Matches in SemOpenAlex for { <https://semopenalex.org/work/W3207168755> ?p ?o ?g. }
Showing items 1 to 85 of
85
with 100 items per page.
- W3207168755 endingPage "102189" @default.
- W3207168755 startingPage "102189" @default.
- W3207168755 abstract "Automated segmentation of three-dimensional medical images is of great importance for the detection and quantification of certain diseases such as stenosis in the coronary arteries. Many 2D and 3D deep learning models, especially deep convolutional neural networks (CNNs), have achieved state-of-the-art segmentation performance on 3D medical images. Yet, there is a trade-off between the field of view and the utilization of inter-slice information when using pure 2D or 3D CNNs for 3D segmentation, which compromises the segmentation accuracy. In this paper, we propose a two-stage strategy that retains the advantages of both 2D and 3D CNNs and apply the method for the segmentation of the human aorta and coronary arteries, with stenosis, from computed tomography (CT) images. In the first stage, a 2D CNN, which can extract large-field-of-view information, is used to segment the aorta and coronary arteries simultaneously in a slice-by-slice fashion. Then, in the second stage, a 3D CNN is applied to extract the inter-slice information to refine the segmentation of the coronary arteries in certain subregions not resolved well in the first stage. We show that the 3D network of the second stage can improve the continuity between slices and reduce the missed detection rate of the 2D CNN. Compared with directly using a 3D CNN, the two-stage approach can alleviate the class imbalance problem caused by the large non-coronary artery (aorta and background) and the small coronary artery and reduce the training time because the vast majority of negative voxels are excluded in the first stage. To validate the efficacy of our method, extensive experiments are carried out to compare with other approaches based on pure 2D or 3D CNNs and those based on hybrid 2D-3D CNNs." @default.
- W3207168755 created "2021-10-25" @default.
- W3207168755 creator A5006367748 @default.
- W3207168755 creator A5066067863 @default.
- W3207168755 date "2021-11-01" @default.
- W3207168755 modified "2023-10-16" @default.
- W3207168755 title "Fusing 2D and 3D convolutional neural networks for the segmentation of aorta and coronary arteries from CT images" @default.
- W3207168755 cites W2153431772 @default.
- W3207168755 cites W2160754664 @default.
- W3207168755 cites W2185291575 @default.
- W3207168755 cites W2301358467 @default.
- W3207168755 cites W2320230300 @default.
- W3207168755 cites W2412782625 @default.
- W3207168755 cites W2508140933 @default.
- W3207168755 cites W2608353599 @default.
- W3207168755 cites W2888570268 @default.
- W3207168755 cites W2903330639 @default.
- W3207168755 cites W2927851116 @default.
- W3207168755 cites W2947263797 @default.
- W3207168755 cites W2986661129 @default.
- W3207168755 cites W2997528981 @default.
- W3207168755 cites W3039706108 @default.
- W3207168755 cites W3111341286 @default.
- W3207168755 cites W3112980510 @default.
- W3207168755 cites W3122226502 @default.
- W3207168755 cites W3145539437 @default.
- W3207168755 cites W3180430380 @default.
- W3207168755 doi "https://doi.org/10.1016/j.artmed.2021.102189" @default.
- W3207168755 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/34763804" @default.
- W3207168755 hasPublicationYear "2021" @default.
- W3207168755 type Work @default.
- W3207168755 sameAs 3207168755 @default.
- W3207168755 citedByCount "10" @default.
- W3207168755 countsByYear W32071687552022 @default.
- W3207168755 countsByYear W32071687552023 @default.
- W3207168755 crossrefType "journal-article" @default.
- W3207168755 hasAuthorship W3207168755A5006367748 @default.
- W3207168755 hasAuthorship W3207168755A5066067863 @default.
- W3207168755 hasConcept C108583219 @default.
- W3207168755 hasConcept C124504099 @default.
- W3207168755 hasConcept C126322002 @default.
- W3207168755 hasConcept C153180895 @default.
- W3207168755 hasConcept C154945302 @default.
- W3207168755 hasConcept C2776820930 @default.
- W3207168755 hasConcept C2778742706 @default.
- W3207168755 hasConcept C2779980429 @default.
- W3207168755 hasConcept C31972630 @default.
- W3207168755 hasConcept C41008148 @default.
- W3207168755 hasConcept C71924100 @default.
- W3207168755 hasConcept C81363708 @default.
- W3207168755 hasConcept C89600930 @default.
- W3207168755 hasConceptScore W3207168755C108583219 @default.
- W3207168755 hasConceptScore W3207168755C124504099 @default.
- W3207168755 hasConceptScore W3207168755C126322002 @default.
- W3207168755 hasConceptScore W3207168755C153180895 @default.
- W3207168755 hasConceptScore W3207168755C154945302 @default.
- W3207168755 hasConceptScore W3207168755C2776820930 @default.
- W3207168755 hasConceptScore W3207168755C2778742706 @default.
- W3207168755 hasConceptScore W3207168755C2779980429 @default.
- W3207168755 hasConceptScore W3207168755C31972630 @default.
- W3207168755 hasConceptScore W3207168755C41008148 @default.
- W3207168755 hasConceptScore W3207168755C71924100 @default.
- W3207168755 hasConceptScore W3207168755C81363708 @default.
- W3207168755 hasConceptScore W3207168755C89600930 @default.
- W3207168755 hasLocation W32071687551 @default.
- W3207168755 hasLocation W32071687552 @default.
- W3207168755 hasOpenAccess W3207168755 @default.
- W3207168755 hasPrimaryLocation W32071687551 @default.
- W3207168755 hasRelatedWork W1988449734 @default.
- W3207168755 hasRelatedWork W2021562513 @default.
- W3207168755 hasRelatedWork W2401216020 @default.
- W3207168755 hasRelatedWork W2412542586 @default.
- W3207168755 hasRelatedWork W2414481425 @default.
- W3207168755 hasRelatedWork W4293226380 @default.
- W3207168755 hasRelatedWork W4313906399 @default.
- W3207168755 hasRelatedWork W4321444604 @default.
- W3207168755 hasRelatedWork W4321487865 @default.
- W3207168755 hasRelatedWork W4383669989 @default.
- W3207168755 hasVolume "121" @default.
- W3207168755 isParatext "false" @default.
- W3207168755 isRetracted "false" @default.
- W3207168755 magId "3207168755" @default.
- W3207168755 workType "article" @default.