We are currently experiencing an unprecedented explosion of artificial intelligence (AI) applications in our everyday lives, which are also becoming increasingly prevalent in medical imaging. In particular, AI is intensively employed in Magnetic Resonance Imaging (MRI) due to MRI intrinsic soft-tissue contrast, a broad spectrum of structural and physiological acquisition protocols, and its diagnostic potential. In the upcoming years, AI will revolutionize MRI, transforming its largely qualitative clinical applications into a new era of quantitative imaging that fully utilizes these large structures of data. MR images, more than any other methodologies, contain a large amount of information and AI has all prerequisites to be the tool that might be able to push boundaries of conventional MRI reads to the next level.

Whilst promising new methodological research is constantly being published, there is currently a lack of standardization and reproducibility testing of these approaches on larger multivendor/multicentre datasets that decelerate clinical AI applications. The ever-increasing large numbers of publications ensure that reviews become quickly out-of-date, therefore, it is important to regularly update the cutting edge AI reports in translational medicine.

This Special Issue aims to present an overview of the latest AI applications in MRI and collate research with the most recent methodological advances in machine and deep learning for improving MR image acquisition, processing, and its clinical applications.

This Special Issue aims to provide the reader with a general comprehension of these techniques and an understanding of the challenges behind them through papers that analyze state-of-the-art techniques. Papers on the topics below will challenge the most onerous boundaries in diagnostic MRI that AI might be able to address. We welcome original research and review articles.

Potential topics include but are not limited to the following:

• Clinical applications of AI using MR images
• Machine learning applications for prediction, detection, classification, registration, and segmentation
• Radiomics and radiogenomics
• Use of multiparametric and non-conventional advanced MR protocols
• Applications in neuroscience, oncology, cardiovascular, MSK, and body imaging
• Big data: data augmentation strategies, synthetic MR images, multicentre studies
• Reliability, reproducibility, challenges, and weaknesses of AI
• Reviews on the history and latest methods