Related Experiment Video
Updated: Sep 12, 2025
12:36
Genomic MRI - a Public Resource for Studying Sequence Patterns within Genomic DNA
Published on: May 9, 2011
10.3K
GPT-4 for automated sequence-level determination of MRI protocols based on radiology request forms from clinical
Robert Terzis1, Kenan Kaya2, Thomas Schömig2
1Institute for Diagnostic and Interventional Radiology, Faculty of Medicine and University Hospital Cologne, University of Cologne, Cologne, Germany. robert.terzis@uk-koeln.de.
European Radiology
|August 8, 2025
Summary
GPT-4 demonstrated comparable accuracy to less experienced residents in selecting MRI sequences, showing high clinical applicability. However, its performance varied across subspecialties, excelling in cardiac and neuroradiology but lagging in musculoskeletal imaging.
Area of Science:
- Artificial Intelligence in Medical Imaging
- Radiology Workflow Optimization
- Machine Learning for Diagnostic Imaging
Background:
- Accurate Magnetic Resonance Imaging (MRI) protocol selection is critical for efficient diagnostics, yet it is time-consuming and prone to errors, particularly for less experienced radiologists.
- Long MRI acquisition times can limit patient access, highlighting the need for optimized protocol selection processes.
Purpose of the Study:
- To evaluate the accuracy of GPT-4 in selecting MRI sequences based on radiology request forms (RRFs).
- To compare GPT-4's performance in MRI protocol selection against radiology residents with varying experience levels.
- To assess the clinical applicability and quality of GPT-4 generated MRI protocols.
Main Methods:
- A retrospective study involving 100 RRFs across cardiac imaging, neuroradiology, musculoskeletal, and oncology subspecialties.
- GPT-4 and two radiology residents (R1: 2 years, R2: 5 years MRI experience) independently selected MRI sequences.
- Protocols were assessed by five specialized radiologists for completeness, quality, and utility using Likert scales, and by a lead radiographer for clinical applicability.
Main Results:
- GPT-4 achieved comparable scores to R1 residents but was inferior to R2 residents in overall protocol quality and utility.
- Protocol quality varied by subspecialty: GPT-4 performed comparably in cardiac and oncology, showed no difference in neuroradiology, but scored lower in musculoskeletal imaging.
- GPT-4-based protocols demonstrated high clinical applicability (95%), similar to residents (95-96%).
Conclusions:
- GPT-4 can generate MRI protocols with notable completeness, quality, utility, and clinical applicability.
- The large language model shows potential as a tool to assist radiologists, especially less experienced ones, in optimizing MRI protocol selection and improving diagnostic efficiency.
- While effective in standardized subspecialties, GPT-4's accuracy in musculoskeletal imaging requires further improvement.
Related Concept Videos
01:24Magnetic Resonance Imaging
6.9K
Magnetic resonance imaging (MRI) is a noninvasive medical imaging technique based on a phenomenon of nuclear physics discovered in the 1930s, in which matter exposed to magnetic fields and radio waves was found to emit radio signals. In 1970, a physician and researcher named Raymond Damadian noticed that malignant (cancerous) tissue gave off different signals than normal body tissue. He applied for a patent for the first MRI scanning device in clinical use by the early 1980s. The early MRI...
6.9K
01:14Imaging Studies I: CT and MRI
443
Introduction: MRI and CT scans are crucial advancements in medical imaging techniques, playing a vital role in diagnosing conditions related to the gastrointestinal (GI) system. Each scan serves distinct purposes, targets specific areas, and requires unique nursing duties.
Description of the Procedures
Computed Tomography (CT) scan:
Computed Tomography (CT) scans use X-ray technology to generate detailed images of bones, organs, and tissues. During the scan, the patient lies on a moving table...
Description of the Procedures
Computed Tomography (CT) scan:
Computed Tomography (CT) scans use X-ray technology to generate detailed images of bones, organs, and tissues. During the scan, the patient lies on a moving table...
443
01:27Imaging Studies IV: Magnetic Resonance Imaging
52
Introduction:Magnetic Resonance Imaging, or MRI, can include a specialized imaging technique of the urinary system known as Magnetic Resonance Urography (MRU). This radiation-free technique uses strong magnetic fields and radio waves to produce detailed images with the help of a computer. MRU is particularly effective for visualizing fluid-filled structures like the kidneys, ureters, and bladder.Applications of MRI in the Genitourinary SystemKidneys and Ureters: MRI detects tumors, cysts,...
52