Matches in SemOpenAlex for { <https://semopenalex.org/work/W3120822816> ?p ?o ?g. }
Showing items 1 to 87 of
87
with 100 items per page.
- W3120822816 abstract "Quantification of viable left atrial (LA) tissue is a reliable information which should be used to support therapy selection in atrial fibrillation (AF) patients. Late gadolinium-enhanced magnetic resonance imaging (LGE-MRI) is employed for the non-invasive assessment of LA fibrotic tissue. Unfortunately, the analysis of LGE-MRI relies on manual tracing of LA boundaries. This task is time-consuming and prone to high inter-observer variability. Therefore, an automatic approach for LA wall detection would be very helpful. In this study, we compared the performance of different deep architectures - U-Net and attention U-Net (AttnU-Net) - and different loss functions - Dice loss (DL) and focal Tversky loss (FTL) to automatically detect LA boundaries from LGE-MRI data. In addition, AttnU-Net was trained without deep supervision (DS) and multi-scale inputs (MI), with DS and with DS+MI. No statistically significant differences were found training the networks with DL or FTL. U-Net was the best-performing algorithm overall, outperforming significantly AttnU-Net with a Dice Coefficient of 0.9015±0.0308 (mean ± standard deviation). However, no significant differences were found between U-Net and AttnU-Net DS/DS+MI. Based on these results, using a DL or FTL does not affect the performance and U-Net was the best-performing solution." @default.
- W3120822816 created "2021-01-18" @default.
- W3120822816 creator A5015267765 @default.
- W3120822816 creator A5031714272 @default.
- W3120822816 creator A5058764257 @default.
- W3120822816 creator A5060301654 @default.
- W3120822816 creator A5084926128 @default.
- W3120822816 date "2020-12-30" @default.
- W3120822816 modified "2023-10-16" @default.
- W3120822816 title "Performance Comparison of Deep Learning Approaches for Left Atrium Segmentation from LGE-MRI Data" @default.
- W3120822816 cites W109871117 @default.
- W3120822816 cites W1901129140 @default.
- W3120822816 cites W1921280435 @default.
- W3120822816 cites W1988911499 @default.
- W3120822816 cites W2114775432 @default.
- W3120822816 cites W2150866578 @default.
- W3120822816 cites W2797694788 @default.
- W3120822816 cites W2798122215 @default.
- W3120822816 cites W2906598409 @default.
- W3120822816 cites W2914480338 @default.
- W3120822816 cites W2919115771 @default.
- W3120822816 cites W2962767316 @default.
- W3120822816 cites W3030420691 @default.
- W3120822816 cites W3080508714 @default.
- W3120822816 cites W3087333144 @default.
- W3120822816 cites W3093394156 @default.
- W3120822816 doi "https://doi.org/10.22489/cinc.2020.306" @default.
- W3120822816 hasPublicationYear "2020" @default.
- W3120822816 type Work @default.
- W3120822816 sameAs 3120822816 @default.
- W3120822816 citedByCount "2" @default.
- W3120822816 countsByYear W31208228162021 @default.
- W3120822816 crossrefType "proceedings-article" @default.
- W3120822816 hasAuthorship W3120822816A5015267765 @default.
- W3120822816 hasAuthorship W3120822816A5031714272 @default.
- W3120822816 hasAuthorship W3120822816A5058764257 @default.
- W3120822816 hasAuthorship W3120822816A5060301654 @default.
- W3120822816 hasAuthorship W3120822816A5084926128 @default.
- W3120822816 hasConcept C105795698 @default.
- W3120822816 hasConcept C108583219 @default.
- W3120822816 hasConcept C124504099 @default.
- W3120822816 hasConcept C126838900 @default.
- W3120822816 hasConcept C143409427 @default.
- W3120822816 hasConcept C148524875 @default.
- W3120822816 hasConcept C153180895 @default.
- W3120822816 hasConcept C154945302 @default.
- W3120822816 hasConcept C163892561 @default.
- W3120822816 hasConcept C164705383 @default.
- W3120822816 hasConcept C22029948 @default.
- W3120822816 hasConcept C2779161974 @default.
- W3120822816 hasConcept C33923547 @default.
- W3120822816 hasConcept C41008148 @default.
- W3120822816 hasConcept C71924100 @default.
- W3120822816 hasConcept C89600930 @default.
- W3120822816 hasConceptScore W3120822816C105795698 @default.
- W3120822816 hasConceptScore W3120822816C108583219 @default.
- W3120822816 hasConceptScore W3120822816C124504099 @default.
- W3120822816 hasConceptScore W3120822816C126838900 @default.
- W3120822816 hasConceptScore W3120822816C143409427 @default.
- W3120822816 hasConceptScore W3120822816C148524875 @default.
- W3120822816 hasConceptScore W3120822816C153180895 @default.
- W3120822816 hasConceptScore W3120822816C154945302 @default.
- W3120822816 hasConceptScore W3120822816C163892561 @default.
- W3120822816 hasConceptScore W3120822816C164705383 @default.
- W3120822816 hasConceptScore W3120822816C22029948 @default.
- W3120822816 hasConceptScore W3120822816C2779161974 @default.
- W3120822816 hasConceptScore W3120822816C33923547 @default.
- W3120822816 hasConceptScore W3120822816C41008148 @default.
- W3120822816 hasConceptScore W3120822816C71924100 @default.
- W3120822816 hasConceptScore W3120822816C89600930 @default.
- W3120822816 hasLocation W31208228161 @default.
- W3120822816 hasOpenAccess W3120822816 @default.
- W3120822816 hasPrimaryLocation W31208228161 @default.
- W3120822816 hasRelatedWork W11730785 @default.
- W3120822816 hasRelatedWork W12676508 @default.
- W3120822816 hasRelatedWork W13275467 @default.
- W3120822816 hasRelatedWork W14128562 @default.
- W3120822816 hasRelatedWork W1446482 @default.
- W3120822816 hasRelatedWork W2526871 @default.
- W3120822816 hasRelatedWork W4081029 @default.
- W3120822816 hasRelatedWork W5260568 @default.
- W3120822816 hasRelatedWork W6572092 @default.
- W3120822816 hasRelatedWork W9952751 @default.
- W3120822816 isParatext "false" @default.
- W3120822816 isRetracted "false" @default.
- W3120822816 magId "3120822816" @default.
- W3120822816 workType "article" @default.