Matches in SemOpenAlex for { <https://semopenalex.org/work/W4287637904> ?p ?o ?g. }
Showing items 1 to 62 of
62
with 100 items per page.
- W4287637904 abstract "Semantic segmentation using convolutional neural networks (CNNs) is the state-of-the-art for many medical segmentation tasks including left ventricle (LV) segmentation in cardiac MR images. However, a drawback is that these CNNs lack explicit shape constraints, occasionally resulting in unrealistic segmentations. In this paper, we perform LV and myocardial segmentation by regression of pose and shape parameters derived from a statistical shape model. The integrated shape model regularizes predicted segmentations and guarantees realistic shapes. Furthermore, in contrast to semantic segmentation, it allows direct calculation of regional measures such as myocardial thickness. We enforce robustness of shape and pose prediction by simultaneously constructing a segmentation distance map during training. We evaluated the proposed method in a fivefold cross validation on a in-house clinical dataset with 75 subjects containing a total of 1539 delineated short-axis slices covering LV from apex to base, and achieved a correlation of 99% for LV area, 94% for myocardial area, 98% for LV dimensions and 88% for regional wall thicknesses. The method was additionally validated on the LVQuan18 and LVQuan19 public datasets and achieved state-of-the-art results." @default.
- W4287637904 created "2022-07-25" @default.
- W4287637904 creator A5035651557 @default.
- W4287637904 creator A5035825547 @default.
- W4287637904 creator A5049273464 @default.
- W4287637904 creator A5068755769 @default.
- W4287637904 creator A5072028836 @default.
- W4287637904 date "2020-10-18" @default.
- W4287637904 modified "2023-09-29" @default.
- W4287637904 title "Shape Constrained CNN for Cardiac MR Segmentation with Simultaneous Prediction of Shape and Pose Parameters" @default.
- W4287637904 doi "https://doi.org/10.48550/arxiv.2010.08952" @default.
- W4287637904 hasPublicationYear "2020" @default.
- W4287637904 type Work @default.
- W4287637904 citedByCount "0" @default.
- W4287637904 crossrefType "posted-content" @default.
- W4287637904 hasAuthorship W4287637904A5035651557 @default.
- W4287637904 hasAuthorship W4287637904A5035825547 @default.
- W4287637904 hasAuthorship W4287637904A5049273464 @default.
- W4287637904 hasAuthorship W4287637904A5068755769 @default.
- W4287637904 hasAuthorship W4287637904A5072028836 @default.
- W4287637904 hasConcept C104317684 @default.
- W4287637904 hasConcept C153180895 @default.
- W4287637904 hasConcept C154945302 @default.
- W4287637904 hasConcept C164705383 @default.
- W4287637904 hasConcept C185592680 @default.
- W4287637904 hasConcept C2778921608 @default.
- W4287637904 hasConcept C31972630 @default.
- W4287637904 hasConcept C41008148 @default.
- W4287637904 hasConcept C55493867 @default.
- W4287637904 hasConcept C63479239 @default.
- W4287637904 hasConcept C71924100 @default.
- W4287637904 hasConcept C81363708 @default.
- W4287637904 hasConcept C89600930 @default.
- W4287637904 hasConceptScore W4287637904C104317684 @default.
- W4287637904 hasConceptScore W4287637904C153180895 @default.
- W4287637904 hasConceptScore W4287637904C154945302 @default.
- W4287637904 hasConceptScore W4287637904C164705383 @default.
- W4287637904 hasConceptScore W4287637904C185592680 @default.
- W4287637904 hasConceptScore W4287637904C2778921608 @default.
- W4287637904 hasConceptScore W4287637904C31972630 @default.
- W4287637904 hasConceptScore W4287637904C41008148 @default.
- W4287637904 hasConceptScore W4287637904C55493867 @default.
- W4287637904 hasConceptScore W4287637904C63479239 @default.
- W4287637904 hasConceptScore W4287637904C71924100 @default.
- W4287637904 hasConceptScore W4287637904C81363708 @default.
- W4287637904 hasConceptScore W4287637904C89600930 @default.
- W4287637904 hasLocation W42876379041 @default.
- W4287637904 hasOpenAccess W4287637904 @default.
- W4287637904 hasPrimaryLocation W42876379041 @default.
- W4287637904 hasRelatedWork W1230437 @default.
- W4287637904 hasRelatedWork W13520748 @default.
- W4287637904 hasRelatedWork W14612285 @default.
- W4287637904 hasRelatedWork W14869171 @default.
- W4287637904 hasRelatedWork W2777938 @default.
- W4287637904 hasRelatedWork W3220901 @default.
- W4287637904 hasRelatedWork W4567138 @default.
- W4287637904 hasRelatedWork W7331946 @default.
- W4287637904 hasRelatedWork W8813607 @default.
- W4287637904 hasRelatedWork W9928955 @default.
- W4287637904 isParatext "false" @default.
- W4287637904 isRetracted "false" @default.
- W4287637904 workType "article" @default.