Matches in SemOpenAlex for { <https://semopenalex.org/work/W4312339904> ?p ?o ?g. }
- W4312339904 endingPage "133" @default.
- W4312339904 startingPage "123" @default.
- W4312339904 abstract "The segmentation of the fetal cerebral cortex from magnetic resonance imaging (MRI) is an important tool for neurobiological research about the developing human brain. Manual segmentation is difficult and time-consuming. Limited image resolution and partial volume effects introduce errors and labeling noise when attempting to automate the process through machine learning. The significant morphological changes observed during brain growth pose additional challenges for learning-based image segmentation methods, which may drastically increase the amount of necessary training data. In this paper, we propose a framework to learn from noisy labels by using additional regularization via shape priors for the accurate segmentation of the cortical gray matter (CGM) in 3D. Firstly, we introduce a novel structure consistency loss based on persistent homology analysis of the cortical topology. Secondly, a regularization loss term is proposed by integrating assumptions about the cortical thickness within each sample. Our experiments on the developing human connectome project (dHCP) dataset show that our method can predict accurate CGM segmentation learned from noisy labels." @default.
- W4312339904 created "2023-01-04" @default.
- W4312339904 creator A5006461848 @default.
- W4312339904 creator A5010565192 @default.
- W4312339904 creator A5030170981 @default.
- W4312339904 creator A5042654952 @default.
- W4312339904 creator A5045477945 @default.
- W4312339904 creator A5049396894 @default.
- W4312339904 creator A5057304825 @default.
- W4312339904 creator A5068936425 @default.
- W4312339904 creator A5071915668 @default.
- W4312339904 creator A5074707604 @default.
- W4312339904 creator A5075545668 @default.
- W4312339904 creator A5078127596 @default.
- W4312339904 creator A5089189158 @default.
- W4312339904 date "2022-01-01" @default.
- W4312339904 modified "2023-10-16" @default.
- W4312339904 title "Fetal Cortex Segmentation with Topology and Thickness Loss Constraints" @default.
- W4312339904 cites W124643305 @default.
- W4312339904 cites W1901129140 @default.
- W4312339904 cites W1994514622 @default.
- W4312339904 cites W2017745767 @default.
- W4312339904 cites W2024251722 @default.
- W4312339904 cites W2046142779 @default.
- W4312339904 cites W2071391326 @default.
- W4312339904 cites W2082117755 @default.
- W4312339904 cites W2085681975 @default.
- W4312339904 cites W2121236251 @default.
- W4312339904 cites W2144044408 @default.
- W4312339904 cites W2549627956 @default.
- W4312339904 cites W2891916841 @default.
- W4312339904 cites W2911432702 @default.
- W4312339904 cites W2912989244 @default.
- W4312339904 cites W2949461491 @default.
- W4312339904 cites W2953130519 @default.
- W4312339904 cites W3043832855 @default.
- W4312339904 cites W3104164805 @default.
- W4312339904 cites W3115552777 @default.
- W4312339904 cites W3116516133 @default.
- W4312339904 cites W3182781195 @default.
- W4312339904 cites W3183422592 @default.
- W4312339904 cites W3204285923 @default.
- W4312339904 cites W4210368967 @default.
- W4312339904 cites W4233690291 @default.
- W4312339904 doi "https://doi.org/10.1007/978-3-031-23223-7_11" @default.
- W4312339904 hasPublicationYear "2022" @default.
- W4312339904 type Work @default.
- W4312339904 citedByCount "2" @default.
- W4312339904 countsByYear W43123399042023 @default.
- W4312339904 crossrefType "book-chapter" @default.
- W4312339904 hasAuthorship W4312339904A5006461848 @default.
- W4312339904 hasAuthorship W4312339904A5010565192 @default.
- W4312339904 hasAuthorship W4312339904A5030170981 @default.
- W4312339904 hasAuthorship W4312339904A5042654952 @default.
- W4312339904 hasAuthorship W4312339904A5045477945 @default.
- W4312339904 hasAuthorship W4312339904A5049396894 @default.
- W4312339904 hasAuthorship W4312339904A5057304825 @default.
- W4312339904 hasAuthorship W4312339904A5068936425 @default.
- W4312339904 hasAuthorship W4312339904A5071915668 @default.
- W4312339904 hasAuthorship W4312339904A5074707604 @default.
- W4312339904 hasAuthorship W4312339904A5075545668 @default.
- W4312339904 hasAuthorship W4312339904A5078127596 @default.
- W4312339904 hasAuthorship W4312339904A5089189158 @default.
- W4312339904 hasConcept C11413529 @default.
- W4312339904 hasConcept C124504099 @default.
- W4312339904 hasConcept C153180895 @default.
- W4312339904 hasConcept C154945302 @default.
- W4312339904 hasConcept C169760540 @default.
- W4312339904 hasConcept C2776135515 @default.
- W4312339904 hasConcept C2874115 @default.
- W4312339904 hasConcept C3018011982 @default.
- W4312339904 hasConcept C31972630 @default.
- W4312339904 hasConcept C41008148 @default.
- W4312339904 hasConcept C65885262 @default.
- W4312339904 hasConcept C82233179 @default.
- W4312339904 hasConcept C86803240 @default.
- W4312339904 hasConcept C89600930 @default.
- W4312339904 hasConcept C97820695 @default.
- W4312339904 hasConceptScore W4312339904C11413529 @default.
- W4312339904 hasConceptScore W4312339904C124504099 @default.
- W4312339904 hasConceptScore W4312339904C153180895 @default.
- W4312339904 hasConceptScore W4312339904C154945302 @default.
- W4312339904 hasConceptScore W4312339904C169760540 @default.
- W4312339904 hasConceptScore W4312339904C2776135515 @default.
- W4312339904 hasConceptScore W4312339904C2874115 @default.
- W4312339904 hasConceptScore W4312339904C3018011982 @default.
- W4312339904 hasConceptScore W4312339904C31972630 @default.
- W4312339904 hasConceptScore W4312339904C41008148 @default.
- W4312339904 hasConceptScore W4312339904C65885262 @default.
- W4312339904 hasConceptScore W4312339904C82233179 @default.
- W4312339904 hasConceptScore W4312339904C86803240 @default.
- W4312339904 hasConceptScore W4312339904C89600930 @default.
- W4312339904 hasConceptScore W4312339904C97820695 @default.
- W4312339904 hasLocation W43123399041 @default.
- W4312339904 hasOpenAccess W4312339904 @default.
- W4312339904 hasPrimaryLocation W43123399041 @default.
- W4312339904 hasRelatedWork W1507266234 @default.
- W4312339904 hasRelatedWork W1669643531 @default.