Matches in SemOpenAlex for { <https://semopenalex.org/work/W4313889562> ?p ?o ?g. }
- W4313889562 endingPage "690" @default.
- W4313889562 startingPage "690" @default.
- W4313889562 abstract "Accurate segmentation of the left atrial structure using magnetic resonance images provides an important basis for the diagnosis of atrial fibrillation (AF) and its treatment using robotic surgery. In this study, an image segmentation method based on sequence relationship learning and multi-scale feature fusion is proposed for 3D to 2D sequence conversion in cardiac magnetic resonance images and the varying scales of left atrial structures within different slices. Firstly, a convolutional neural network layer with an attention module was designed to extract and fuse contextual information at different scales in the image, to strengthen the target features using the correlation between features in different regions within the image, and to improve the network’s ability to distinguish the left atrial structure. Secondly, a recurrent neural network layer oriented to two-dimensional images was designed to capture the correlation of left atrial structures in adjacent slices by simulating the continuous relationship between sequential image slices. Finally, a combined loss function was constructed to reduce the effect of positive and negative sample imbalance and improve model stability. The Dice, IoU, and Hausdorff distance values reached 90.73%, 89.37%, and 4.803 mm, respectively, based on the LASC2013 (left atrial segmentation challenge in 2013) dataset; the corresponding values reached 92.05%, 89.41% and 9.056 mm, respectively, based on the ASC2018 (atrial segmentation challenge at 2018) dataset." @default.
- W4313889562 created "2023-01-10" @default.
- W4313889562 creator A5039745146 @default.
- W4313889562 creator A5040733611 @default.
- W4313889562 creator A5056025791 @default.
- W4313889562 creator A5067777950 @default.
- W4313889562 creator A5086136006 @default.
- W4313889562 date "2023-01-07" @default.
- W4313889562 modified "2023-10-07" @default.
- W4313889562 title "Cardiac Magnetic Resonance Image Segmentation Method Based on Multi-Scale Feature Fusion and Sequence Relationship Learning" @default.
- W4313889562 cites W1903029394 @default.
- W4313889562 cites W2046289434 @default.
- W4313889562 cites W2157331557 @default.
- W4313889562 cites W2160754664 @default.
- W4313889562 cites W2194775991 @default.
- W4313889562 cites W2464708700 @default.
- W4313889562 cites W2560023338 @default.
- W4313889562 cites W2734349601 @default.
- W4313889562 cites W2889158831 @default.
- W4313889562 cites W2955058313 @default.
- W4313889562 cites W2963351448 @default.
- W4313889562 cites W3034410199 @default.
- W4313889562 cites W3035496790 @default.
- W4313889562 cites W3093394156 @default.
- W4313889562 cites W3124370379 @default.
- W4313889562 cites W3145782339 @default.
- W4313889562 cites W3202544408 @default.
- W4313889562 cites W3202799979 @default.
- W4313889562 cites W3214613347 @default.
- W4313889562 cites W4206602097 @default.
- W4313889562 cites W4220812427 @default.
- W4313889562 cites W4221046079 @default.
- W4313889562 cites W4224213587 @default.
- W4313889562 cites W4225323878 @default.
- W4313889562 cites W4280513226 @default.
- W4313889562 cites W4281731138 @default.
- W4313889562 cites W4285040393 @default.
- W4313889562 cites W4290755973 @default.
- W4313889562 cites W4293546472 @default.
- W4313889562 cites W4296351008 @default.
- W4313889562 cites W4303418880 @default.
- W4313889562 doi "https://doi.org/10.3390/s23020690" @default.
- W4313889562 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/36679487" @default.
- W4313889562 hasPublicationYear "2023" @default.
- W4313889562 type Work @default.
- W4313889562 citedByCount "2" @default.
- W4313889562 countsByYear W43138895622023 @default.
- W4313889562 crossrefType "journal-article" @default.
- W4313889562 hasAuthorship W4313889562A5039745146 @default.
- W4313889562 hasAuthorship W4313889562A5040733611 @default.
- W4313889562 hasAuthorship W4313889562A5056025791 @default.
- W4313889562 hasAuthorship W4313889562A5067777950 @default.
- W4313889562 hasAuthorship W4313889562A5086136006 @default.
- W4313889562 hasBestOaLocation W43138895621 @default.
- W4313889562 hasConcept C103278499 @default.
- W4313889562 hasConcept C108583219 @default.
- W4313889562 hasConcept C115961682 @default.
- W4313889562 hasConcept C124504099 @default.
- W4313889562 hasConcept C126838900 @default.
- W4313889562 hasConcept C138885662 @default.
- W4313889562 hasConcept C141898687 @default.
- W4313889562 hasConcept C143409427 @default.
- W4313889562 hasConcept C153180895 @default.
- W4313889562 hasConcept C154945302 @default.
- W4313889562 hasConcept C2776401178 @default.
- W4313889562 hasConcept C31972630 @default.
- W4313889562 hasConcept C41008148 @default.
- W4313889562 hasConcept C41895202 @default.
- W4313889562 hasConcept C50644808 @default.
- W4313889562 hasConcept C69744172 @default.
- W4313889562 hasConcept C71924100 @default.
- W4313889562 hasConcept C81363708 @default.
- W4313889562 hasConcept C89600930 @default.
- W4313889562 hasConceptScore W4313889562C103278499 @default.
- W4313889562 hasConceptScore W4313889562C108583219 @default.
- W4313889562 hasConceptScore W4313889562C115961682 @default.
- W4313889562 hasConceptScore W4313889562C124504099 @default.
- W4313889562 hasConceptScore W4313889562C126838900 @default.
- W4313889562 hasConceptScore W4313889562C138885662 @default.
- W4313889562 hasConceptScore W4313889562C141898687 @default.
- W4313889562 hasConceptScore W4313889562C143409427 @default.
- W4313889562 hasConceptScore W4313889562C153180895 @default.
- W4313889562 hasConceptScore W4313889562C154945302 @default.
- W4313889562 hasConceptScore W4313889562C2776401178 @default.
- W4313889562 hasConceptScore W4313889562C31972630 @default.
- W4313889562 hasConceptScore W4313889562C41008148 @default.
- W4313889562 hasConceptScore W4313889562C41895202 @default.
- W4313889562 hasConceptScore W4313889562C50644808 @default.
- W4313889562 hasConceptScore W4313889562C69744172 @default.
- W4313889562 hasConceptScore W4313889562C71924100 @default.
- W4313889562 hasConceptScore W4313889562C81363708 @default.
- W4313889562 hasConceptScore W4313889562C89600930 @default.
- W4313889562 hasIssue "2" @default.
- W4313889562 hasLocation W43138895621 @default.
- W4313889562 hasLocation W43138895622 @default.
- W4313889562 hasLocation W43138895623 @default.
- W4313889562 hasLocation W43138895624 @default.
- W4313889562 hasOpenAccess W4313889562 @default.