Related Experiment Video
Updated: Aug 6, 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
Comparison of deep learning-based reconstruction of PROPELLER Shoulder MRI with conventional reconstruction
Seok Hahn1, Jisook Yi2, Ho-Joon Lee1
1Department of Radiology, Haeundae Paik Hospital, Inje University College of Medicine, Busan, South Korea, Republic of Korea.
Objective:
To compare the image quality and agreement among conventional and accelerated periodically rotated overlapping parallel lines with enhanced reconstruction (PROPELLER) MRI with both conventional reconstruction (CR) and deep learning-based reconstruction (DLR) methods for evaluation of shoulder.
Materials And Methods:
We included patients who underwent conventional (acquisition time, 8 min) and accelerated (acquisition time, 4 min and 24 s; 45% reduction) PROPELLER shoulder MRI using both CR and DLR methods between February 2021 and February 2022 on a 3 T MRI system. Quantitative evaluation was performed by calculating the signal-to-noise ratio (SNR). Two musculoskeletal radiologists compared the image quality using conventional sequence with CR as the reference standard. Interobserver agreement between image sets for evaluating shoulder was analyzed using weighted/unweighted kappa statistics.
Results:
Ninety-two patients with 100 shoulder MRI scans were included. Conventional sequence with DLR had the highest SNR (P < .001), followed by accelerated sequence with DLR, conventional sequence with CR, and accelerated sequence with CR. Comparison of image quality by both readers revealed that conventional sequence with DLR (P = .003 and P < .001) and accelerated sequence with DLR (P = .016 and P < .001) had better image quality than the conventional sequence with CR. Interobserver agreement was substantial to almost perfect for detecting shoulder abnormalities (κ = 0.600-0.884). Agreement between the image sets was substantial to almost perfect (κ = 0.691-1).
Conclusion:
Accelerated PROPELLER with DLR showed even better image quality than conventional PROPELLER with CR and interobserver agreement for shoulder pathologies comparable to that of conventional PROPELLER with CR, despite the shorter scan time.
Insights
Accelerated PROPELLER MRI with deep learning reconstruction offers superior shoulder image quality and comparable agreement to conventional methods, despite a 45% shorter scan time.
Area of Science:
- Radiology
- Medical Imaging
- Artificial Intelligence in Medicine
Background:
- Shoulder MRI evaluation is crucial for diagnosing pathologies.
- Conventional PROPELLER MRI provides detailed images but has a long acquisition time.
- Deep learning-based reconstruction (DLR) offers potential for accelerated MRI acquisition without compromising quality.
Purpose of the Study:
- To compare image quality and inter-observer agreement of conventional and accelerated PROPELLER MRI for shoulder evaluation.
- To assess the impact of conventional reconstruction (CR) versus DLR on image quality and agreement.
Main Methods:
- A comparative study included 92 patients undergoing shoulder MRI using conventional and accelerated PROPELLER sequences.
- Acquisition times were 8 minutes for conventional and 4 minutes 24 seconds for accelerated scans (45% reduction).
- Image quality was assessed quantitatively (SNR) and qualitatively by musculoskeletal radiologists, with agreement analyzed using kappa statistics.
Main Results:
- Accelerated PROPELLER with DLR demonstrated the highest signal-to-noise ratio (SNR).
- Both conventional and accelerated PROPELLER with DLR showed significantly better image quality compared to conventional reconstruction.
- Inter-observer agreement for detecting shoulder abnormalities was substantial to almost perfect (κ = 0.600–0.884).
Conclusions:
- Accelerated PROPELLER MRI with DLR achieves superior image quality compared to conventional PROPELLER with CR.
- The accelerated DLR method provides image quality and diagnostic agreement comparable to conventional methods, with a significant reduction in scan time.
- This advancement holds promise for more efficient and effective shoulder MRI evaluations.
More Related Videos
07:46Author Spotlight: Revolutionizing Remote Surgery with Augmented Reality and Robotics for Enhanced Precision and Accessibility
Published on: August 9, 2024
07:34Functional MRI in Conjunction with a Novel MRI-compatible Hand-induced Robotic Device to Evaluate Rehabilitation of Individuals Recovering from Hand Grip Deficits
Published on: November 23, 2019
