and prospects

“…In recent years, plenty of papers reporting a use of Deep Learning (DL) for medical image analysis have been published. These approaches have already demonstrated very high potential for efficient medical image processing and analysis [47][48][49][50] and are believed to play a significant role in medical registration [6]. Viergever et al refer to an earlier review on the same topic and show a confrontation between trends noticed 20 years ago and recent developments.…”

“…The advantages of using DL instead of standard deformable registration algorithms are in accuracy [51] and speed improvements [47]. Application of DL in medical image analysis and image registration is reported in various reviews [47,49,50,52] but little in renal image registration. However, many papers cited contain essential contributions that can be transferred to the kidney image registration task.…”

P5 eHealth: An Agenda for the Health Technologies of the Future

“…ML and AI find in medical imaging field a concrete application in order to analyse images and help physician with particular regard in the field of radiology in decisionmaking processes improving patient's management (Jiang et al 2017;Ker et al 2018;Kim et al 2018). Indeed, the P5 approach underlines the importance of decision-making process and the usage of eHealth in order to improve it.…”

Predictive Precision Medicine: Towards the Computational Challenge

“…In particular, CNN, autoencoders and RNN are excellent algorithms for medical imaging analysis (Kim et al 2018). Convolution that is based on addition and multiplication is suitable for image recognition; the procedure takes into account connected information (i.e.…”