Enhancing Radiologist Productivity with Artificial Intelligence in Magnetic Resonance Imaging (MRI): A Narrative Review

Abstract

Artificial intelligence (AI) shows promise in streamlining MRI workflows by reducing radiologists' workload and improving diagnostic accuracy. Despite MRI's extensive clinical use, systematic evaluation of AI-driven productivity gains in MRI remains limited. This review addresses that gap by synthesizing evidence on how AI can shorten scanning and reading times, optimize worklist triage, and automate segmentation. On 15 November 2024, we searched PubMed, EMBASE, MEDLINE, Web of Science, Google Scholar, and Cochrane Library for English-language studies published between 2000 and 15 November 2024, focusing on AI applications in MRI. Additional searches of grey literature were conducted. After screening for relevance and full-text review, 67 studies met inclusion criteria. Extracted data included study design, AI techniques, and productivity-related outcomes such as time savings and diagnostic accuracy. The included studies were categorized into five themes: reducing scan times, automating segmentation, optimizing workflow, decreasing reading times, and general time-saving or workload reduction. Convolutional neural networks (CNNs), especially architectures like ResNet and U-Net, were commonly used for tasks ranging from segmentation to automated reporting. A few studies also explored machine learning-based automation software and, more recently, large language models. Although most demonstrated gains in efficiency and accuracy, limited external validation and dataset heterogeneity could reduce broader adoption. AI applications in MRI offer potential to enhance radiologist productivity, mainly through accelerated scans, automated segmentation, and streamlined workflows. Further research, including prospective validation and standardized metrics, is needed to enable safe, efficient, and equitable deployment of AI tools in clinical MRI practice.

Keywords: MRI; artificial intelligence; automated segmentation; deep learning; machine learning; productivity; radiologist efficiency; radiology workflow; worklist triage.

Figure 1

PRISMA flowchart showing the two-step study screening process. Adapted from PRISMA Group, 2020 [26].

Figure 2

The relationship between AI, ML, DL, and CNN. ML lies within the field of AI and allows computer systems to learn without explicit programming or knowledge. As a subsection of machine learning, deep learning uses computational models similar to the neuronal architecture within the brain, simulating multilayer neural networks in order to resolve complex tasks. A CNN automatically learns and adapts to spatial hierarchies of features through backpropagation using multiple building blocks, allowing analysis of 2D and 3D medical images.

Figure 3

Outline of AI application in radiology workflow in typical clinical setting. AI has potential in reducing scan times during image acquisition and processing, support specific image-based task processes such as segmentation/diagnosis/staging, reduce reading time during reporting, and improve integrated diagnostic processes beyond the reporting phase, including deciding appropriate treatment plans and evaluating prognosis in patients.