Prospective Deployment of Deep Learning inMRI: A Framework for Important Considerations, Challenges, and Recommendations for Best Practices

Artificial intelligence algorithms based on principles of deep learning (DL) have made a large impact on the acquisition, reconstruction, and interpretation of MRI data. Despite the large number of retrospective studies using DL, there are fewer applications of DL in the clinic on a routine basis. To address this large translational gap, we review the recent publications to determine three major use cases that DL can have in MRI, namely, that of model-free image synthesis, model-based image reconstruction, and image or pixel-level classification. For each of these three areas, we provide a framework for important considerations that consist of appropriate model training paradigms, evaluation of model robustness, downstream clinical utility, opportunities for future advances, as well recommendations for best current practices. We draw inspiration for this framework from advances in computer vision in natural imaging as well as additional healthcare fields. We further emphasize the need for reproducibility of research studies through the sharing of datasets and software. Level of Evidence 5 Technical Efficacy Stage 2

Automated summary

Deep learning algorithms have had a significant impact on MRI data acquisition, reconstruction, and interpretation. Three major use cases of deep learning in MRI are model-free image synthesis, model-based image reconstruction, and image or pixel-level classification. Important considerations include model training, evaluation of model robustness, clinical utility, future opportunities, and reproducibility of research.