Enhancing resolution and image quality in musculoskeletal MRI using deep learning reconstruction

Clinical Snapshot

Key Findings

• P Value: p < 0.001 for image quality improvement

• Effect Size: All structures showed higher or similar Likert scores in HR-DLR sequences

• Primary Outcome: Image quality scores significantly higher for HR-DLR across all structures and sequences

• Nnt Or Sensitivity: Inter-reader agreement: τ = 0.613-0.788 (SR) vs τ = 0.682-0.961 (HR-DLR)

• Confidence Interval: Not reported

Clinical Application

Requires DLR-capable MRI systems and software, shorter acquisition times may improve patient throughput Relevant to Australian radiology practices using 1.5-T MRI systems. May improve efficiency in public hospital settings with high MSK imaging demand. Technology adoption would need TGA approval and cost-effectiveness evaluation for PBS consideration Patients requiring MSK MRI at 1.5-T field strength across multiple joint sites

Abstract

OBJECTIVE: Deep learning-based noise reduction enhances image quality, overcoming the tradeoff among acquisition time, spatial resolution, and signal-to-noise ratio (SNR). We implemented deep learning reconstruction (DLR) into a 1.5-T musculoskeletal (MSK) magnetic resonance imaging (MRI) protocol to improve image quality without compromising SNR. MATERIALS AND METHODS: We retrospectively analyzed 39 MRI examinations performed on a 1.5-T scanner using standard-resolution (SR) sequences and sequences with higher resolution reconstructed with DLR (HR-DLR). Exams of the knees, shoulders, ankles, and hips were evaluated. The included sequences were: three-dimensional T2-weighted fast advanced spin-echo; T1-weighted and proton density-weighted fast spin-echo. One expert reader and two junior readers in agreement evaluated the visibility of various structures using a 5-point Likert scale in a blind manner. A fourth reader estimated the SNR and contrast-to-noise ratio (CNR) in bone and muscle. A mixed model was used to compare HR-DLR versus SR measures. The agreement between radiologists was assessed with the Kendall τ coefficient. RESULTS: The HR-DLR sequences globally had a smaller pixel size and shorter acquisition time. A good inter-reader agreement was obtained for SR sequences (0.613 ≤ τ ≤ 0.788) and even higher levels of agreement for HR-DLR sequences (0.682 ≤ τ ≤ 0.961). All the structures had higher or similar Likert scores in HR-DLR sequences (p < 0.001), regardless of joint and sequence contrast. Apparent SNR and CNR of HR-DLR and SR were similar. CONCLUSION: Incorporating DLR into 1.5-T MSK MRI protocols enhances resolution and maintains SNR and CNR, improving MSK structure visualization. RELEVANCE STATEMENT: This study demonstrated the effectiveness of deep learning reconstruction in improving the efficiency of 1.5-T musculoskeletal MRI exams. Despite shorter acquisition times, the visibility of key MSK structures was consistently rated as superior or similar in higher-resolution images with DLR. KEY POINTS: MRI is one of the primary diagnostic tools for evaluating MSK injuries and disorders. Deep learning reconstruction (DLR) implemented in a 1.5-T MSK protocol improved resolution, still preserving SNR and CNR. Higher scores were assigned by different raters to the DLR images, showing image quality improvement.

References

1. 1.Porta, M., Agresti, G., Laganà, M. M., Orofino, S., Pangaro, S., Carapella, N., Bonaffini, P. A., Bernasconi, P., Genovese, E. A., Sironi, S., & Aliprandi, A. (2026). Enhancing resolution and image quality in musculoskeletal MRI using deep learning reconstruction. European Radiology Experimental. https://doi.org/10.2214/AJR.16.17708