Matches in SemOpenAlex for { <https://semopenalex.org/work/W4387322810> ?p ?o ?g. }
Showing items 1 to 71 of
71
with 100 items per page.
- W4387322810 abstract "Fully automatic cardiac segmentation can be a fast and reproducible method to extract clinical measurements from an echocardiography examination. The U-Net architecture is the current state-of-the-art deep learning architecture for medical segmentation and can segment cardiac structures in real-time with average errors comparable to inter-observer variability. However, this architecture still generates large outliers that are often anatomically incorrect. This work uses the concept of graph convolutional neural networks that predict the contour points of the structures of interest instead of labeling each pixel. We propose a graph architecture that uses two convolutional rings based on cardiac anatomy and show that this eliminates anatomical incorrect multi-structure segmentations on the publicly available CAMUS dataset. Additionally, this work contributes with an ablation study on the graph convolutional architecture and an evaluation of clinical measurements on the clinical HUNT4 dataset. Finally, we propose to use the inter-model agreement of the U-Net and the graph network as a predictor of both the input and segmentation quality. We show this predictor can detect out-of-distribution and unsuitable input images in real-time. Source code is available online: https://github.com/gillesvntnu/GCN_multistructure" @default.
- W4387322810 created "2023-10-04" @default.
- W4387322810 creator A5004404233 @default.
- W4387322810 creator A5030363408 @default.
- W4387322810 creator A5030646079 @default.
- W4387322810 creator A5044809861 @default.
- W4387322810 creator A5048844030 @default.
- W4387322810 creator A5077326564 @default.
- W4387322810 creator A5088266518 @default.
- W4387322810 date "2023-10-02" @default.
- W4387322810 modified "2023-10-14" @default.
- W4387322810 title "Towards Robust Cardiac Segmentation using Graph Convolutional Networks" @default.
- W4387322810 doi "https://doi.org/10.48550/arxiv.2310.01210" @default.
- W4387322810 hasPublicationYear "2023" @default.
- W4387322810 type Work @default.
- W4387322810 citedByCount "0" @default.
- W4387322810 crossrefType "posted-content" @default.
- W4387322810 hasAuthorship W4387322810A5004404233 @default.
- W4387322810 hasAuthorship W4387322810A5030363408 @default.
- W4387322810 hasAuthorship W4387322810A5030646079 @default.
- W4387322810 hasAuthorship W4387322810A5044809861 @default.
- W4387322810 hasAuthorship W4387322810A5048844030 @default.
- W4387322810 hasAuthorship W4387322810A5077326564 @default.
- W4387322810 hasAuthorship W4387322810A5088266518 @default.
- W4387322810 hasBestOaLocation W43873228101 @default.
- W4387322810 hasConcept C108583219 @default.
- W4387322810 hasConcept C111919701 @default.
- W4387322810 hasConcept C123657996 @default.
- W4387322810 hasConcept C132525143 @default.
- W4387322810 hasConcept C142362112 @default.
- W4387322810 hasConcept C153180895 @default.
- W4387322810 hasConcept C153349607 @default.
- W4387322810 hasConcept C154945302 @default.
- W4387322810 hasConcept C160633673 @default.
- W4387322810 hasConcept C41008148 @default.
- W4387322810 hasConcept C43126263 @default.
- W4387322810 hasConcept C79337645 @default.
- W4387322810 hasConcept C80444323 @default.
- W4387322810 hasConcept C81363708 @default.
- W4387322810 hasConcept C89600930 @default.
- W4387322810 hasConceptScore W4387322810C108583219 @default.
- W4387322810 hasConceptScore W4387322810C111919701 @default.
- W4387322810 hasConceptScore W4387322810C123657996 @default.
- W4387322810 hasConceptScore W4387322810C132525143 @default.
- W4387322810 hasConceptScore W4387322810C142362112 @default.
- W4387322810 hasConceptScore W4387322810C153180895 @default.
- W4387322810 hasConceptScore W4387322810C153349607 @default.
- W4387322810 hasConceptScore W4387322810C154945302 @default.
- W4387322810 hasConceptScore W4387322810C160633673 @default.
- W4387322810 hasConceptScore W4387322810C41008148 @default.
- W4387322810 hasConceptScore W4387322810C43126263 @default.
- W4387322810 hasConceptScore W4387322810C79337645 @default.
- W4387322810 hasConceptScore W4387322810C80444323 @default.
- W4387322810 hasConceptScore W4387322810C81363708 @default.
- W4387322810 hasConceptScore W4387322810C89600930 @default.
- W4387322810 hasLocation W43873228101 @default.
- W4387322810 hasOpenAccess W4387322810 @default.
- W4387322810 hasPrimaryLocation W43873228101 @default.
- W4387322810 hasRelatedWork W2731899572 @default.
- W4387322810 hasRelatedWork W2790662084 @default.
- W4387322810 hasRelatedWork W2999805992 @default.
- W4387322810 hasRelatedWork W3011074480 @default.
- W4387322810 hasRelatedWork W3116150086 @default.
- W4387322810 hasRelatedWork W3133861977 @default.
- W4387322810 hasRelatedWork W4200173597 @default.
- W4387322810 hasRelatedWork W4291897433 @default.
- W4387322810 hasRelatedWork W4312417841 @default.
- W4387322810 hasRelatedWork W4321369474 @default.
- W4387322810 isParatext "false" @default.
- W4387322810 isRetracted "false" @default.
- W4387322810 workType "article" @default.