Matches in SemOpenAlex for { <https://semopenalex.org/work/W3136689951> ?p ?o ?g. }
Showing items 1 to 80 of
80
with 100 items per page.
- W3136689951 endingPage "27" @default.
- W3136689951 startingPage "1" @default.
- W3136689951 abstract "Organ segmentation in CT volumes is an important pre-processing step in many computer assisted intervention and diagnosis methods. In recent years, convolutional neural networks have dominated the state of the art in this task. However, since this problem presents a challenging environment due to high variability in the organ’s shape and similarity between tissues, the generation of false negative and false positive regions in the output segmentation is a common issue. Recent works have shown that the uncertainty analysis of the model can provide us with useful information about potential errors in the segmentation. In this context, we proposed a segmentation refinement method based on uncertainty analysis and graph convolutional networks. We employ the uncertainty levels of the convolutional network in a particular input volume to formulate a semi-supervised graph learning problem that is solved by training a graph convolutional network. To test our method we refine the initial output of a 2D U-Net. We validate our framework with the NIH pancreas dataset and the spleen dataset of the medical segmentation decathlon. We show that our method outperforms the state-of-the-art CRF refinement method by improving the dice score by 1% for the pancreas and 2% for spleen, with respect to the original U-Net’s prediction. Finally, we perform a sensitivity analysis on the parameters of our proposal and discuss the applicability to other CNN architectures, the results, and current limitations of the model for future work in this research direction. For reproducibility purposes, we make our code publicly available at https://github.com/rodsom22/gcn_refinement" @default.
- W3136689951 created "2021-03-29" @default.
- W3136689951 creator A5046294027 @default.
- W3136689951 creator A5046896448 @default.
- W3136689951 creator A5046955009 @default.
- W3136689951 date "2020-12-11" @default.
- W3136689951 modified "2023-09-27" @default.
- W3136689951 title "An Uncertainty-Driven GCN Refinement Strategy for Organ Segmentation" @default.
- W3136689951 hasPublicationYear "2020" @default.
- W3136689951 type Work @default.
- W3136689951 sameAs 3136689951 @default.
- W3136689951 citedByCount "0" @default.
- W3136689951 crossrefType "journal-article" @default.
- W3136689951 hasAuthorship W3136689951A5046294027 @default.
- W3136689951 hasAuthorship W3136689951A5046896448 @default.
- W3136689951 hasAuthorship W3136689951A5046955009 @default.
- W3136689951 hasConcept C105795698 @default.
- W3136689951 hasConcept C111919701 @default.
- W3136689951 hasConcept C119857082 @default.
- W3136689951 hasConcept C124101348 @default.
- W3136689951 hasConcept C132525143 @default.
- W3136689951 hasConcept C151730666 @default.
- W3136689951 hasConcept C153180895 @default.
- W3136689951 hasConcept C154945302 @default.
- W3136689951 hasConcept C22029948 @default.
- W3136689951 hasConcept C2779343474 @default.
- W3136689951 hasConcept C33923547 @default.
- W3136689951 hasConcept C41008148 @default.
- W3136689951 hasConcept C43126263 @default.
- W3136689951 hasConcept C80444323 @default.
- W3136689951 hasConcept C81363708 @default.
- W3136689951 hasConcept C86803240 @default.
- W3136689951 hasConcept C89600930 @default.
- W3136689951 hasConceptScore W3136689951C105795698 @default.
- W3136689951 hasConceptScore W3136689951C111919701 @default.
- W3136689951 hasConceptScore W3136689951C119857082 @default.
- W3136689951 hasConceptScore W3136689951C124101348 @default.
- W3136689951 hasConceptScore W3136689951C132525143 @default.
- W3136689951 hasConceptScore W3136689951C151730666 @default.
- W3136689951 hasConceptScore W3136689951C153180895 @default.
- W3136689951 hasConceptScore W3136689951C154945302 @default.
- W3136689951 hasConceptScore W3136689951C22029948 @default.
- W3136689951 hasConceptScore W3136689951C2779343474 @default.
- W3136689951 hasConceptScore W3136689951C33923547 @default.
- W3136689951 hasConceptScore W3136689951C41008148 @default.
- W3136689951 hasConceptScore W3136689951C43126263 @default.
- W3136689951 hasConceptScore W3136689951C80444323 @default.
- W3136689951 hasConceptScore W3136689951C81363708 @default.
- W3136689951 hasConceptScore W3136689951C86803240 @default.
- W3136689951 hasConceptScore W3136689951C89600930 @default.
- W3136689951 hasLocation W31366899511 @default.
- W3136689951 hasOpenAccess W3136689951 @default.
- W3136689951 hasPrimaryLocation W31366899511 @default.
- W3136689951 hasRelatedWork W2330601728 @default.
- W3136689951 hasRelatedWork W2477957254 @default.
- W3136689951 hasRelatedWork W2512569467 @default.
- W3136689951 hasRelatedWork W2799657635 @default.
- W3136689951 hasRelatedWork W2914456020 @default.
- W3136689951 hasRelatedWork W2945667908 @default.
- W3136689951 hasRelatedWork W2947903101 @default.
- W3136689951 hasRelatedWork W2966782955 @default.
- W3136689951 hasRelatedWork W3048132434 @default.
- W3136689951 hasRelatedWork W3089334789 @default.
- W3136689951 hasRelatedWork W3091541864 @default.
- W3136689951 hasRelatedWork W3118743179 @default.
- W3136689951 hasRelatedWork W3119795314 @default.
- W3136689951 hasRelatedWork W3134093991 @default.
- W3136689951 hasRelatedWork W3136421420 @default.
- W3136689951 hasRelatedWork W3169270314 @default.
- W3136689951 hasRelatedWork W3171239615 @default.
- W3136689951 hasRelatedWork W3202006693 @default.
- W3136689951 hasRelatedWork W2182208022 @default.
- W3136689951 hasRelatedWork W3086807020 @default.
- W3136689951 hasVolume "1" @default.
- W3136689951 isParatext "false" @default.
- W3136689951 isRetracted "false" @default.
- W3136689951 magId "3136689951" @default.
- W3136689951 workType "article" @default.