FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4200316488> ?p ?o ?g. }

• W4200316488 endingPage "108347" @default.
• W4200316488 startingPage "108347" @default.
• W4200316488 abstract "The automated analysis of eye fundus images is crucial towards facilitating the screening and early diagnosis of glaucoma. Nowadays, there are two common alternatives for the diagnosis of this disease using deep neural networks. One is the segmentation of the optic disc and cup followed by the morphological analysis of these structures. The other is to directly address the diagnosis as an image classification task. The segmentation approach presents the advantage of using pixel-level labels with precise morphological information for training. However, while this detailed training feedback is not available for the classification approach, in this case the image-level labels may allow the discovery of additional non-morphological cues that are also relevant for the diagnosis. In this work, we propose a novel multi-task approach for the simultaneous classification of glaucoma and segmentation of the optic disc and cup. This approach can improve the overall performance by taking advantage of both pixel-level and image-level labels during the network training. Additionally, the segmentation maps that are predicted together with the diagnosis allow the extraction of relevant biomarkers such as the cup-to-disc ratio. The proposed methodology presents two relevant technical novelties. First, a network architecture for simultaneous segmentation and classification that increases the number of shared parameters between both tasks. Second, a multi-adaptive optimization strategy that ensures that both tasks contribute similarly to the parameter updates during training, avoiding the use of loss weighting hyperparameters. To validate our proposal, an exhaustive experimentation was performed on the public REFUGE and DRISHTI-GS datasets. The results show that our proposal outperforms comparable multi-task baselines and is highly competitive with existing state-of-the-art approaches. Additionally, the provided ablation study shows that both the network architecture and the optimization approach are independently advantageous for multi-task learning." @default.
• W4200316488 created "2021-12-31" @default.
• W4200316488 creator A5057860861 @default.
• W4200316488 creator A5059859767 @default.
• W4200316488 creator A5077849552 @default.
• W4200316488 creator A5087575858 @default.
• W4200316488 date "2022-02-01" @default.
• W4200316488 modified "2023-10-12" @default.
• W4200316488 title "End-to-end multi-task learning for simultaneous optic disc and cup segmentation and glaucoma classification in eye fundus images" @default.
• W4200316488 cites W1956294409 @default.
• W4200316488 cites W2034742711 @default.
• W4200316488 cites W2160605010 @default.
• W4200316488 cites W2884120031 @default.
• W4200316488 cites W2895387432 @default.
• W4200316488 cites W2897507310 @default.
• W4200316488 cites W2912806832 @default.
• W4200316488 cites W2915496375 @default.
• W4200316488 cites W2923062287 @default.
• W4200316488 cites W2935464137 @default.
• W4200316488 cites W2937343562 @default.
• W4200316488 cites W2941075605 @default.
• W4200316488 cites W2945789372 @default.
• W4200316488 cites W2963730393 @default.
• W4200316488 cites W2974825848 @default.
• W4200316488 cites W2975043431 @default.
• W4200316488 cites W2979448322 @default.
• W4200316488 cites W2980262056 @default.
• W4200316488 cites W2982287615 @default.
• W4200316488 cites W2982428510 @default.
• W4200316488 cites W2985345218 @default.
• W4200316488 cites W3012086751 @default.
• W4200316488 cites W3028380273 @default.
• W4200316488 cites W3037073017 @default.
• W4200316488 cites W3042340386 @default.
• W4200316488 cites W3045215429 @default.
• W4200316488 cites W3085046840 @default.
• W4200316488 cites W3092624683 @default.
• W4200316488 cites W3101386228 @default.
• W4200316488 cites W3185542499 @default.
• W4200316488 cites W4252684946 @default.
• W4200316488 doi "https://doi.org/10.1016/j.asoc.2021.108347" @default.
• W4200316488 hasPublicationYear "2022" @default.
• W4200316488 type Work @default.
• W4200316488 citedByCount "15" @default.
• W4200316488 countsByYear W42003164882022 @default.
• W4200316488 countsByYear W42003164882023 @default.
• W4200316488 crossrefType "journal-article" @default.
• W4200316488 hasAuthorship W4200316488A5057860861 @default.
• W4200316488 hasAuthorship W4200316488A5059859767 @default.
• W4200316488 hasAuthorship W4200316488A5077849552 @default.
• W4200316488 hasAuthorship W4200316488A5087575858 @default.
• W4200316488 hasBestOaLocation W42003164881 @default.
• W4200316488 hasConcept C108583219 @default.
• W4200316488 hasConcept C118487528 @default.
• W4200316488 hasConcept C119857082 @default.
• W4200316488 hasConcept C124504099 @default.
• W4200316488 hasConcept C126838900 @default.
• W4200316488 hasConcept C153180895 @default.
• W4200316488 hasConcept C154945302 @default.
• W4200316488 hasConcept C160633673 @default.
• W4200316488 hasConcept C162324750 @default.
• W4200316488 hasConcept C183115368 @default.
• W4200316488 hasConcept C187736073 @default.
• W4200316488 hasConcept C2776391266 @default.
• W4200316488 hasConcept C2778527774 @default.
• W4200316488 hasConcept C2779735895 @default.
• W4200316488 hasConcept C2780451532 @default.
• W4200316488 hasConcept C31972630 @default.
• W4200316488 hasConcept C41008148 @default.
• W4200316488 hasConcept C50644808 @default.
• W4200316488 hasConcept C71924100 @default.
• W4200316488 hasConcept C89600930 @default.
• W4200316488 hasConceptScore W4200316488C108583219 @default.
• W4200316488 hasConceptScore W4200316488C118487528 @default.
• W4200316488 hasConceptScore W4200316488C119857082 @default.
• W4200316488 hasConceptScore W4200316488C124504099 @default.
• W4200316488 hasConceptScore W4200316488C126838900 @default.
• W4200316488 hasConceptScore W4200316488C153180895 @default.
• W4200316488 hasConceptScore W4200316488C154945302 @default.
• W4200316488 hasConceptScore W4200316488C160633673 @default.
• W4200316488 hasConceptScore W4200316488C162324750 @default.
• W4200316488 hasConceptScore W4200316488C183115368 @default.
• W4200316488 hasConceptScore W4200316488C187736073 @default.
• W4200316488 hasConceptScore W4200316488C2776391266 @default.
• W4200316488 hasConceptScore W4200316488C2778527774 @default.
• W4200316488 hasConceptScore W4200316488C2779735895 @default.
• W4200316488 hasConceptScore W4200316488C2780451532 @default.
• W4200316488 hasConceptScore W4200316488C31972630 @default.
• W4200316488 hasConceptScore W4200316488C41008148 @default.
• W4200316488 hasConceptScore W4200316488C50644808 @default.
• W4200316488 hasConceptScore W4200316488C71924100 @default.
• W4200316488 hasConceptScore W4200316488C89600930 @default.
• W4200316488 hasLocation W42003164881 @default.
• W4200316488 hasLocation W42003164882 @default.
• W4200316488 hasOpenAccess W4200316488 @default.
• W4200316488 hasPrimaryLocation W42003164881 @default.
• W4200316488 hasRelatedWork W1993455246 @default.
• W4200316488 hasRelatedWork W2009907433 @default.

• next