Related Experiment Video
Updated: Sep 15, 2025
Real-time Video Projection in an MRI for Characterization of Neural Correlates Associated with Mirror Therapy for Phantom Limb Pain
Published on: April 20, 2019
Motion artifacts and image quality in stroke MRI: associated factors and impact on AI and human diagnostic accuracy
Christian Hedeager Krag1,2,3, Felix Christoph Müller4,5, Karen Lind Gandrup4
1Department of Radiology, University Hospital Copenhagen-Herlev and Gentofte, Copenhagen, Denmark. christian.hedeager.krag.01@regionh.dk.
Objectives:
To assess the prevalence of motion artifacts and the factors associated with them in a cohort of suspected stroke patients, and to determine their impact on diagnostic accuracy for both AI and radiologists.
Materials And Methods:
This retrospective cross-sectional study included brain MRI scans of consecutive adult suspected stroke patients from a non-comprehensive Danish stroke center between January and April 2020. An expert neuroradiologist identified acute ischemic, hemorrhagic, and space-occupying lesions as references. Two blinded radiology residents rated MRI image quality and motion artifacts. The diagnostic accuracy of a CE-marked deep learning tool was compared to that of radiology reports. Multivariate analysis examined associations between patient characteristics and motion artifacts.
Results:
775 patients (68 years ± 16, 420 female) were included. Acute ischemic, hemorrhagic, and space-occupying lesions were found in 216 (27.9%), 12 (1.5%), and 20 (2.6%). Motion artifacts were present in 57 (7.4%). Increasing age (OR per decade, 1.60; 95% CI: 1.26, 2.09; p < 0.001) and limb motor symptoms (OR, 2.36; 95% CI: 1.32, 4.20; p = 0.003) were independently associated with motion artifacts in multivariate analysis. Motion artifacts significantly reduced the accuracy of detecting hemorrhage. This reduction was greater for the AI tool (from 88 to 67%; p < 0.001) than for radiology reports (from 100 to 93%; p < 0.001). Ischemic and space-occupying lesion detection was not significantly affected.
Conclusion:
Motion artifacts are common in suspected stroke patients, particularly in the elderly and patients with motor symptoms, reducing accuracy for hemorrhage detection by both AI and radiologists.
Key Points:
Question Motion artifacts reduce the quality of MRI scans, but it is unclear which factors are associated with them and how they impact diagnostic accuracy. Findings Motion artifacts occurred in 7% of suspected stroke MRI scans, associated with higher patient age and motor symptoms, lowering hemorrhage detection by AI and radiologists. Clinical relevance Motion artifacts in stroke brain MRIs significantly reduce the diagnostic accuracy of human and AI detection of intracranial hemorrhages. Elderly patients and those with motor symptoms may benefit from a greater focus on motion artifact prevention and reduction.
Insights
Motion artifacts are common in brain MRI scans for suspected stroke patients, particularly in older adults and those with motor symptoms. These artifacts significantly reduce the accuracy of detecting intracranial hemorrhages for both artificial intelligence (AI) and radiologists.
Area of Science:
- Radiology
- Medical Imaging
- Artificial Intelligence in Medicine
Background:
- Motion artifacts are a known issue in Magnetic Resonance Imaging (MRI), potentially degrading image quality and impacting diagnostic accuracy.
- The prevalence of motion artifacts and their specific associations with patient characteristics in suspected stroke cohorts remain incompletely understood.
- Understanding these factors is crucial for optimizing diagnostic workflows and improving patient outcomes.
Purpose of the Study:
- To determine the prevalence of motion artifacts in brain MRI scans of suspected stroke patients.
- To identify patient-specific factors associated with the presence of motion artifacts.
- To evaluate the impact of motion artifacts on the diagnostic accuracy of both artificial intelligence (AI) tools and human radiologists.
Main Methods:
- Retrospective analysis of brain MRI scans from adult suspected stroke patients.
- Expert neuroradiologist identification of reference lesions (ischemic, hemorrhagic, space-occupying).
- Blinded assessment of image quality and motion artifacts by radiology residents.
- Comparison of diagnostic accuracy between a CE-marked AI tool and radiology reports.
- Multivariate analysis to identify factors associated with motion artifacts.
Main Results:
- Motion artifacts were present in 7.4% of the 775 included MRI scans.
- Increasing patient age and the presence of limb motor symptoms were independently associated with a higher likelihood of motion artifacts.
- Motion artifacts significantly decreased the accuracy of hemorrhage detection, with a more pronounced effect on the AI tool (88% to 67%) compared to radiology reports (100% to 93%).
- Detection of ischemic and space-occupying lesions was not significantly affected.
Conclusions:
- Motion artifacts are a significant concern in brain MRI for suspected stroke, affecting approximately 7% of scans.
- Elderly patients and those experiencing motor symptoms are more prone to motion artifacts.
- These artifacts critically impair the accurate detection of intracranial hemorrhages, impacting both AI and human interpretation, highlighting the need for artifact mitigation strategies.
