Enhancing resolution and image quality in musculoskeletal MRI using deep learning reconstruction.
Authors
Affiliations (9)
Affiliations (9)
- Department of Radiology, Istituti Clinici Zucchi, Monza (MB), Italy.
- Canon Medical Systems, Rome, Italy. [email protected].
- Canon Medical Systems, Rome, Italy.
- Department of Radiology, University of Brescia, Brescia, Italy.
- Department of Radiology, ASST Papa Giovanni XXIII Hospital, Bergamo, Italy.
- School of Medicine, University Milano Bicocca, Milano, Italy.
- Studio Radiologico Bernasconi, Seregno (MB), Italy.
- Medicine and Surgery Department, Insubria University, Varese, Italy.
- Medical Clinical Institute Intermedica-Columbus, Milano, Italy.
Abstract
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. 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. 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. Incorporating DLR into 1.5-T MSK MRI protocols enhances resolution and maintains SNR and CNR, improving MSK structure visualization. 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. 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.