Matches in SemOpenAlex for { <https://semopenalex.org/work/W4296551294> ?p ?o ?g. }
Showing items 1 to 77 of
77
with 100 items per page.
- W4296551294 abstract "In order to achieve good performance and generalisability, medical image segmentation models should be trained on sizeable datasets with sufficient variability. Due to ethics and governance restrictions, and the costs associated with labelling data, scientific development is often stifled, with models trained and tested on limited data. Data augmentation is often used to artificially increase the variability in the data distribution and improve model generalisability. Recent works have explored deep generative models for image synthesis, as such an approach would enable the generation of an effectively infinite amount of varied data, addressing the generalisability and data access problems. However, many proposed solutions limit the user's control over what is generated. In this work, we propose brainSPADE, a model which combines a synthetic diffusion-based label generator with a semantic image generator. Our model can produce fully synthetic brain labels on-demand, with or without pathology of interest, and then generate a corresponding MRI image of an arbitrary guided style. Experiments show that brainSPADE synthetic data can be used to train segmentation models with performance comparable to that of models trained on real data." @default.
- W4296551294 created "2022-09-21" @default.
- W4296551294 creator A5007172717 @default.
- W4296551294 creator A5014883517 @default.
- W4296551294 creator A5028279799 @default.
- W4296551294 creator A5047180446 @default.
- W4296551294 creator A5074184782 @default.
- W4296551294 creator A5083427047 @default.
- W4296551294 creator A5086341126 @default.
- W4296551294 date "2022-09-17" @default.
- W4296551294 modified "2023-10-05" @default.
- W4296551294 title "Can segmentation models be trained with fully synthetically generated data?" @default.
- W4296551294 doi "https://doi.org/10.48550/arxiv.2209.08256" @default.
- W4296551294 hasPublicationYear "2022" @default.
- W4296551294 type Work @default.
- W4296551294 citedByCount "0" @default.
- W4296551294 crossrefType "posted-content" @default.
- W4296551294 hasAuthorship W4296551294A5007172717 @default.
- W4296551294 hasAuthorship W4296551294A5014883517 @default.
- W4296551294 hasAuthorship W4296551294A5028279799 @default.
- W4296551294 hasAuthorship W4296551294A5047180446 @default.
- W4296551294 hasAuthorship W4296551294A5074184782 @default.
- W4296551294 hasAuthorship W4296551294A5083427047 @default.
- W4296551294 hasAuthorship W4296551294A5086341126 @default.
- W4296551294 hasBestOaLocation W42965512941 @default.
- W4296551294 hasConcept C115961682 @default.
- W4296551294 hasConcept C119857082 @default.
- W4296551294 hasConcept C121332964 @default.
- W4296551294 hasConcept C124101348 @default.
- W4296551294 hasConcept C124504099 @default.
- W4296551294 hasConcept C125308379 @default.
- W4296551294 hasConcept C144133560 @default.
- W4296551294 hasConcept C153180895 @default.
- W4296551294 hasConcept C154945302 @default.
- W4296551294 hasConcept C160920958 @default.
- W4296551294 hasConcept C162853370 @default.
- W4296551294 hasConcept C163258240 @default.
- W4296551294 hasConcept C167966045 @default.
- W4296551294 hasConcept C2780992000 @default.
- W4296551294 hasConcept C39890363 @default.
- W4296551294 hasConcept C41008148 @default.
- W4296551294 hasConcept C62520636 @default.
- W4296551294 hasConcept C89600930 @default.
- W4296551294 hasConceptScore W4296551294C115961682 @default.
- W4296551294 hasConceptScore W4296551294C119857082 @default.
- W4296551294 hasConceptScore W4296551294C121332964 @default.
- W4296551294 hasConceptScore W4296551294C124101348 @default.
- W4296551294 hasConceptScore W4296551294C124504099 @default.
- W4296551294 hasConceptScore W4296551294C125308379 @default.
- W4296551294 hasConceptScore W4296551294C144133560 @default.
- W4296551294 hasConceptScore W4296551294C153180895 @default.
- W4296551294 hasConceptScore W4296551294C154945302 @default.
- W4296551294 hasConceptScore W4296551294C160920958 @default.
- W4296551294 hasConceptScore W4296551294C162853370 @default.
- W4296551294 hasConceptScore W4296551294C163258240 @default.
- W4296551294 hasConceptScore W4296551294C167966045 @default.
- W4296551294 hasConceptScore W4296551294C2780992000 @default.
- W4296551294 hasConceptScore W4296551294C39890363 @default.
- W4296551294 hasConceptScore W4296551294C41008148 @default.
- W4296551294 hasConceptScore W4296551294C62520636 @default.
- W4296551294 hasConceptScore W4296551294C89600930 @default.
- W4296551294 hasLocation W42965512941 @default.
- W4296551294 hasOpenAccess W4296551294 @default.
- W4296551294 hasPrimaryLocation W42965512941 @default.
- W4296551294 hasRelatedWork W2280377497 @default.
- W4296551294 hasRelatedWork W2967848559 @default.
- W4296551294 hasRelatedWork W3014948380 @default.
- W4296551294 hasRelatedWork W3174044702 @default.
- W4296551294 hasRelatedWork W4238433571 @default.
- W4296551294 hasRelatedWork W4283803360 @default.
- W4296551294 hasRelatedWork W4316116392 @default.
- W4296551294 hasRelatedWork W4317695495 @default.
- W4296551294 hasRelatedWork W4365211920 @default.
- W4296551294 hasRelatedWork W4380551139 @default.
- W4296551294 isParatext "false" @default.
- W4296551294 isRetracted "false" @default.
- W4296551294 workType "article" @default.