Related Experiment Video
Updated: Jun 28, 2025
Author Spotlight: Advancing Hepatic Fibrosis Diagnosis Using Magnetic Resonance Elastography and AI
Published on: July 21, 2023
Thin-slice elbow MRI with deep learning reconstruction: Superior diagnostic performance of elbow ligament pathologies
Jisook Yi1, Seok Hahn1, Ho-Joon Lee1
1Department of Radiology, Inje University College of Medicine, Haeundae Paik Hospital, 875 Haeundae-ro, Haeundae-gu, Busan 48108, Republic of Korea.
Purpose:
With the slice thickness routinely used in elbow MRI, small or subtle lesions may be overlooked or misinterpreted as insignificant. To compare 1 mm slice thickness MRI (1 mm MRI) with deep learning reconstruction (DLR) to 3 mm slice thickness MRI (3 mm MRI) without/with DLR, and 1 mm MRI without DLR regarding image quality and diagnostic performance for elbow tendons and ligaments.
Methods:
This retrospective study included 53 patients between February 2021 and January 2022, who underwent 3 T elbow MRI, including T2-weighted fat-saturated coronal 3 mm and 1 mm MRI without/with DLR. Two radiologists independently assessed four MRI scans for image quality and artefacts, and identified the pathologies of the five elbow tendons and ligaments. In 19 patients underwent elbow surgery after elbow MRI, diagnostic performance was evaluated using surgical records as a reference standard.
Results:
For both readers, 3 mm MRI with DLR had significant higher image quality scores than 3 mm MRI without DLR and 1 mm MRI with DLR (all P < 0.01). For common extensor tendon and elbow ligament pathologies, 1 mm MRI with DLR showed the highest number of pathologies for both readers. The 1 mm MRI with DLR had the highest kappa values for all tendons and ligaments. For reader 1, 1 mm MRI with DLR showed superior diagnostic performance than 3 mm MRI without/with DLR. For reader 2, 1 mm MRI with DLR showed the highest diagnostic performance; however, there was no significant difference.
Conclusions:
One mm MRI with DLR showed the highest diagnostic performance for evaluating elbow tendon and ligament pathologies, with similar subjective image qualities and artefacts.
Insights
One mm MRI with deep learning reconstruction (DLR) offers superior diagnostic performance for elbow tendons and ligaments. This technique enhances pathology detection compared to standard 3 mm MRI, improving diagnostic accuracy for elbow injuries.
Area of Science:
- Radiology
- Medical Imaging
- Orthopedics
Background:
- Standard elbow MRI slice thickness may miss subtle tendon and ligament lesions.
- Deep learning reconstruction (DLR) shows promise in enhancing MRI image quality.
Purpose of the Study:
- Compare 1 mm MRI with DLR to 3 mm MRI (with/without DLR) and 1 mm MRI without DLR.
- Evaluate image quality and diagnostic performance for elbow tendons and ligaments.
Main Methods:
- Retrospective study of 53 patients undergoing 3T elbow MRI.
- Inclusion of 1 mm and 3 mm slice thickness MRI, with and without DLR.
- Independent assessment by two radiologists for image quality, artifacts, and pathologies; surgical records used as reference in 19 patients.
Main Results:
- 3 mm MRI with DLR had significantly higher image quality scores than 3 mm MRI without DLR and 1 mm MRI with DLR.
- 1 mm MRI with DLR identified the most pathologies for both readers.
- 1 mm MRI with DLR demonstrated the highest diagnostic performance and kappa values for elbow tendons and ligaments.
Conclusions:
- 1 mm MRI with DLR offers the highest diagnostic performance for elbow tendon and ligament pathologies.
- Subjective image quality and artifact levels were similar across techniques.
- This advanced MRI technique improves the detection of subtle elbow injuries.
