FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4220820843> ?p ?o ?g. }

• W4220820843 endingPage "5311" @default.
• W4220820843 startingPage "5293" @default.
• W4220820843 abstract "Diabetic retinopathy is the leading cause of vision loss in working-age adults. Early screening and diagnosis can help to facilitate subsequent treatment and prevent vision loss. Deep learning has been applied in various fields of medical identification. However, current deep learning-based lesion segmentation techniques rely on a large amount of pixel-level labeled ground truth data, which limits their performance and application. In this work, we present a weakly supervised deep learning framework for eye fundus lesion segmentation in patients with diabetic retinopathy.First, an efficient segmentation algorithm based on grayscale and morphological features is proposed for rapid coarse segmentation of lesions. Then, a deep learning model named Residual-Attention Unet (RAUNet) is proposed for eye fundus lesion segmentation. Finally, a data sample of fundus images with labeled lesions and unlabeled images with coarse segmentation results is jointly used to train RAUNet to broaden the diversity of lesion samples and increase the robustness of the segmentation model.A dataset containing 582 fundus images with labels verified by doctors, including hemorrhage (HE), microaneurysm (MA), hard exudate (EX) and soft exudate (SE), and 903 images without labels was used to evaluate the model. In ablation test, the proposed RAUNet achieved the highest intersection over union (IOU) on the labeled dataset, and the proposed attention and residual modules both improved the IOU of the UNet benchmark. Using both the images labeled by doctors and the proposed coarse segmentation method, the weakly supervised framework based on RAUNet architecture significantly improved the mean segmentation accuracy by over 7% on the lesions.This study demonstrates that combining unlabeled medical images with coarse segmentation results can effectively improve the robustness of the lesion segmentation model and proposes a practical framework for improving the performance of medical image segmentation given limited labeled data samples." @default.
• W4220820843 created "2022-04-03" @default.
• W4220820843 creator A5018073672 @default.
• W4220820843 creator A5024839012 @default.
• W4220820843 creator A5034961228 @default.
• W4220820843 creator A5043136166 @default.
• W4220820843 creator A5070141978 @default.
• W4220820843 creator A5076476272 @default.
• W4220820843 date "2022-01-01" @default.
• W4220820843 modified "2023-09-30" @default.
• W4220820843 title "Weakly supervised training for eye fundus lesion segmentation in patients with diabetic retinopathy" @default.
• W4220820843 cites W1878915617 @default.
• W4220820843 cites W1969496006 @default.
• W4220820843 cites W1977055509 @default.
• W4220820843 cites W2168792047 @default.
• W4220820843 cites W2433157206 @default.
• W4220820843 cites W2557738935 @default.
• W4220820843 cites W2592152820 @default.
• W4220820843 cites W2735168623 @default.
• W4220820843 cites W2746791238 @default.
• W4220820843 cites W2792618444 @default.
• W4220820843 cites W2905123846 @default.
• W4220820843 cites W2910297572 @default.
• W4220820843 cites W2923062287 @default.
• W4220820843 cites W2939250925 @default.
• W4220820843 cites W2942080964 @default.
• W4220820843 cites W2946839276 @default.
• W4220820843 cites W2948685905 @default.
• W4220820843 cites W2963307106 @default.
• W4220820843 cites W2964309882 @default.
• W4220820843 cites W2972415570 @default.
• W4220820843 cites W2994814705 @default.
• W4220820843 cites W2996968220 @default.
• W4220820843 cites W3009238059 @default.
• W4220820843 cites W3010500903 @default.
• W4220820843 cites W3047343382 @default.
• W4220820843 cites W3096756903 @default.
• W4220820843 cites W3099733385 @default.
• W4220820843 cites W3104165962 @default.
• W4220820843 cites W3123543052 @default.
• W4220820843 cites W3124526182 @default.
• W4220820843 cites W3137734413 @default.
• W4220820843 cites W3138360643 @default.
• W4220820843 cites W3189369139 @default.
• W4220820843 cites W60978252 @default.
• W4220820843 doi "https://doi.org/10.3934/mbe.2022248" @default.
• W4220820843 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/35430865" @default.
• W4220820843 hasPublicationYear "2022" @default.
• W4220820843 type Work @default.
• W4220820843 citedByCount "4" @default.
• W4220820843 countsByYear W42208208432022 @default.
• W4220820843 countsByYear W42208208432023 @default.
• W4220820843 crossrefType "journal-article" @default.
• W4220820843 hasAuthorship W4220820843A5018073672 @default.
• W4220820843 hasAuthorship W4220820843A5024839012 @default.
• W4220820843 hasAuthorship W4220820843A5034961228 @default.
• W4220820843 hasAuthorship W4220820843A5043136166 @default.
• W4220820843 hasAuthorship W4220820843A5070141978 @default.
• W4220820843 hasAuthorship W4220820843A5076476272 @default.
• W4220820843 hasBestOaLocation W42208208431 @default.
• W4220820843 hasConcept C108583219 @default.
• W4220820843 hasConcept C11413529 @default.
• W4220820843 hasConcept C118487528 @default.
• W4220820843 hasConcept C124504099 @default.
• W4220820843 hasConcept C134018914 @default.
• W4220820843 hasConcept C146849305 @default.
• W4220820843 hasConcept C153180895 @default.
• W4220820843 hasConcept C154945302 @default.
• W4220820843 hasConcept C155512373 @default.
• W4220820843 hasConcept C2776391266 @default.
• W4220820843 hasConcept C2779829184 @default.
• W4220820843 hasConcept C31972630 @default.
• W4220820843 hasConcept C41008148 @default.
• W4220820843 hasConcept C555293320 @default.
• W4220820843 hasConcept C71924100 @default.
• W4220820843 hasConcept C89600930 @default.
• W4220820843 hasConceptScore W4220820843C108583219 @default.
• W4220820843 hasConceptScore W4220820843C11413529 @default.
• W4220820843 hasConceptScore W4220820843C118487528 @default.
• W4220820843 hasConceptScore W4220820843C124504099 @default.
• W4220820843 hasConceptScore W4220820843C134018914 @default.
• W4220820843 hasConceptScore W4220820843C146849305 @default.
• W4220820843 hasConceptScore W4220820843C153180895 @default.
• W4220820843 hasConceptScore W4220820843C154945302 @default.
• W4220820843 hasConceptScore W4220820843C155512373 @default.
• W4220820843 hasConceptScore W4220820843C2776391266 @default.
• W4220820843 hasConceptScore W4220820843C2779829184 @default.
• W4220820843 hasConceptScore W4220820843C31972630 @default.
• W4220820843 hasConceptScore W4220820843C41008148 @default.
• W4220820843 hasConceptScore W4220820843C555293320 @default.
• W4220820843 hasConceptScore W4220820843C71924100 @default.
• W4220820843 hasConceptScore W4220820843C89600930 @default.
• W4220820843 hasIssue "5" @default.
• W4220820843 hasLocation W42208208431 @default.
• W4220820843 hasLocation W42208208432 @default.
• W4220820843 hasOpenAccess W4220820843 @default.
• W4220820843 hasPrimaryLocation W42208208431 @default.
• W4220820843 hasRelatedWork W158826679 @default.

• next