Matches in SemOpenAlex for { <https://semopenalex.org/work/W4313334496> ?p ?o ?g. }
Showing items 1 to 100 of
100
with 100 items per page.
- W4313334496 endingPage "2043.e1" @default.
- W4313334496 startingPage "2037" @default.
- W4313334496 abstract "In this work, we applied and validated an artificial intelligence technique known as generative adversarial networks (GANs) to create large volumes of high-fidelity synthetic anteroposterior (AP) pelvis radiographs that can enable deep learning (DL)-based image analyses, while ensuring patient privacy.AP pelvis radiographs with native hips were gathered from an institutional registry between 1998 and 2018. The data was used to train a model to create 512 × 512 pixel synthetic AP pelvis images. The network was trained on 25 million images produced through augmentation. A set of 100 random images (50/50 real/synthetic) was evaluated by 3 orthopaedic surgeons and 2 radiologists to discern real versus synthetic images. Two models (joint localization and segmentation) were trained using synthetic images and tested on real images.The final model was trained on 37,640 real radiographs (16,782 patients). In a computer assessment of image fidelity, the final model achieved an excellent rating. In a blinded review of paired images (1 real, 1 synthetic), orthopaedic surgeon reviewers were unable to correctly identify which image was synthetic (accuracy = 55%, Kappa = 0.11), highlighting synthetic image fidelity. The synthetic and real images showed equivalent performance when they were assessed by established DL models.This work shows the ability to use a DL technique to generate a large volume of high-fidelity synthetic pelvis images not discernible from real imaging by computers or experts. These images can be used for cross-institutional sharing and model pretraining, further advancing the performance of DL models without risk to patient data safety.Level III." @default.
- W4313334496 created "2023-01-06" @default.
- W4313334496 creator A5000122766 @default.
- W4313334496 creator A5003233066 @default.
- W4313334496 creator A5003289617 @default.
- W4313334496 creator A5008832314 @default.
- W4313334496 creator A5016701027 @default.
- W4313334496 creator A5021441821 @default.
- W4313334496 creator A5023677665 @default.
- W4313334496 creator A5038658155 @default.
- W4313334496 creator A5041981029 @default.
- W4313334496 creator A5044687271 @default.
- W4313334496 date "2023-10-01" @default.
- W4313334496 modified "2023-10-08" @default.
- W4313334496 title "Creating High Fidelity Synthetic Pelvis Radiographs Using Generative Adversarial Networks: Unlocking the Potential of Deep Learning Models Without Patient Privacy Concerns" @default.
- W4313334496 cites W2618530766 @default.
- W4313334496 cites W2790706219 @default.
- W4313334496 cites W2794022343 @default.
- W4313334496 cites W2804649465 @default.
- W4313334496 cites W2811374795 @default.
- W4313334496 cites W2962843773 @default.
- W4313334496 cites W2982036758 @default.
- W4313334496 cites W3129432353 @default.
- W4313334496 cites W3130679116 @default.
- W4313334496 cites W3131152693 @default.
- W4313334496 cites W3134189189 @default.
- W4313334496 cites W3166971825 @default.
- W4313334496 cites W4286717671 @default.
- W4313334496 cites W4294106961 @default.
- W4313334496 cites W4308185840 @default.
- W4313334496 doi "https://doi.org/10.1016/j.arth.2022.12.013" @default.
- W4313334496 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/36535448" @default.
- W4313334496 hasPublicationYear "2023" @default.
- W4313334496 type Work @default.
- W4313334496 citedByCount "1" @default.
- W4313334496 countsByYear W43133344962023 @default.
- W4313334496 crossrefType "journal-article" @default.
- W4313334496 hasAuthorship W4313334496A5000122766 @default.
- W4313334496 hasAuthorship W4313334496A5003233066 @default.
- W4313334496 hasAuthorship W4313334496A5003289617 @default.
- W4313334496 hasAuthorship W4313334496A5008832314 @default.
- W4313334496 hasAuthorship W4313334496A5016701027 @default.
- W4313334496 hasAuthorship W4313334496A5021441821 @default.
- W4313334496 hasAuthorship W4313334496A5023677665 @default.
- W4313334496 hasAuthorship W4313334496A5038658155 @default.
- W4313334496 hasAuthorship W4313334496A5041981029 @default.
- W4313334496 hasAuthorship W4313334496A5044687271 @default.
- W4313334496 hasConcept C108583219 @default.
- W4313334496 hasConcept C119857082 @default.
- W4313334496 hasConcept C126838900 @default.
- W4313334496 hasConcept C154945302 @default.
- W4313334496 hasConcept C160920958 @default.
- W4313334496 hasConcept C2776459999 @default.
- W4313334496 hasConcept C2778357063 @default.
- W4313334496 hasConcept C31601959 @default.
- W4313334496 hasConcept C31972630 @default.
- W4313334496 hasConcept C36454342 @default.
- W4313334496 hasConcept C41008148 @default.
- W4313334496 hasConcept C58489278 @default.
- W4313334496 hasConcept C71924100 @default.
- W4313334496 hasConcept C76155785 @default.
- W4313334496 hasConcept C81363708 @default.
- W4313334496 hasConceptScore W4313334496C108583219 @default.
- W4313334496 hasConceptScore W4313334496C119857082 @default.
- W4313334496 hasConceptScore W4313334496C126838900 @default.
- W4313334496 hasConceptScore W4313334496C154945302 @default.
- W4313334496 hasConceptScore W4313334496C160920958 @default.
- W4313334496 hasConceptScore W4313334496C2776459999 @default.
- W4313334496 hasConceptScore W4313334496C2778357063 @default.
- W4313334496 hasConceptScore W4313334496C31601959 @default.
- W4313334496 hasConceptScore W4313334496C31972630 @default.
- W4313334496 hasConceptScore W4313334496C36454342 @default.
- W4313334496 hasConceptScore W4313334496C41008148 @default.
- W4313334496 hasConceptScore W4313334496C58489278 @default.
- W4313334496 hasConceptScore W4313334496C71924100 @default.
- W4313334496 hasConceptScore W4313334496C76155785 @default.
- W4313334496 hasConceptScore W4313334496C81363708 @default.
- W4313334496 hasFunder F4320309464 @default.
- W4313334496 hasFunder F4320332161 @default.
- W4313334496 hasIssue "10" @default.
- W4313334496 hasLocation W43133344961 @default.
- W4313334496 hasLocation W43133344962 @default.
- W4313334496 hasOpenAccess W4313334496 @default.
- W4313334496 hasPrimaryLocation W43133344961 @default.
- W4313334496 hasRelatedWork W2724710774 @default.
- W4313334496 hasRelatedWork W2731899572 @default.
- W4313334496 hasRelatedWork W3111570720 @default.
- W4313334496 hasRelatedWork W3116150086 @default.
- W4313334496 hasRelatedWork W3133861977 @default.
- W4313334496 hasRelatedWork W4200173597 @default.
- W4313334496 hasRelatedWork W4281780675 @default.
- W4313334496 hasRelatedWork W4297820521 @default.
- W4313334496 hasRelatedWork W4312417841 @default.
- W4313334496 hasRelatedWork W4321369474 @default.
- W4313334496 hasVolume "38" @default.
- W4313334496 isParatext "false" @default.
- W4313334496 isRetracted "false" @default.
- W4313334496 workType "article" @default.