Matches in SemOpenAlex for { <https://semopenalex.org/work/W3138329850> ?p ?o ?g. }
Showing items 1 to 96 of
96
with 100 items per page.
- W3138329850 endingPage "2312" @default.
- W3138329850 startingPage "2312" @default.
- W3138329850 abstract "Automated lesion segmentation is one of the important tasks for the quantitative assessment of retinal diseases in SD-OCT images. Recently, deep convolutional neural networks (CNN) have shown promising advancements in the field of automated image segmentation, whereas they always benefit from large-scale datasets with high-quality pixel-wise annotations. Unfortunately, obtaining accurate annotations is expensive in both human effort and finance. In this paper, we propose a weakly supervised two-stage learning architecture to detect and further segment central serous chorioretinopathy (CSC) retinal detachment with only image-level annotations. Specifically, in the first stage, a Located-CNN is designed to detect the location of lesion regions in the whole SD-OCT retinal images, and highlight the distinguishing regions. To generate available a pseudo pixel-level label, the conventional level set method is employed to refine the distinguishing regions. In the second stage, we customize the active-contour loss function in deep networks to achieve the effective segmentation of the lesion area. A challenging dataset is used to evaluate our proposed method, and the results demonstrate that the proposed method consistently outperforms some current models trained with a different level of supervision, and is even as competitive as those relying on stronger supervision. To our best knowledge, we are the first to achieve CSC segmentation in SD-OCT images using weakly supervised learning, which can greatly reduce the labeling efforts." @default.
- W3138329850 created "2021-03-29" @default.
- W3138329850 creator A5001005426 @default.
- W3138329850 creator A5034946941 @default.
- W3138329850 creator A5036479222 @default.
- W3138329850 creator A5070492038 @default.
- W3138329850 creator A5076863688 @default.
- W3138329850 creator A5079884578 @default.
- W3138329850 date "2021-03-24" @default.
- W3138329850 modified "2023-10-17" @default.
- W3138329850 title "Weakly supervised serous retinal detachment segmentation in SD-OCT images by two-stage learning" @default.
- W3138329850 cites W1993893886 @default.
- W3138329850 cites W2008924408 @default.
- W3138329850 cites W2037227137 @default.
- W3138329850 cites W2057600571 @default.
- W3138329850 cites W2057842522 @default.
- W3138329850 cites W2116040950 @default.
- W3138329850 cites W2122333898 @default.
- W3138329850 cites W2133515615 @default.
- W3138329850 cites W2134542952 @default.
- W3138329850 cites W2303778079 @default.
- W3138329850 cites W2319638030 @default.
- W3138329850 cites W2337570847 @default.
- W3138329850 cites W2412782625 @default.
- W3138329850 cites W2473838373 @default.
- W3138329850 cites W2606000143 @default.
- W3138329850 cites W2748604568 @default.
- W3138329850 cites W2753922518 @default.
- W3138329850 cites W2763160469 @default.
- W3138329850 cites W2803790834 @default.
- W3138329850 cites W2810621733 @default.
- W3138329850 cites W2942275886 @default.
- W3138329850 cites W2969265612 @default.
- W3138329850 cites W3014779154 @default.
- W3138329850 doi "https://doi.org/10.1364/boe.416167" @default.
- W3138329850 hasPubMedCentralId "https://www.ncbi.nlm.nih.gov/pmc/articles/8086451" @default.
- W3138329850 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/33996231" @default.
- W3138329850 hasPublicationYear "2021" @default.
- W3138329850 type Work @default.
- W3138329850 sameAs 3138329850 @default.
- W3138329850 citedByCount "6" @default.
- W3138329850 countsByYear W31383298502021 @default.
- W3138329850 countsByYear W31383298502022 @default.
- W3138329850 countsByYear W31383298502023 @default.
- W3138329850 crossrefType "journal-article" @default.
- W3138329850 hasAuthorship W3138329850A5001005426 @default.
- W3138329850 hasAuthorship W3138329850A5034946941 @default.
- W3138329850 hasAuthorship W3138329850A5036479222 @default.
- W3138329850 hasAuthorship W3138329850A5070492038 @default.
- W3138329850 hasAuthorship W3138329850A5076863688 @default.
- W3138329850 hasAuthorship W3138329850A5079884578 @default.
- W3138329850 hasBestOaLocation W31383298501 @default.
- W3138329850 hasConcept C108583219 @default.
- W3138329850 hasConcept C124504099 @default.
- W3138329850 hasConcept C153180895 @default.
- W3138329850 hasConcept C154945302 @default.
- W3138329850 hasConcept C160633673 @default.
- W3138329850 hasConcept C31972630 @default.
- W3138329850 hasConcept C41008148 @default.
- W3138329850 hasConcept C81363708 @default.
- W3138329850 hasConcept C89600930 @default.
- W3138329850 hasConceptScore W3138329850C108583219 @default.
- W3138329850 hasConceptScore W3138329850C124504099 @default.
- W3138329850 hasConceptScore W3138329850C153180895 @default.
- W3138329850 hasConceptScore W3138329850C154945302 @default.
- W3138329850 hasConceptScore W3138329850C160633673 @default.
- W3138329850 hasConceptScore W3138329850C31972630 @default.
- W3138329850 hasConceptScore W3138329850C41008148 @default.
- W3138329850 hasConceptScore W3138329850C81363708 @default.
- W3138329850 hasConceptScore W3138329850C89600930 @default.
- W3138329850 hasFunder F4320321001 @default.
- W3138329850 hasFunder F4320321543 @default.
- W3138329850 hasFunder F4320324174 @default.
- W3138329850 hasFunder F4320333596 @default.
- W3138329850 hasIssue "4" @default.
- W3138329850 hasLocation W31383298501 @default.
- W3138329850 hasLocation W31383298502 @default.
- W3138329850 hasOpenAccess W3138329850 @default.
- W3138329850 hasPrimaryLocation W31383298501 @default.
- W3138329850 hasRelatedWork W1669643531 @default.
- W3138329850 hasRelatedWork W2122581818 @default.
- W3138329850 hasRelatedWork W2738221750 @default.
- W3138329850 hasRelatedWork W2739874619 @default.
- W3138329850 hasRelatedWork W2795329967 @default.
- W3138329850 hasRelatedWork W2948658236 @default.
- W3138329850 hasRelatedWork W3102253946 @default.
- W3138329850 hasRelatedWork W3144574764 @default.
- W3138329850 hasRelatedWork W4226289457 @default.
- W3138329850 hasRelatedWork W4293211451 @default.
- W3138329850 hasVolume "12" @default.
- W3138329850 isParatext "false" @default.
- W3138329850 isRetracted "false" @default.
- W3138329850 magId "3138329850" @default.
- W3138329850 workType "article" @default.