Matches in SemOpenAlex for { <https://semopenalex.org/work/W4298102292> ?p ?o ?g. }
Showing items 1 to 75 of
75
with 100 items per page.
- W4298102292 abstract "Purpose: To improve reconstruction fidelity of fine structures and textures in deep learning (DL) based reconstructions. Methods: A novel patch-based Unsupervised Feature Loss (UFLoss) is proposed and incorporated into the training of DL-based reconstruction frameworks in order to preserve perceptual similarity and high-order statistics. The UFLoss provides instance-level discrimination by mapping similar instances to similar low-dimensional feature vectors and is trained without any human annotation. By adding an additional loss function on the low-dimensional feature space during training, the reconstruction frameworks from under-sampled or corrupted data can reproduce more realistic images that are closer to the original with finer textures, sharper edges, and improved overall image quality. The performance of the proposed UFLoss is demonstrated on unrolled networks for accelerated 2D and 3D knee MRI reconstruction with retrospective under-sampling. Quantitative metrics including NRMSE, SSIM, and our proposed UFLoss were used to evaluate the performance of the proposed method and compare it with others. Results: In-vivo experiments indicate that adding the UFLoss encourages sharper edges and more faithful contrasts compared to traditional and learning-based methods with pure l2 loss. More detailed textures can be seen in both 2D and 3D knee MR images. Quantitative results indicate that reconstruction with UFLoss can provide comparable NRMSE and a higher SSIM while achieving a much lower UFLoss value. Conclusion: We present UFLoss, a patch-based unsupervised learned feature loss, which allows the training of DL-based reconstruction to obtain more detailed texture, finer features, and sharper edges with higher overall image quality under DL-based reconstruction frameworks." @default.
- W4298102292 created "2022-10-01" @default.
- W4298102292 creator A5026906414 @default.
- W4298102292 creator A5042014034 @default.
- W4298102292 creator A5056163027 @default.
- W4298102292 creator A5064167907 @default.
- W4298102292 creator A5078648020 @default.
- W4298102292 creator A5082297273 @default.
- W4298102292 creator A5086880888 @default.
- W4298102292 date "2021-08-27" @default.
- W4298102292 modified "2023-09-29" @default.
- W4298102292 title "High Fidelity Deep Learning-based MRI Reconstruction with Instance-wise Discriminative Feature Matching Loss" @default.
- W4298102292 doi "https://doi.org/10.48550/arxiv.2108.12460" @default.
- W4298102292 hasPublicationYear "2021" @default.
- W4298102292 type Work @default.
- W4298102292 citedByCount "0" @default.
- W4298102292 crossrefType "posted-content" @default.
- W4298102292 hasAuthorship W4298102292A5026906414 @default.
- W4298102292 hasAuthorship W4298102292A5042014034 @default.
- W4298102292 hasAuthorship W4298102292A5056163027 @default.
- W4298102292 hasAuthorship W4298102292A5064167907 @default.
- W4298102292 hasAuthorship W4298102292A5078648020 @default.
- W4298102292 hasAuthorship W4298102292A5082297273 @default.
- W4298102292 hasAuthorship W4298102292A5086880888 @default.
- W4298102292 hasBestOaLocation W42981022921 @default.
- W4298102292 hasConcept C103278499 @default.
- W4298102292 hasConcept C105795698 @default.
- W4298102292 hasConcept C115961682 @default.
- W4298102292 hasConcept C138885662 @default.
- W4298102292 hasConcept C141379421 @default.
- W4298102292 hasConcept C153180895 @default.
- W4298102292 hasConcept C154945302 @default.
- W4298102292 hasConcept C165064840 @default.
- W4298102292 hasConcept C2776401178 @default.
- W4298102292 hasConcept C2776459999 @default.
- W4298102292 hasConcept C31972630 @default.
- W4298102292 hasConcept C33923547 @default.
- W4298102292 hasConcept C41008148 @default.
- W4298102292 hasConcept C41895202 @default.
- W4298102292 hasConcept C76155785 @default.
- W4298102292 hasConcept C83665646 @default.
- W4298102292 hasConcept C97931131 @default.
- W4298102292 hasConceptScore W4298102292C103278499 @default.
- W4298102292 hasConceptScore W4298102292C105795698 @default.
- W4298102292 hasConceptScore W4298102292C115961682 @default.
- W4298102292 hasConceptScore W4298102292C138885662 @default.
- W4298102292 hasConceptScore W4298102292C141379421 @default.
- W4298102292 hasConceptScore W4298102292C153180895 @default.
- W4298102292 hasConceptScore W4298102292C154945302 @default.
- W4298102292 hasConceptScore W4298102292C165064840 @default.
- W4298102292 hasConceptScore W4298102292C2776401178 @default.
- W4298102292 hasConceptScore W4298102292C2776459999 @default.
- W4298102292 hasConceptScore W4298102292C31972630 @default.
- W4298102292 hasConceptScore W4298102292C33923547 @default.
- W4298102292 hasConceptScore W4298102292C41008148 @default.
- W4298102292 hasConceptScore W4298102292C41895202 @default.
- W4298102292 hasConceptScore W4298102292C76155785 @default.
- W4298102292 hasConceptScore W4298102292C83665646 @default.
- W4298102292 hasConceptScore W4298102292C97931131 @default.
- W4298102292 hasLocation W42981022921 @default.
- W4298102292 hasOpenAccess W4298102292 @default.
- W4298102292 hasPrimaryLocation W42981022921 @default.
- W4298102292 hasRelatedWork W1461621550 @default.
- W4298102292 hasRelatedWork W1971623867 @default.
- W4298102292 hasRelatedWork W1982770690 @default.
- W4298102292 hasRelatedWork W2125743092 @default.
- W4298102292 hasRelatedWork W2546942002 @default.
- W4298102292 hasRelatedWork W2554403468 @default.
- W4298102292 hasRelatedWork W2773500201 @default.
- W4298102292 hasRelatedWork W2786306966 @default.
- W4298102292 hasRelatedWork W2944661354 @default.
- W4298102292 hasRelatedWork W3202305871 @default.
- W4298102292 isParatext "false" @default.
- W4298102292 isRetracted "false" @default.
- W4298102292 workType "article" @default.