Matches in SemOpenAlex for { <https://semopenalex.org/work/W4286539715> ?p ?o ?g. }
Showing items 1 to 74 of
74
with 100 items per page.
- W4286539715 endingPage "13" @default.
- W4286539715 startingPage "1" @default.
- W4286539715 abstract "Optical coherence tomography angiography (OCTA) has been widely used in ophthalmology in recent years due to its non-invasive and high resolution. In OCTA images, two biomarkers are extremely important for clinical diagnosis, <i>i.e</i>., foveal avascular zone (FAZ) and retinal vessel (RV), and RV has an implicit constraint on FAZ in position. In previous studies, the segmentation of the two biomarkers is naturally separated, which undoubtedly leads to the omission of such constraints between them. In this paper, we propose a joint segmentation framework (<i>Joint-Seg</i>), a single-encoder and dual-decoder architecture, through which simultaneous FAZ and RV extraction from <i>en-face</i> OCTA images can be achieved. Specifically, the OCTA image is encoded through joint encoding and provides FAZ- or RV-related information to separate decoding branches through a feature adaptive filter. In the FAZ segmentation branch, we propose a feature alignment decoder block (FADB) to recover image details, especially boundaries. While in the RV segmentation branch, a multi-scale soft fusion module (MSFM) is designed to adapt to different vessel thicknesses. Finally, we evaluate the proposed <i>Joint-Seg</i> on the OCTA-500 dataset, the experimental results show that our <i>Joint-Seg</i> outperforms the state-of-the-art methods on both FAZ and RV segmentation and has fewer FLOPs and parameters. The generalization experiments on four other datasets, <i>i.e</i>., OCTAGON, sFAZ, OCTA-25K, and ROSE also demonstrate the portability and scalability of the proposed <i>Joint-Seg</i> framework. In addition, the noise analysis further shows good robustness of the proposed method against noise." @default.
- W4286539715 created "2022-07-22" @default.
- W4286539715 creator A5010870600 @default.
- W4286539715 creator A5023745572 @default.
- W4286539715 creator A5024121467 @default.
- W4286539715 creator A5042291956 @default.
- W4286539715 creator A5078491805 @default.
- W4286539715 date "2022-01-01" @default.
- W4286539715 modified "2023-10-18" @default.
- W4286539715 title "Joint-Seg: Treat Foveal Avascular Zone and Retinal Vessel Segmentation in OCTA Images as a Joint Task" @default.
- W4286539715 doi "https://doi.org/10.1109/tim.2022.3193188" @default.
- W4286539715 hasPublicationYear "2022" @default.
- W4286539715 type Work @default.
- W4286539715 citedByCount "5" @default.
- W4286539715 countsByYear W42865397152023 @default.
- W4286539715 crossrefType "journal-article" @default.
- W4286539715 hasAuthorship W4286539715A5010870600 @default.
- W4286539715 hasAuthorship W4286539715A5023745572 @default.
- W4286539715 hasAuthorship W4286539715A5024121467 @default.
- W4286539715 hasAuthorship W4286539715A5042291956 @default.
- W4286539715 hasAuthorship W4286539715A5078491805 @default.
- W4286539715 hasConcept C118487528 @default.
- W4286539715 hasConcept C127413603 @default.
- W4286539715 hasConcept C138885662 @default.
- W4286539715 hasConcept C153180895 @default.
- W4286539715 hasConcept C154945302 @default.
- W4286539715 hasConcept C170154142 @default.
- W4286539715 hasConcept C18555067 @default.
- W4286539715 hasConcept C2776401178 @default.
- W4286539715 hasConcept C2780827179 @default.
- W4286539715 hasConcept C30181142 @default.
- W4286539715 hasConcept C31972630 @default.
- W4286539715 hasConcept C41008148 @default.
- W4286539715 hasConcept C41895202 @default.
- W4286539715 hasConcept C71924100 @default.
- W4286539715 hasConcept C89600930 @default.
- W4286539715 hasConceptScore W4286539715C118487528 @default.
- W4286539715 hasConceptScore W4286539715C127413603 @default.
- W4286539715 hasConceptScore W4286539715C138885662 @default.
- W4286539715 hasConceptScore W4286539715C153180895 @default.
- W4286539715 hasConceptScore W4286539715C154945302 @default.
- W4286539715 hasConceptScore W4286539715C170154142 @default.
- W4286539715 hasConceptScore W4286539715C18555067 @default.
- W4286539715 hasConceptScore W4286539715C2776401178 @default.
- W4286539715 hasConceptScore W4286539715C2780827179 @default.
- W4286539715 hasConceptScore W4286539715C30181142 @default.
- W4286539715 hasConceptScore W4286539715C31972630 @default.
- W4286539715 hasConceptScore W4286539715C41008148 @default.
- W4286539715 hasConceptScore W4286539715C41895202 @default.
- W4286539715 hasConceptScore W4286539715C71924100 @default.
- W4286539715 hasConceptScore W4286539715C89600930 @default.
- W4286539715 hasFunder F4320318547 @default.
- W4286539715 hasFunder F4320321001 @default.
- W4286539715 hasFunder F4320322843 @default.
- W4286539715 hasFunder F4320322866 @default.
- W4286539715 hasLocation W42865397151 @default.
- W4286539715 hasOpenAccess W4286539715 @default.
- W4286539715 hasPrimaryLocation W42865397151 @default.
- W4286539715 hasRelatedWork W1516923435 @default.
- W4286539715 hasRelatedWork W1669643531 @default.
- W4286539715 hasRelatedWork W2005437358 @default.
- W4286539715 hasRelatedWork W2008656436 @default.
- W4286539715 hasRelatedWork W2039154422 @default.
- W4286539715 hasRelatedWork W2122581818 @default.
- W4286539715 hasRelatedWork W2134924024 @default.
- W4286539715 hasRelatedWork W2517104666 @default.
- W4286539715 hasRelatedWork W79820356 @default.
- W4286539715 hasRelatedWork W2182382398 @default.
- W4286539715 hasVolume "71" @default.
- W4286539715 isParatext "false" @default.
- W4286539715 isRetracted "false" @default.
- W4286539715 workType "article" @default.