Matches in SemOpenAlex for { <https://semopenalex.org/work/W3133516013> ?p ?o ?g. }
- W3133516013 endingPage "2938" @default.
- W3133516013 startingPage "2926" @default.
- W3133516013 abstract "Despite the successes of deep neural networks on many challenging vision tasks, they often fail to generalize to new test domains that are not distributed identically to the training data. The domain adaptation becomes more challenging for cross-modality medical data with a notable domain shift. Given that specific annotated imaging modalities may not be accessible nor complete. Our proposed solution is based on the cross-modality synthesis of medical images to reduce the costly annotation burden by radiologists and bridge the domain gap in radiological images. We present a novel approach for image-to-image translation in medical images, capable of supervised or unsupervised (unpaired image data) setups. Built upon adversarial training, we propose a learnable self-attentive spatial normalization of the deep convolutional generator network's intermediate activations. Unlike previous attention-based image-to-image translation approaches, which are either domain-specific or require distortion of the source domain's structures, we unearth the importance of the auxiliary semantic information to handle the geometric changes and preserve anatomical structures during image translation. We achieve superior results for cross-modality segmentation between unpaired MRI and CT data for multi-modality whole heart and multi-modal brain tumor MRI (T1/T2) datasets compared to the state-of-the-art methods. We also observe encouraging results in cross-modality conversion for paired MRI and CT images on a brain dataset. Furthermore, a detailed analysis of the cross-modality image translation, thorough ablation studies confirm our proposed method's efficacy." @default.
- W3133516013 created "2021-03-15" @default.
- W3133516013 creator A5058274549 @default.
- W3133516013 creator A5067782007 @default.
- W3133516013 creator A5067894953 @default.
- W3133516013 creator A5074768533 @default.
- W3133516013 creator A5085627246 @default.
- W3133516013 date "2021-10-01" @default.
- W3133516013 modified "2023-10-05" @default.
- W3133516013 title "Self-Attentive Spatial Adaptive Normalization for Cross-Modality Domain Adaptation" @default.
- W3133516013 cites W1641498739 @default.
- W3133516013 cites W1882516042 @default.
- W3133516013 cites W1979775925 @default.
- W3133516013 cites W2043626403 @default.
- W3133516013 cites W2082718270 @default.
- W3133516013 cites W2166485554 @default.
- W3133516013 cites W2208340121 @default.
- W3133516013 cites W2331128040 @default.
- W3133516013 cites W2475287302 @default.
- W3133516013 cites W2513595145 @default.
- W3133516013 cites W2584009249 @default.
- W3133516013 cites W2603777577 @default.
- W3133516013 cites W2745006834 @default.
- W3133516013 cites W2753053025 @default.
- W3133516013 cites W2794022343 @default.
- W3133516013 cites W2895281799 @default.
- W3133516013 cites W2904322775 @default.
- W3133516013 cites W2904832356 @default.
- W3133516013 cites W2914057844 @default.
- W3133516013 cites W2962687275 @default.
- W3133516013 cites W2962785568 @default.
- W3133516013 cites W2962793481 @default.
- W3133516013 cites W2962891897 @default.
- W3133516013 cites W2962974533 @default.
- W3133516013 cites W2963073614 @default.
- W3133516013 cites W2963768110 @default.
- W3133516013 cites W2963814095 @default.
- W3133516013 cites W2963999992 @default.
- W3133516013 cites W2979492950 @default.
- W3133516013 cites W2984810221 @default.
- W3133516013 cites W2985368596 @default.
- W3133516013 cites W3006040295 @default.
- W3133516013 cites W3007486523 @default.
- W3133516013 cites W3037260676 @default.
- W3133516013 cites W3101123465 @default.
- W3133516013 cites W944333893 @default.
- W3133516013 doi "https://doi.org/10.1109/tmi.2021.3059265" @default.
- W3133516013 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/33577450" @default.
- W3133516013 hasPublicationYear "2021" @default.
- W3133516013 type Work @default.
- W3133516013 sameAs 3133516013 @default.
- W3133516013 citedByCount "32" @default.
- W3133516013 countsByYear W31335160132021 @default.
- W3133516013 countsByYear W31335160132022 @default.
- W3133516013 countsByYear W31335160132023 @default.
- W3133516013 crossrefType "journal-article" @default.
- W3133516013 hasAuthorship W3133516013A5058274549 @default.
- W3133516013 hasAuthorship W3133516013A5067782007 @default.
- W3133516013 hasAuthorship W3133516013A5067894953 @default.
- W3133516013 hasAuthorship W3133516013A5074768533 @default.
- W3133516013 hasAuthorship W3133516013A5085627246 @default.
- W3133516013 hasBestOaLocation W31335160132 @default.
- W3133516013 hasConcept C104317684 @default.
- W3133516013 hasConcept C105580179 @default.
- W3133516013 hasConcept C108583219 @default.
- W3133516013 hasConcept C115961682 @default.
- W3133516013 hasConcept C116580362 @default.
- W3133516013 hasConcept C136886441 @default.
- W3133516013 hasConcept C144024400 @default.
- W3133516013 hasConcept C149364088 @default.
- W3133516013 hasConcept C153180895 @default.
- W3133516013 hasConcept C154945302 @default.
- W3133516013 hasConcept C185592680 @default.
- W3133516013 hasConcept C19165224 @default.
- W3133516013 hasConcept C2779757391 @default.
- W3133516013 hasConcept C2780226545 @default.
- W3133516013 hasConcept C31601959 @default.
- W3133516013 hasConcept C31972630 @default.
- W3133516013 hasConcept C41008148 @default.
- W3133516013 hasConcept C54170458 @default.
- W3133516013 hasConcept C55493867 @default.
- W3133516013 hasConcept C81363708 @default.
- W3133516013 hasConcept C89600930 @default.
- W3133516013 hasConceptScore W3133516013C104317684 @default.
- W3133516013 hasConceptScore W3133516013C105580179 @default.
- W3133516013 hasConceptScore W3133516013C108583219 @default.
- W3133516013 hasConceptScore W3133516013C115961682 @default.
- W3133516013 hasConceptScore W3133516013C116580362 @default.
- W3133516013 hasConceptScore W3133516013C136886441 @default.
- W3133516013 hasConceptScore W3133516013C144024400 @default.
- W3133516013 hasConceptScore W3133516013C149364088 @default.
- W3133516013 hasConceptScore W3133516013C153180895 @default.
- W3133516013 hasConceptScore W3133516013C154945302 @default.
- W3133516013 hasConceptScore W3133516013C185592680 @default.
- W3133516013 hasConceptScore W3133516013C19165224 @default.
- W3133516013 hasConceptScore W3133516013C2779757391 @default.
- W3133516013 hasConceptScore W3133516013C2780226545 @default.
- W3133516013 hasConceptScore W3133516013C31601959 @default.