Matches in SemOpenAlex for { <https://semopenalex.org/work/W4280611096> ?p ?o ?g. }
Showing items 1 to 80 of
80
with 100 items per page.
- W4280611096 endingPage "106887" @default.
- W4280611096 startingPage "106887" @default.
- W4280611096 abstract "Deep learning abdominal multi-organ segmentation provides preoperative guidance for abdominal surgery. However, due to the large volume of 3D CT sequences, the existing methods cannot balance complete semantic features and high-resolution detail information, which leads to uncertain, rough, and inaccurate segmentation, especially in small and irregular organs. In this paper, we propose a two-stage algorithm named multi-dimensional cascaded net (MDCNet) to solve the above problems and segment multi-organs in CT images, including the spleen, kidney, gallbladder, esophagus, liver, stomach, pancreas, and duodenum.MDCNet combines the powerful semantic encoder ability of a 3D net and the rich high-resolution information of a 2.5D net. In stage1, a prior-guided shallow-layer-enhanced 3D location net extracts entire semantic features from a downsampled CT volume to perform rough segmentation. Additionally, we use circular inference and parameter Dice loss to alleviate uncertain boundary. The inputs of stage2 are high-resolution slices, which are obtained by the original image and coarse segmentation of stage1. Stage2 offsets the details lost during downsampling, resulting in smooth and accurate refined contours. The 2.5D net from the axial, coronal, and sagittal views also compensates for the missing spatial information of a single view.The experiments on the two datasets both obtained the best performance, particularly a higher Dice on small gallbladders and irregular duodenums, which reached 0.85±0.12 and 0.77±0.07 respectively, increasing by 0.02 and 0.03 compared to the state-of-the-art method.Our method can extract all semantic and high-resolution detail information from a large-volume CT image. It reduces the boundary uncertainty while yielding smoother segmentation edges, indicating good clinical application prospects." @default.
- W4280611096 created "2022-05-22" @default.
- W4280611096 creator A5015277614 @default.
- W4280611096 creator A5026108830 @default.
- W4280611096 creator A5064803348 @default.
- W4280611096 creator A5065418938 @default.
- W4280611096 creator A5072362034 @default.
- W4280611096 date "2022-06-01" @default.
- W4280611096 modified "2023-10-17" @default.
- W4280611096 title "Multi-Dimensional Cascaded Net with Uncertain Probability Reduction for Abdominal Multi-Organ Segmentation in CT Sequences" @default.
- W4280611096 cites W2790662084 @default.
- W4280611096 cites W2791680898 @default.
- W4280611096 cites W2792124446 @default.
- W4280611096 cites W2963908753 @default.
- W4280611096 cites W2975354219 @default.
- W4280611096 cites W2986785750 @default.
- W4280611096 cites W3005188470 @default.
- W4280611096 cites W3008652188 @default.
- W4280611096 cites W3027531156 @default.
- W4280611096 cites W3040717749 @default.
- W4280611096 cites W3112701542 @default.
- W4280611096 cites W3200501385 @default.
- W4280611096 cites W3209179387 @default.
- W4280611096 cites W3216078403 @default.
- W4280611096 doi "https://doi.org/10.1016/j.cmpb.2022.106887" @default.
- W4280611096 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/35597204" @default.
- W4280611096 hasPublicationYear "2022" @default.
- W4280611096 type Work @default.
- W4280611096 citedByCount "2" @default.
- W4280611096 countsByYear W42806110962023 @default.
- W4280611096 crossrefType "journal-article" @default.
- W4280611096 hasAuthorship W4280611096A5015277614 @default.
- W4280611096 hasAuthorship W4280611096A5026108830 @default.
- W4280611096 hasAuthorship W4280611096A5064803348 @default.
- W4280611096 hasAuthorship W4280611096A5065418938 @default.
- W4280611096 hasAuthorship W4280611096A5072362034 @default.
- W4280611096 hasConcept C110384440 @default.
- W4280611096 hasConcept C115961682 @default.
- W4280611096 hasConcept C153180895 @default.
- W4280611096 hasConcept C154945302 @default.
- W4280611096 hasConcept C22029948 @default.
- W4280611096 hasConcept C2524010 @default.
- W4280611096 hasConcept C2776214188 @default.
- W4280611096 hasConcept C31972630 @default.
- W4280611096 hasConcept C33923547 @default.
- W4280611096 hasConcept C41008148 @default.
- W4280611096 hasConcept C89600930 @default.
- W4280611096 hasConceptScore W4280611096C110384440 @default.
- W4280611096 hasConceptScore W4280611096C115961682 @default.
- W4280611096 hasConceptScore W4280611096C153180895 @default.
- W4280611096 hasConceptScore W4280611096C154945302 @default.
- W4280611096 hasConceptScore W4280611096C22029948 @default.
- W4280611096 hasConceptScore W4280611096C2524010 @default.
- W4280611096 hasConceptScore W4280611096C2776214188 @default.
- W4280611096 hasConceptScore W4280611096C31972630 @default.
- W4280611096 hasConceptScore W4280611096C33923547 @default.
- W4280611096 hasConceptScore W4280611096C41008148 @default.
- W4280611096 hasConceptScore W4280611096C89600930 @default.
- W4280611096 hasFunder F4320321001 @default.
- W4280611096 hasFunder F4320321885 @default.
- W4280611096 hasLocation W42806110961 @default.
- W4280611096 hasLocation W42806110962 @default.
- W4280611096 hasOpenAccess W4280611096 @default.
- W4280611096 hasPrimaryLocation W42806110961 @default.
- W4280611096 hasRelatedWork W2009559548 @default.
- W4280611096 hasRelatedWork W2016385589 @default.
- W4280611096 hasRelatedWork W2385445039 @default.
- W4280611096 hasRelatedWork W2390936256 @default.
- W4280611096 hasRelatedWork W2475857072 @default.
- W4280611096 hasRelatedWork W2483429559 @default.
- W4280611096 hasRelatedWork W2906397153 @default.
- W4280611096 hasRelatedWork W3021239166 @default.
- W4280611096 hasRelatedWork W3104750253 @default.
- W4280611096 hasRelatedWork W4366341510 @default.
- W4280611096 hasVolume "221" @default.
- W4280611096 isParatext "false" @default.
- W4280611096 isRetracted "false" @default.
- W4280611096 workType "article" @default.