Matches in SemOpenAlex for { <https://semopenalex.org/work/W4205087751> ?p ?o ?g. }
- W4205087751 endingPage "1559" @default.
- W4205087751 startingPage "1547" @default.
- W4205087751 abstract "The segmentation of pathological fluid lesions in optical coherence tomography (OCT), including intraretinal fluid, subretinal fluid, and pigment epithelial detachment, is of great importance for the diagnosis and treatment of various eye diseases such as neovascular age-related macular degeneration and diabetic macular edema. Although significant progress has been achieved with the rapid development of fully convolutional neural networks (FCN) in recent years, some important issues remain unsolved. First, pathological fluid lesions in OCT show large variations in location, size, and shape, imposing challenges on the design of FCN architecture. Second, fluid lesions should be continuous regions without holes inside. But the current architectures lack the capability to preserve the shape prior information. In this study, we introduce an FCN architecture for the simultaneous segmentation of three types of pathological fluid lesions in OCT. First, attention gate and spatial pyramid pooling modules are employed to improve the ability of the network to extract multi-scale objects. Then, we introduce a novel curvature regularization term in the loss function to incorporate shape prior information. The proposed method was extensively evaluated on public and clinical datasets with significantly improved performance compared with the state-of-the-art methods." @default.
- W4205087751 created "2022-01-25" @default.
- W4205087751 creator A5018846377 @default.
- W4205087751 creator A5018872953 @default.
- W4205087751 creator A5033831630 @default.
- W4205087751 creator A5037989560 @default.
- W4205087751 creator A5071166150 @default.
- W4205087751 creator A5083371477 @default.
- W4205087751 creator A5083784734 @default.
- W4205087751 creator A5090254049 @default.
- W4205087751 date "2022-06-01" @default.
- W4205087751 modified "2023-10-11" @default.
- W4205087751 title "Multi-Scale Pathological Fluid Segmentation in OCT With a Novel Curvature Loss in Convolutional Neural Network" @default.
- W4205087751 cites W1990889412 @default.
- W4205087751 cites W2074598933 @default.
- W4205087751 cites W2337570847 @default.
- W4205087751 cites W2560023338 @default.
- W4205087751 cites W2580772840 @default.
- W4205087751 cites W2606000143 @default.
- W4205087751 cites W2606534623 @default.
- W4205087751 cites W2737714978 @default.
- W4205087751 cites W2742087205 @default.
- W4205087751 cites W2753708825 @default.
- W4205087751 cites W2753922518 @default.
- W4205087751 cites W2761273289 @default.
- W4205087751 cites W2772059204 @default.
- W4205087751 cites W2792141483 @default.
- W4205087751 cites W2792836735 @default.
- W4205087751 cites W2884436604 @default.
- W4205087751 cites W2885262262 @default.
- W4205087751 cites W2886281300 @default.
- W4205087751 cites W2907100905 @default.
- W4205087751 cites W2917393555 @default.
- W4205087751 cites W2919070891 @default.
- W4205087751 cites W2942275886 @default.
- W4205087751 cites W2953122916 @default.
- W4205087751 cites W2962053516 @default.
- W4205087751 cites W2962731543 @default.
- W4205087751 cites W2962767316 @default.
- W4205087751 cites W2964065611 @default.
- W4205087751 cites W2966434031 @default.
- W4205087751 cites W2979814206 @default.
- W4205087751 cites W3013227159 @default.
- W4205087751 cites W3029869524 @default.
- W4205087751 cites W3039402890 @default.
- W4205087751 cites W3102564565 @default.
- W4205087751 cites W3138329850 @default.
- W4205087751 cites W4211020962 @default.
- W4205087751 doi "https://doi.org/10.1109/tmi.2022.3142048" @default.
- W4205087751 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/35015634" @default.
- W4205087751 hasPublicationYear "2022" @default.
- W4205087751 type Work @default.
- W4205087751 citedByCount "11" @default.
- W4205087751 countsByYear W42050877512022 @default.
- W4205087751 countsByYear W42050877512023 @default.
- W4205087751 crossrefType "journal-article" @default.
- W4205087751 hasAuthorship W4205087751A5018846377 @default.
- W4205087751 hasAuthorship W4205087751A5018872953 @default.
- W4205087751 hasAuthorship W4205087751A5033831630 @default.
- W4205087751 hasAuthorship W4205087751A5037989560 @default.
- W4205087751 hasAuthorship W4205087751A5071166150 @default.
- W4205087751 hasAuthorship W4205087751A5083371477 @default.
- W4205087751 hasAuthorship W4205087751A5083784734 @default.
- W4205087751 hasAuthorship W4205087751A5090254049 @default.
- W4205087751 hasConcept C108583219 @default.
- W4205087751 hasConcept C118487528 @default.
- W4205087751 hasConcept C153180895 @default.
- W4205087751 hasConcept C154945302 @default.
- W4205087751 hasConcept C195065555 @default.
- W4205087751 hasConcept C2524010 @default.
- W4205087751 hasConcept C2778818243 @default.
- W4205087751 hasConcept C31972630 @default.
- W4205087751 hasConcept C33923547 @default.
- W4205087751 hasConcept C41008148 @default.
- W4205087751 hasConcept C70437156 @default.
- W4205087751 hasConcept C71924100 @default.
- W4205087751 hasConcept C81363708 @default.
- W4205087751 hasConcept C89600930 @default.
- W4205087751 hasConceptScore W4205087751C108583219 @default.
- W4205087751 hasConceptScore W4205087751C118487528 @default.
- W4205087751 hasConceptScore W4205087751C153180895 @default.
- W4205087751 hasConceptScore W4205087751C154945302 @default.
- W4205087751 hasConceptScore W4205087751C195065555 @default.
- W4205087751 hasConceptScore W4205087751C2524010 @default.
- W4205087751 hasConceptScore W4205087751C2778818243 @default.
- W4205087751 hasConceptScore W4205087751C31972630 @default.
- W4205087751 hasConceptScore W4205087751C33923547 @default.
- W4205087751 hasConceptScore W4205087751C41008148 @default.
- W4205087751 hasConceptScore W4205087751C70437156 @default.
- W4205087751 hasConceptScore W4205087751C71924100 @default.
- W4205087751 hasConceptScore W4205087751C81363708 @default.
- W4205087751 hasConceptScore W4205087751C89600930 @default.
- W4205087751 hasIssue "6" @default.
- W4205087751 hasLocation W42050877511 @default.
- W4205087751 hasLocation W42050877512 @default.
- W4205087751 hasOpenAccess W4205087751 @default.
- W4205087751 hasPrimaryLocation W42050877511 @default.
- W4205087751 hasRelatedWork W2005437358 @default.