Quantification of edge-enhancing effects using accelerated deep learning reconstructed orbital MRI sequences.
Authors
Affiliations (5)
Affiliations (5)
- Department of Diagnostic and Interventional Neuroradiology, Eberhard Karls University Tuebingen, Tuebingen D-72076, Germany.
- Centre for Ophthalmology, University Eye Hospital, Eberhard Karls University of Tuebingen, Tuebingen D-72076, Germany.
- Department of Radiation Oncology, University Hospital Tuebingen, Tuebingen D-72076, Germany.
- Department of Neurosurgery, University of Tuebingen, Tuebingen D-72076, Germany.
- Center for Neuro-Oncology, Comprehensive Cancer Center Tuebingen-Stuttgart, University Hospital of Tuebingen, Eberhard Karls University of Tuebingen, Tuebingen D-72070, Germany.
Abstract
To qualitatively and quantitatively compare image quality, edge sharpness, and internal-structure delineation of accelerated deep learning-reconstructed turbo spin-echo (TSE<sub>DLR</sub>) sequences versus conventionally reconstructed TSE (TSE<sub>CR</sub>) in 3 T orbital MRI. Twenty-five patients undergoing 3 T orbital MRI were retrospectively selected. All underwent conventional and accelerated (up to 75%) deep learning-reconstructed axial and coronal T2-weighted and contrast-enhanced fat-saturated T1-weighted TSE (T1CEfs) sequences. Two blinded neuroradiologists rated image quality, edge sharpness, internal tissue delineation, overall sharpness, lesion detection confidence, and lesion conspicuity on a 5-point Likert scale. Quantitative analyses included similarity and image-quality metrics, the Perceptual Sharpness Index (PSI), blur metrics, and edge parameters after Roberts, Sobel, or Canny edge extraction. Qualitatively, edge and overall sharpness were superior with TSE<sub>DLR</sub> in T1CEfs (all p < 0.001), and mainly in T2-weighted imaging. Internal tissue delineation was rater-dependent, with the experienced rater favoring TSE<sub>CR</sub>. Lesion-detection confidence did not differ significantly across reconstructions. Quantitatively, TSE<sub>DLR</sub> improved edge sharpness, with increased edge steepness (all p < 0.001) and decreased edge width (most p ≤ 0.003), though edge contrast was slightly reduced. Blur metrics favored TSE<sub>CR</sub>, while PSI (all p < 0.001) and SNR/PSNR favored TSE<sub>DLR</sub>. Structural similarity was high (SSIM 0.986-0.995; MS-SSIM 0.998-0.999), while high-frequency similarity was lower (FSIM: 0.804-0.861; WASH: 0.729-0.747). Accelerated DL-based reconstructions for orbital MRI maintain or improve lesion conspicuity, overall image quality, and edge sharpness, while substantially reducing scan time. However, reduced internal anatomical delineation warrants cautious interpretation of the images.