Matches in SemOpenAlex for { <https://semopenalex.org/work/W3127252229> ?p ?o ?g. }
Showing items 1 to 92 of
92
with 100 items per page.
- W3127252229 abstract "22. Shortening acquisition time and reducing the motion-artifact are two of the most critical issues in MRI. As a promising solution, high-quality MRI image restoration provides a new approach to achieve higher resolution without costing additional acquisition time or modification on the pulse sequences. Recently, as to the rise of deep learning, convolutional neural networks have been proposed for super-resolution (SR) image generation and motion-artifact reduction (MAR) for MRI. Recent studies suggest that using perceptual feature space loss and k space loss to capture the perceptual information and high-frequency information of images, respectively. However, the quality of reconstructed SR and MAR MR images is limited because the most important details of the informative area in the MR image, the edges and the structure, cannot be very well restored. Besides, lots of the SR approaches are trained by using low-resolution images generated by applying bicubic or blur-downscale degradation, which cannot represent the real process of MRI measurement. Such inconsistencies lead to performance degradation in the reconstruction of SR images as well. This study reveals that using the L1 loss of SSIM and gradient map edge quality loss could force the deep learning model to focus on studying the features of edges and structure details of MR images, thus generating SR images with more accurate, fruitful information and reduced motion-artifact. We employed a state-of-the-art model, RCAN, as the network framework in both SR and MAR tasks, trained the model by using low-resolution images and motion-artifact affected images which were generated by emulating how they are measured in the real MRI measurement to ensure the model can be easily applied in the practical clinic environment, and verified the trained model could work fairly well." @default.
- W3127252229 created "2021-02-15" @default.
- W3127252229 creator A5018744849 @default.
- W3127252229 creator A5019560977 @default.
- W3127252229 date "2021-01-30" @default.
- W3127252229 modified "2023-09-26" @default.
- W3127252229 title "Edge, Structure and Texture Refinement for Retrospective High Quality MRI Restoration using Deep Learning" @default.
- W3127252229 cites W2133665775 @default.
- W3127252229 cites W2194775991 @default.
- W3127252229 cites W2242218935 @default.
- W3127252229 cites W2331128040 @default.
- W3127252229 cites W2476548250 @default.
- W3127252229 cites W2562637781 @default.
- W3127252229 cites W2778924750 @default.
- W3127252229 cites W2780544323 @default.
- W3127252229 cites W2794800073 @default.
- W3127252229 cites W2794977498 @default.
- W3127252229 cites W2866634454 @default.
- W3127252229 cites W2906473494 @default.
- W3127252229 cites W2945147429 @default.
- W3127252229 cites W2953427271 @default.
- W3127252229 cites W2963372104 @default.
- W3127252229 cites W2963446712 @default.
- W3127252229 cites W2963729050 @default.
- W3127252229 cites W3015686011 @default.
- W3127252229 cites W3020887200 @default.
- W3127252229 cites W3037784355 @default.
- W3127252229 cites W3098848838 @default.
- W3127252229 hasPublicationYear "2021" @default.
- W3127252229 type Work @default.
- W3127252229 sameAs 3127252229 @default.
- W3127252229 citedByCount "0" @default.
- W3127252229 crossrefType "posted-content" @default.
- W3127252229 hasAuthorship W3127252229A5018744849 @default.
- W3127252229 hasAuthorship W3127252229A5019560977 @default.
- W3127252229 hasConcept C108583219 @default.
- W3127252229 hasConcept C115961682 @default.
- W3127252229 hasConcept C138885662 @default.
- W3127252229 hasConcept C153180895 @default.
- W3127252229 hasConcept C154945302 @default.
- W3127252229 hasConcept C162307627 @default.
- W3127252229 hasConcept C171836373 @default.
- W3127252229 hasConcept C2776401178 @default.
- W3127252229 hasConcept C2779010991 @default.
- W3127252229 hasConcept C31972630 @default.
- W3127252229 hasConcept C41008148 @default.
- W3127252229 hasConcept C41895202 @default.
- W3127252229 hasConcept C49608258 @default.
- W3127252229 hasConcept C55020928 @default.
- W3127252229 hasConcept C81363708 @default.
- W3127252229 hasConceptScore W3127252229C108583219 @default.
- W3127252229 hasConceptScore W3127252229C115961682 @default.
- W3127252229 hasConceptScore W3127252229C138885662 @default.
- W3127252229 hasConceptScore W3127252229C153180895 @default.
- W3127252229 hasConceptScore W3127252229C154945302 @default.
- W3127252229 hasConceptScore W3127252229C162307627 @default.
- W3127252229 hasConceptScore W3127252229C171836373 @default.
- W3127252229 hasConceptScore W3127252229C2776401178 @default.
- W3127252229 hasConceptScore W3127252229C2779010991 @default.
- W3127252229 hasConceptScore W3127252229C31972630 @default.
- W3127252229 hasConceptScore W3127252229C41008148 @default.
- W3127252229 hasConceptScore W3127252229C41895202 @default.
- W3127252229 hasConceptScore W3127252229C49608258 @default.
- W3127252229 hasConceptScore W3127252229C55020928 @default.
- W3127252229 hasConceptScore W3127252229C81363708 @default.
- W3127252229 hasLocation W31272522291 @default.
- W3127252229 hasOpenAccess W3127252229 @default.
- W3127252229 hasPrimaryLocation W31272522291 @default.
- W3127252229 hasRelatedWork W2523912646 @default.
- W3127252229 hasRelatedWork W2603313224 @default.
- W3127252229 hasRelatedWork W2751748841 @default.
- W3127252229 hasRelatedWork W2806407713 @default.
- W3127252229 hasRelatedWork W2891378267 @default.
- W3127252229 hasRelatedWork W2920329386 @default.
- W3127252229 hasRelatedWork W2924128390 @default.
- W3127252229 hasRelatedWork W2952420925 @default.
- W3127252229 hasRelatedWork W2953427271 @default.
- W3127252229 hasRelatedWork W2958204294 @default.
- W3127252229 hasRelatedWork W2981120421 @default.
- W3127252229 hasRelatedWork W3014027047 @default.
- W3127252229 hasRelatedWork W3033962650 @default.
- W3127252229 hasRelatedWork W3129455730 @default.
- W3127252229 hasRelatedWork W3157040989 @default.
- W3127252229 hasRelatedWork W3159447794 @default.
- W3127252229 hasRelatedWork W3173801342 @default.
- W3127252229 hasRelatedWork W3183394902 @default.
- W3127252229 hasRelatedWork W3185971934 @default.
- W3127252229 hasRelatedWork W3213580212 @default.
- W3127252229 isParatext "false" @default.
- W3127252229 isRetracted "false" @default.
- W3127252229 magId "3127252229" @default.
- W3127252229 workType "article" @default.