We found a match
Your institution may have rights to this item. Sign in to continue.
- Title
Utility of deep learning super-resolution in the context of osteoarthritis MRI biomarkers.
- Authors
Chaudhari, Akshay S.; Stevens, Kathryn J.; Wood, Jeff P.; Chakraborty, Amit K.; Gibbons, Eric K.; Fang, Zhongnan; Desai, Arjun D.; Lee, Jin Hyung; Gold, Garry E.; Hargreaves, Brian A.
- Abstract
<bold>Background: </bold>Super-resolution is an emerging method for enhancing MRI resolution; however, its impact on image quality is still unknown.<bold>Purpose: </bold>To evaluate MRI super-resolution using quantitative and qualitative metrics of cartilage morphometry, osteophyte detection, and global image blurring.<bold>Study Type: </bold>Retrospective.<bold>Population: </bold>In all, 176 MRI studies of subjects at varying stages of osteoarthritis.<bold>Field Strength/sequence: </bold>Original-resolution 3D double-echo steady-state (DESS) and DESS with 3× thicker slices retrospectively enhanced using super-resolution and tricubic interpolation (TCI) at 3T.<bold>Assessment: </bold>A quantitative comparison of femoral cartilage morphometry was performed for the original-resolution DESS, the super-resolution, and the TCI scans in 17 subjects. A reader study by three musculoskeletal radiologists assessed cartilage image quality, overall image sharpness, and osteophytes incidence in all three sets of scans. A referenceless blurring metric evaluated blurring in all three image dimensions for the three sets of scans.<bold>Statistical Tests: </bold>Mann-Whitney U-tests compared Dice coefficients (DC) of segmentation accuracy for the DESS, super-resolution, and TCI images, along with the image quality readings and blurring metrics. Sensitivity, specificity, and diagnostic odds ratio (DOR) with 95% confidence intervals compared osteophyte detection for the super-resolution and TCI images, with the original-resolution as a reference.<bold>Results: </bold>DC for the original-resolution (90.2 ± 1.7%) and super-resolution (89.6 ± 2.0%) were significantly higher (P < 0.001) than TCI (86.3 ± 5.6%). Segmentation overlap of super-resolution with the original-resolution (DC = 97.6 ± 0.7%) was significantly higher (P < 0.0001) than TCI overlap (DC = 95.0 ± 1.1%). Cartilage image quality for sharpness and contrast levels, and the through-plane quantitative blur factor for super-resolution images, was significantly (P < 0.001) better than TCI. Super-resolution osteophyte detection sensitivity of 80% (76-82%), specificity of 93% (92-94%), and DOR of 32 (22-46) was significantly higher (P < 0.001) than TCI sensitivity of 73% (69-76%), specificity of 90% (89-91%), and DOR of 17 (13-22).<bold>Data Conclusion: </bold>Super-resolution appears to consistently outperform naïve interpolation and may improve image quality without biasing quantitative biomarkers.<bold>Level Of Evidence: </bold>2 Technical Efficacy: Stage 2 J. Magn. Reson. Imaging 2020;51:768-779.
- Subjects
DEEP learning; HIGH resolution imaging; ODDS ratio; CARTILAGE; CONFIDENCE intervals
- Publication
Journal of Magnetic Resonance Imaging, 2020, Vol 51, Issue 3, p768
- ISSN
1053-1807
- Publication type
journal article
- DOI
10.1002/jmri.26872