FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4296129249> ?p ?o ?g. }

• W4296129249 abstract "Abstract Recent work within neuroimaging consortia have aimed to identify reproducible, and often subtle, brain signatures of psychiatric or neurological conditions. To allow for high-powered brain imaging analyses, it is often necessary to pool MR images that were acquired with different protocols across multiple scanners. Current retrospective harmonization techniques have shown promise in removing cross-site image variation. However, most statistical approaches may over-correct for technical, scanning-related, variation as they cannot distinguish between confounded image-acquisition based variability and cross-site population variability. Such statistical methods often require that datasets contain subjects or patient groups with similar clinical or demographic information to isolate the acquisition-based variability. To overcome this limitation, we consider cross-site MRI image harmonization as a style transfer problem rather than a domain transfer problem. Using a fully unsupervised deep-learning framework based on a generative adversarial network (GAN), we show that MR images can be harmonized by inserting the style information encoded from a single reference image, without knowing their site/scanner labels a priori . We trained our model using data from five large-scale multi-site datasets with varied demographics. Results demonstrated that our style-encoding model can harmonize MR images, and match intensity profiles, without relying on traveling subjects. This model also avoids the need to control for clinical, diagnostic, or demographic information. We highlight the effectiveness of our method for clinical research by comparing extracted cortical and subcortical features, brain-age estimates, and case-control effect sizes before and after the harmonization. We showed that our harmonization removed the cross-site variances, while preserving the anatomical information and clinical meaningful patterns. We further demonstrated that with a diverse training set, our method successfully harmonized MR images collected from unseen scanners and protocols, suggesting a promising novel tool for ongoing collaborative studies. Source code is released in USC-IGC/style_transfer_harmonization (github.com) ." @default.
• W4296129249 created "2022-09-17" @default.
• W4296129249 creator A5010454256 @default.
• W4296129249 creator A5017365268 @default.
• W4296129249 creator A5017878656 @default.
• W4296129249 creator A5019325729 @default.
• W4296129249 creator A5019781190 @default.
• W4296129249 creator A5020243335 @default.
• W4296129249 creator A5041359892 @default.
• W4296129249 creator A5066345371 @default.
• W4296129249 date "2022-09-15" @default.
• W4296129249 modified "2023-10-15" @default.
• W4296129249 title "Style Transfer Generative Adversarial Networks to Harmonize Multi-Site MRI to a Single Reference Image to Avoid Over-Correction" @default.
• W4296129249 cites W2078524519 @default.
• W4296129249 cites W2110208125 @default.
• W4296129249 cites W2413166264 @default.
• W4296129249 cites W2950086191 @default.
• W4296129249 cites W2951042025 @default.
• W4296129249 cites W2961602927 @default.
• W4296129249 cites W2968446587 @default.
• W4296129249 cites W2980199629 @default.
• W4296129249 cites W2990590397 @default.
• W4296129249 cites W3015083995 @default.
• W4296129249 cites W3031827021 @default.
• W4296129249 cites W3037286432 @default.
• W4296129249 cites W3089660604 @default.
• W4296129249 cites W3092335084 @default.
• W4296129249 cites W3115055674 @default.
• W4296129249 cites W3153445520 @default.
• W4296129249 cites W3197863729 @default.
• W4296129249 cites W3203233031 @default.
• W4296129249 cites W3204364267 @default.
• W4296129249 cites W3216447229 @default.
• W4296129249 cites W4224937102 @default.
• W4296129249 cites W4225257091 @default.
• W4296129249 cites W4226348722 @default.
• W4296129249 cites W4241074797 @default.
• W4296129249 cites W4318263505 @default.
• W4296129249 doi "https://doi.org/10.1101/2022.09.12.506445" @default.
• W4296129249 hasPublicationYear "2022" @default.
• W4296129249 type Work @default.
• W4296129249 citedByCount "1" @default.
• W4296129249 countsByYear W42961292492023 @default.
• W4296129249 crossrefType "posted-content" @default.
• W4296129249 hasAuthorship W4296129249A5010454256 @default.
• W4296129249 hasAuthorship W4296129249A5017365268 @default.
• W4296129249 hasAuthorship W4296129249A5017878656 @default.
• W4296129249 hasAuthorship W4296129249A5019325729 @default.
• W4296129249 hasAuthorship W4296129249A5019781190 @default.
• W4296129249 hasAuthorship W4296129249A5020243335 @default.
• W4296129249 hasAuthorship W4296129249A5041359892 @default.
• W4296129249 hasAuthorship W4296129249A5066345371 @default.
• W4296129249 hasBestOaLocation W42961292491 @default.
• W4296129249 hasConcept C111472728 @default.
• W4296129249 hasConcept C115961682 @default.
• W4296129249 hasConcept C118552586 @default.
• W4296129249 hasConcept C119857082 @default.
• W4296129249 hasConcept C121332964 @default.
• W4296129249 hasConcept C124101348 @default.
• W4296129249 hasConcept C138885662 @default.
• W4296129249 hasConcept C150899416 @default.
• W4296129249 hasConcept C152139883 @default.
• W4296129249 hasConcept C153180895 @default.
• W4296129249 hasConcept C154945302 @default.
• W4296129249 hasConcept C15744967 @default.
• W4296129249 hasConcept C167966045 @default.
• W4296129249 hasConcept C24890656 @default.
• W4296129249 hasConcept C2779751349 @default.
• W4296129249 hasConcept C2779962950 @default.
• W4296129249 hasConcept C2908647359 @default.
• W4296129249 hasConcept C39890363 @default.
• W4296129249 hasConcept C41008148 @default.
• W4296129249 hasConcept C58693492 @default.
• W4296129249 hasConcept C71924100 @default.
• W4296129249 hasConcept C75553542 @default.
• W4296129249 hasConcept C99454951 @default.
• W4296129249 hasConceptScore W4296129249C111472728 @default.
• W4296129249 hasConceptScore W4296129249C115961682 @default.
• W4296129249 hasConceptScore W4296129249C118552586 @default.
• W4296129249 hasConceptScore W4296129249C119857082 @default.
• W4296129249 hasConceptScore W4296129249C121332964 @default.
• W4296129249 hasConceptScore W4296129249C124101348 @default.
• W4296129249 hasConceptScore W4296129249C138885662 @default.
• W4296129249 hasConceptScore W4296129249C150899416 @default.
• W4296129249 hasConceptScore W4296129249C152139883 @default.
• W4296129249 hasConceptScore W4296129249C153180895 @default.
• W4296129249 hasConceptScore W4296129249C154945302 @default.
• W4296129249 hasConceptScore W4296129249C15744967 @default.
• W4296129249 hasConceptScore W4296129249C167966045 @default.
• W4296129249 hasConceptScore W4296129249C24890656 @default.
• W4296129249 hasConceptScore W4296129249C2779751349 @default.
• W4296129249 hasConceptScore W4296129249C2779962950 @default.
• W4296129249 hasConceptScore W4296129249C2908647359 @default.
• W4296129249 hasConceptScore W4296129249C39890363 @default.
• W4296129249 hasConceptScore W4296129249C41008148 @default.
• W4296129249 hasConceptScore W4296129249C58693492 @default.
• W4296129249 hasConceptScore W4296129249C71924100 @default.
• W4296129249 hasConceptScore W4296129249C75553542 @default.
• W4296129249 hasConceptScore W4296129249C99454951 @default.
• W4296129249 hasLocation W42961292491 @default.

• next