FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3119639969> ?p ?o ?g. }

• W3119639969 endingPage "2794" @default.
• W3119639969 startingPage "2783" @default.
• W3119639969 abstract "Deep learning can bring time savings and increased reproducibility to medical image analysis. However, acquiring training data is challenging due to the time-intensive nature of labeling and high inter-observer variability in annotations. Rather than labeling images, in this work we propose an alternative pipeline where images are generated from existing high-quality annotations using generative adversarial networks (GANs). Annotations are derived automatically from previously built anatomical models and are transformed into realistic synthetic ultrasound images with paired labels using a CycleGAN. We demonstrate the pipeline by generating synthetic 2D echocardiography images to compare with existing deep learning ultrasound segmentation datasets. A convolutional neural network is trained to segment the left ventricle and left atrium using only synthetic images. Networks trained with synthetic images were extensively tested on four different unseen datasets of real images with median Dice scores of 91, 90, 88, and 87 for left ventricle segmentation. These results match or are better than inter-observer results measured on real ultrasound datasets and are comparable to a network trained on a separate set of real images. Results demonstrate the images produced can effectively be used in place of real data for training. The proposed pipeline opens the door for automatic generation of training data for many tasks in medical imaging as the same process can be applied to other segmentation or landmark detection tasks in any modality. The source code and anatomical models are available to other researchers.11https://adgilbert.github.io/data-generation/." @default.
• W3119639969 created "2021-01-18" @default.
• W3119639969 creator A5011859160 @default.
• W3119639969 creator A5017717812 @default.
• W3119639969 creator A5019810821 @default.
• W3119639969 creator A5022215449 @default.
• W3119639969 creator A5082938227 @default.
• W3119639969 creator A5085599943 @default.
• W3119639969 date "2021-10-01" @default.
• W3119639969 modified "2023-10-16" @default.
• W3119639969 title "Generating Synthetic Labeled Data From Existing Anatomical Models: An Example With Echocardiography Segmentation" @default.
• W3119639969 cites W149222749 @default.
• W3119639969 cites W1503282236 @default.
• W3119639969 cites W1588161861 @default.
• W3119639969 cites W1967557118 @default.
• W3119639969 cites W1984857191 @default.
• W3119639969 cites W1989431850 @default.
• W3119639969 cites W1992343541 @default.
• W3119639969 cites W2015421863 @default.
• W3119639969 cites W2031342017 @default.
• W3119639969 cites W2034463328 @default.
• W3119639969 cites W2042293234 @default.
• W3119639969 cites W2076426701 @default.
• W3119639969 cites W2083704705 @default.
• W3119639969 cites W2117967733 @default.
• W3119639969 cites W2494116072 @default.
• W3119639969 cites W2617665094 @default.
• W3119639969 cites W2794399231 @default.
• W3119639969 cites W2884065486 @default.
• W3119639969 cites W2894839648 @default.
• W3119639969 cites W2903213872 @default.
• W3119639969 cites W2947395348 @default.
• W3119639969 cites W2956892385 @default.
• W3119639969 cites W2962825119 @default.
• W3119639969 cites W2963660453 @default.
• W3119639969 cites W2971013993 @default.
• W3119639969 cites W2979752514 @default.
• W3119639969 cites W2980049073 @default.
• W3119639969 cites W3010152544 @default.
• W3119639969 cites W3013692475 @default.
• W3119639969 cites W3017253860 @default.
• W3119639969 cites W3037817333 @default.
• W3119639969 cites W3047625747 @default.
• W3119639969 cites W3103943044 @default.
• W3119639969 cites W4252684946 @default.
• W3119639969 cites W2979324188 @default.
• W3119639969 doi "https://doi.org/10.1109/tmi.2021.3051806" @default.
• W3119639969 hasPubMedCentralId "https://www.ncbi.nlm.nih.gov/pmc/articles/8493532" @default.
• W3119639969 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/33444134" @default.
• W3119639969 hasPublicationYear "2021" @default.
• W3119639969 type Work @default.
• W3119639969 sameAs 3119639969 @default.
• W3119639969 citedByCount "30" @default.
• W3119639969 countsByYear W31196399692021 @default.
• W3119639969 countsByYear W31196399692022 @default.
• W3119639969 countsByYear W31196399692023 @default.
• W3119639969 crossrefType "journal-article" @default.
• W3119639969 hasAuthorship W3119639969A5011859160 @default.
• W3119639969 hasAuthorship W3119639969A5017717812 @default.
• W3119639969 hasAuthorship W3119639969A5019810821 @default.
• W3119639969 hasAuthorship W3119639969A5022215449 @default.
• W3119639969 hasAuthorship W3119639969A5082938227 @default.
• W3119639969 hasAuthorship W3119639969A5085599943 @default.
• W3119639969 hasBestOaLocation W31196399691 @default.
• W3119639969 hasConcept C108583219 @default.
• W3119639969 hasConcept C124504099 @default.
• W3119639969 hasConcept C153180895 @default.
• W3119639969 hasConcept C154945302 @default.
• W3119639969 hasConcept C160920958 @default.
• W3119639969 hasConcept C199360897 @default.
• W3119639969 hasConcept C31972630 @default.
• W3119639969 hasConcept C41008148 @default.
• W3119639969 hasConcept C43521106 @default.
• W3119639969 hasConcept C58489278 @default.
• W3119639969 hasConcept C81363708 @default.
• W3119639969 hasConcept C89600930 @default.
• W3119639969 hasConceptScore W3119639969C108583219 @default.
• W3119639969 hasConceptScore W3119639969C124504099 @default.
• W3119639969 hasConceptScore W3119639969C153180895 @default.
• W3119639969 hasConceptScore W3119639969C154945302 @default.
• W3119639969 hasConceptScore W3119639969C160920958 @default.
• W3119639969 hasConceptScore W3119639969C199360897 @default.
• W3119639969 hasConceptScore W3119639969C31972630 @default.
• W3119639969 hasConceptScore W3119639969C41008148 @default.
• W3119639969 hasConceptScore W3119639969C43521106 @default.
• W3119639969 hasConceptScore W3119639969C58489278 @default.
• W3119639969 hasConceptScore W3119639969C81363708 @default.
• W3119639969 hasConceptScore W3119639969C89600930 @default.
• W3119639969 hasFunder F4320307874 @default.
• W3119639969 hasFunder F4320338337 @default.
• W3119639969 hasIssue "10" @default.
• W3119639969 hasLocation W31196399691 @default.
• W3119639969 hasLocation W31196399692 @default.
• W3119639969 hasLocation W31196399693 @default.
• W3119639969 hasOpenAccess W3119639969 @default.
• W3119639969 hasPrimaryLocation W31196399691 @default.
• W3119639969 hasRelatedWork W2811106690 @default.
• W3119639969 hasRelatedWork W2922305141 @default.

• next