Matches in SemOpenAlex for { <https://semopenalex.org/work/W4229032878> ?p ?o ?g. }
Showing items 1 to 100 of
100
with 100 items per page.
- W4229032878 endingPage "108942" @default.
- W4229032878 startingPage "108942" @default.
- W4229032878 abstract "Myocardial pathology segmentation is essential for the diagnosis and treatment of patients suffering from myocardial infarction. In this work, we propose an end-to-end deep learning based segmentation method for automatically delineating the area of left ventricle (LV) myocardial infarct and edema regions. The proposed method uses the 6 layers deep U-Net architecture as the segmentation backbone, which adopts a hierarchical feature representation with symmetrical encoder–decoder paths. Skip connections are added between encoder and decoder paths, to concatenate low-level and high-level information for better feature representation. Moreover, three other modules, direction field module (DFM), channel self-attention module (CAM) and selective kernel module (SKM), have also been implemented for further exploration of performance improvement. The proposed method is tested on the public MyoPS 2020 (myocardial pathology segmentation combining multi-sequence cardiac magnetic resonance) challenge dataset. Compared with extra self-attention module or selective kernel module, plain deep U-Net with curriculum learning achieves better results on testing dataset. Extensive ablation experiments are performed to explore the optimal depth of U-Net, multiple loss functions and different data augmentation methods. Using the official evaluation kit, our solution outperforms state-of-the-art single stage approaches, and achieves comparable performance with other advanced multi-stage methods. The evaluation results demonstrate our method’s effectiveness on myocardial pathology segmentation in multi-sequence cardiac magnetic resonance (CMR) data, and the superiority to the current state-of-the-art single stage methods." @default.
- W4229032878 created "2022-05-08" @default.
- W4229032878 creator A5028235866 @default.
- W4229032878 creator A5034520275 @default.
- W4229032878 creator A5040937623 @default.
- W4229032878 creator A5068555557 @default.
- W4229032878 creator A5073292890 @default.
- W4229032878 date "2022-08-01" @default.
- W4229032878 modified "2023-10-12" @default.
- W4229032878 title "Deep U-Net architecture with curriculum learning for myocardial pathology segmentation in multi-sequence cardiac magnetic resonance images" @default.
- W4229032878 cites W1903029394 @default.
- W4229032878 cites W2525945566 @default.
- W4229032878 cites W2757248724 @default.
- W4229032878 cites W2887276061 @default.
- W4229032878 cites W2898910301 @default.
- W4229032878 cites W2900827846 @default.
- W4229032878 cites W2928133111 @default.
- W4229032878 cites W2955058313 @default.
- W4229032878 cites W2962974533 @default.
- W4229032878 cites W2963890275 @default.
- W4229032878 cites W2995848654 @default.
- W4229032878 cites W3013735888 @default.
- W4229032878 cites W3112701542 @default.
- W4229032878 cites W3129063931 @default.
- W4229032878 cites W3203934147 @default.
- W4229032878 cites W3214613347 @default.
- W4229032878 doi "https://doi.org/10.1016/j.knosys.2022.108942" @default.
- W4229032878 hasPublicationYear "2022" @default.
- W4229032878 type Work @default.
- W4229032878 citedByCount "8" @default.
- W4229032878 countsByYear W42290328782022 @default.
- W4229032878 countsByYear W42290328782023 @default.
- W4229032878 crossrefType "journal-article" @default.
- W4229032878 hasAuthorship W4229032878A5028235866 @default.
- W4229032878 hasAuthorship W4229032878A5034520275 @default.
- W4229032878 hasAuthorship W4229032878A5040937623 @default.
- W4229032878 hasAuthorship W4229032878A5068555557 @default.
- W4229032878 hasAuthorship W4229032878A5073292890 @default.
- W4229032878 hasConcept C108583219 @default.
- W4229032878 hasConcept C123657996 @default.
- W4229032878 hasConcept C126838900 @default.
- W4229032878 hasConcept C14166107 @default.
- W4229032878 hasConcept C142362112 @default.
- W4229032878 hasConcept C143409427 @default.
- W4229032878 hasConcept C153349607 @default.
- W4229032878 hasConcept C154945302 @default.
- W4229032878 hasConcept C15744967 @default.
- W4229032878 hasConcept C19417346 @default.
- W4229032878 hasConcept C2524010 @default.
- W4229032878 hasConcept C2778112365 @default.
- W4229032878 hasConcept C2987145844 @default.
- W4229032878 hasConcept C33923547 @default.
- W4229032878 hasConcept C41008148 @default.
- W4229032878 hasConcept C47177190 @default.
- W4229032878 hasConcept C54355233 @default.
- W4229032878 hasConcept C71924100 @default.
- W4229032878 hasConcept C86803240 @default.
- W4229032878 hasConcept C89600930 @default.
- W4229032878 hasConceptScore W4229032878C108583219 @default.
- W4229032878 hasConceptScore W4229032878C123657996 @default.
- W4229032878 hasConceptScore W4229032878C126838900 @default.
- W4229032878 hasConceptScore W4229032878C14166107 @default.
- W4229032878 hasConceptScore W4229032878C142362112 @default.
- W4229032878 hasConceptScore W4229032878C143409427 @default.
- W4229032878 hasConceptScore W4229032878C153349607 @default.
- W4229032878 hasConceptScore W4229032878C154945302 @default.
- W4229032878 hasConceptScore W4229032878C15744967 @default.
- W4229032878 hasConceptScore W4229032878C19417346 @default.
- W4229032878 hasConceptScore W4229032878C2524010 @default.
- W4229032878 hasConceptScore W4229032878C2778112365 @default.
- W4229032878 hasConceptScore W4229032878C2987145844 @default.
- W4229032878 hasConceptScore W4229032878C33923547 @default.
- W4229032878 hasConceptScore W4229032878C41008148 @default.
- W4229032878 hasConceptScore W4229032878C47177190 @default.
- W4229032878 hasConceptScore W4229032878C54355233 @default.
- W4229032878 hasConceptScore W4229032878C71924100 @default.
- W4229032878 hasConceptScore W4229032878C86803240 @default.
- W4229032878 hasConceptScore W4229032878C89600930 @default.
- W4229032878 hasFunder F4320321001 @default.
- W4229032878 hasFunder F4320328119 @default.
- W4229032878 hasFunder F4320335787 @default.
- W4229032878 hasLocation W42290328781 @default.
- W4229032878 hasOpenAccess W4229032878 @default.
- W4229032878 hasPrimaryLocation W42290328781 @default.
- W4229032878 hasRelatedWork W2790662084 @default.
- W4229032878 hasRelatedWork W2948658236 @default.
- W4229032878 hasRelatedWork W2960184797 @default.
- W4229032878 hasRelatedWork W4200477060 @default.
- W4229032878 hasRelatedWork W4220708658 @default.
- W4229032878 hasRelatedWork W4220855245 @default.
- W4229032878 hasRelatedWork W4243168368 @default.
- W4229032878 hasRelatedWork W4285827401 @default.
- W4229032878 hasRelatedWork W4293211451 @default.
- W4229032878 hasRelatedWork W4295036012 @default.
- W4229032878 hasVolume "249" @default.
- W4229032878 isParatext "false" @default.
- W4229032878 isRetracted "false" @default.
- W4229032878 workType "article" @default.