Matches in SemOpenAlex for { <https://semopenalex.org/work/W4321366769> ?p ?o ?g. }
- W4321366769 endingPage "493" @default.
- W4321366769 startingPage "483" @default.
- W4321366769 abstract "Ischemic stroke is an acute cerebral vascular disease and makes up about 80% of all stroke cases. Noncontrast computed tomography (NCCT) is a widely applied imaging technique for ischemic stroke assessment. However, it is challenging to identify ischemic lesion on NCCT images due to its high variability in location, contrast, and geometry. In this work, we propose IS-Net, an encoder–decoder convolutional neural network for automatic ischemic stroke lesion segmentation on NCCT images. The proposed IS-Net takes a hierarchical network as backbone while the pyramid feature aggregation (PFA) module is designed to aggregate features from multistages of backbone, and reasonable feature fusion strategy is considered in PFA to enhance multilevel propagation. To fully mine the boundary cues, the edge constraint scheme is introduced by deep supervision which broadcasts low-level features to different modules. In addition, to overcome the limitation of fixed geometric structure of convolution for multirange dependency exploitation, a nonlocal parallel decoder is introduced with deformable convolution and self-attention. The proposed IS-Net is evaluated on manually labeled follow-up NCCT dataset composed of 1004 cases (totally 9020 images). The proposed IS-Net is compared with the state-of-the-art segmentation models and illustrates the highest score on segmentation criteria and sensitivity." @default.
- W4321366769 created "2023-02-21" @default.
- W4321366769 creator A5007066234 @default.
- W4321366769 creator A5021113880 @default.
- W4321366769 creator A5021809579 @default.
- W4321366769 creator A5037910108 @default.
- W4321366769 creator A5070357433 @default.
- W4321366769 creator A5070952629 @default.
- W4321366769 creator A5088230949 @default.
- W4321366769 date "2023-05-01" @default.
- W4321366769 modified "2023-10-14" @default.
- W4321366769 title "IS-Net: Automatic Ischemic Stroke Lesion Segmentation on CT Images" @default.
- W4321366769 cites W1909740415 @default.
- W4321366769 cites W2079934729 @default.
- W4321366769 cites W2097805840 @default.
- W4321366769 cites W2117539524 @default.
- W4321366769 cites W2145023731 @default.
- W4321366769 cites W2194775991 @default.
- W4321366769 cites W2498042080 @default.
- W4321366769 cites W2509609015 @default.
- W4321366769 cites W2560023338 @default.
- W4321366769 cites W2565639579 @default.
- W4321366769 cites W2592929672 @default.
- W4321366769 cites W2601564443 @default.
- W4321366769 cites W2800836803 @default.
- W4321366769 cites W2928165649 @default.
- W4321366769 cites W2941578761 @default.
- W4321366769 cites W2962914239 @default.
- W4321366769 cites W2963091558 @default.
- W4321366769 cites W2963150697 @default.
- W4321366769 cites W2963361270 @default.
- W4321366769 cites W2963803174 @default.
- W4321366769 cites W2963881378 @default.
- W4321366769 cites W2966926453 @default.
- W4321366769 cites W2990030464 @default.
- W4321366769 cites W2996290406 @default.
- W4321366769 cites W3027763298 @default.
- W4321366769 cites W3040090744 @default.
- W4321366769 cites W3049161665 @default.
- W4321366769 cites W3090878720 @default.
- W4321366769 cites W3096604384 @default.
- W4321366769 cites W3103010481 @default.
- W4321366769 cites W3110440461 @default.
- W4321366769 cites W3138516171 @default.
- W4321366769 doi "https://doi.org/10.1109/trpms.2023.3246496" @default.
- W4321366769 hasPublicationYear "2023" @default.
- W4321366769 type Work @default.
- W4321366769 citedByCount "1" @default.
- W4321366769 countsByYear W43213667692023 @default.
- W4321366769 crossrefType "journal-article" @default.
- W4321366769 hasAuthorship W4321366769A5007066234 @default.
- W4321366769 hasAuthorship W4321366769A5021113880 @default.
- W4321366769 hasAuthorship W4321366769A5021809579 @default.
- W4321366769 hasAuthorship W4321366769A5037910108 @default.
- W4321366769 hasAuthorship W4321366769A5070357433 @default.
- W4321366769 hasAuthorship W4321366769A5070952629 @default.
- W4321366769 hasAuthorship W4321366769A5088230949 @default.
- W4321366769 hasConcept C138885662 @default.
- W4321366769 hasConcept C142575187 @default.
- W4321366769 hasConcept C153180895 @default.
- W4321366769 hasConcept C154945302 @default.
- W4321366769 hasConcept C2524010 @default.
- W4321366769 hasConcept C2776401178 @default.
- W4321366769 hasConcept C31972630 @default.
- W4321366769 hasConcept C33923547 @default.
- W4321366769 hasConcept C41008148 @default.
- W4321366769 hasConcept C41895202 @default.
- W4321366769 hasConcept C45347329 @default.
- W4321366769 hasConcept C50644808 @default.
- W4321366769 hasConcept C81363708 @default.
- W4321366769 hasConcept C89600930 @default.
- W4321366769 hasConceptScore W4321366769C138885662 @default.
- W4321366769 hasConceptScore W4321366769C142575187 @default.
- W4321366769 hasConceptScore W4321366769C153180895 @default.
- W4321366769 hasConceptScore W4321366769C154945302 @default.
- W4321366769 hasConceptScore W4321366769C2524010 @default.
- W4321366769 hasConceptScore W4321366769C2776401178 @default.
- W4321366769 hasConceptScore W4321366769C31972630 @default.
- W4321366769 hasConceptScore W4321366769C33923547 @default.
- W4321366769 hasConceptScore W4321366769C41008148 @default.
- W4321366769 hasConceptScore W4321366769C41895202 @default.
- W4321366769 hasConceptScore W4321366769C45347329 @default.
- W4321366769 hasConceptScore W4321366769C50644808 @default.
- W4321366769 hasConceptScore W4321366769C81363708 @default.
- W4321366769 hasConceptScore W4321366769C89600930 @default.
- W4321366769 hasFunder F4320321001 @default.
- W4321366769 hasFunder F4320325911 @default.
- W4321366769 hasIssue "5" @default.
- W4321366769 hasLocation W43213667691 @default.
- W4321366769 hasOpenAccess W4321366769 @default.
- W4321366769 hasPrimaryLocation W43213667691 @default.
- W4321366769 hasRelatedWork W1669643531 @default.
- W4321366769 hasRelatedWork W1982826852 @default.
- W4321366769 hasRelatedWork W2005437358 @default.
- W4321366769 hasRelatedWork W2008656436 @default.
- W4321366769 hasRelatedWork W2023558673 @default.
- W4321366769 hasRelatedWork W2110230079 @default.
- W4321366769 hasRelatedWork W2134924024 @default.