Developing and deploying deep learning models in brain MRI: a review

TL;DR

This review discusses the development, deployment, and challenges of deep learning models in brain MRI, emphasizing good practices, explainability, and clinical integration.

Contribution

It provides a comprehensive overview of the entire pipeline from data collection to clinical deployment, including guidelines and a checklist based on FDA principles.

Findings

Deep learning models improve MRI analysis but face deployment barriers.

Guidelines and best practices are essential for clinical integration.

Challenges include data quality, explainability, and regulatory approval.

Abstract

Magnetic Resonance Imaging (MRI) of the brain has benefited from deep learning (DL) to alleviate the burden on radiologists and MR technologists, and improve throughput. The easy accessibility of DL tools have resulted in the rapid increase of DL models and subsequent peer-reviewed publications. However, the rate of deployment in clinical settings is low. Therefore, this review attempts to bring together the ideas from data collection to deployment into the clinic building on the guidelines and principles that accreditation agencies have espoused. We introduce the need for and the role of DL to deliver accessible MRI. This is followed by a brief review of DL examples in the context of neuropathologies. Based on these studies and others, we collate the prerequisites to develop and deploy DL models for brain MRI. We then delve into the guiding principles to practice good machine learning practices in the context of neuroimaging with a focus on explainability. A checklist based on the FDA's good machine learning practices is provided as a summary of these guidelines. Finally, we review the current challenges and future opportunities in DL for brain MRI.