Matches in SemOpenAlex for { <https://semopenalex.org/work/W3199907666> ?p ?o ?g. }
Showing items 1 to 97 of
97
with 100 items per page.
- W3199907666 endingPage "948" @default.
- W3199907666 startingPage "948" @default.
- W3199907666 abstract "<ns3:p>Diabetes is one of the top ten causes of death among adults worldwide. People with diabetes are prone to suffer from eye disease such as diabetic retinopathy (DR). DR damages the blood vessels in the retina and can result in vision loss. DR grading is an essential step to take to help in the early diagnosis and in the effective treatment thereof, and also to slow down its progression to vision impairment. Existing automatic solutions are mostly based on traditional image processing and machine learning techniques. Hence, there is a big gap when it comes to more generic detection and grading of DR. Various deep learning models such as convolutional neural networks (CNNs) have been previously utilized for this purpose. To enhance DR grading, this paper proposes a novel solution based on an ensemble of state-of-the-art deep learning models called vision transformers. A challenging public DR dataset proposed in a 2015 Kaggle challenge was used for training and evaluation of the proposed method. This dataset includes highly imbalanced data with five levels of severity: No DR, Mild, Moderate, Severe, and Proliferative DR. The experiments conducted showed that the proposed solution outperforms existing methods in terms of precision (47%), recall (45%), F1 score (42%), and Quadratic Weighted Kappa (QWK) (60.2%). Finally, it was able to run with low inference time (1.12 seconds). For this reason, the proposed solution can help examiners grade DR more accurately than manual means.</ns3:p>" @default.
- W3199907666 created "2021-09-27" @default.
- W3199907666 creator A5007717604 @default.
- W3199907666 creator A5027445807 @default.
- W3199907666 creator A5037300629 @default.
- W3199907666 creator A5082635027 @default.
- W3199907666 creator A5085785861 @default.
- W3199907666 date "2021-09-21" @default.
- W3199907666 modified "2023-10-11" @default.
- W3199907666 title "Encoding Retina Image to Words using Ensemble of Vision Transformers for Diabetic Retinopathy Grading" @default.
- W3199907666 cites W2005409914 @default.
- W3199907666 cites W2009904828 @default.
- W3199907666 cites W2022126925 @default.
- W3199907666 cites W2051013472 @default.
- W3199907666 cites W2051424632 @default.
- W3199907666 cites W2097564701 @default.
- W3199907666 cites W2123634291 @default.
- W3199907666 cites W2138480916 @default.
- W3199907666 cites W2159389777 @default.
- W3199907666 cites W2160041268 @default.
- W3199907666 cites W2338167986 @default.
- W3199907666 cites W2344912502 @default.
- W3199907666 cites W2409181047 @default.
- W3199907666 cites W2470155373 @default.
- W3199907666 cites W2502390809 @default.
- W3199907666 cites W2529609428 @default.
- W3199907666 cites W2537959867 @default.
- W3199907666 cites W2557738935 @default.
- W3199907666 cites W2596818854 @default.
- W3199907666 cites W2809489644 @default.
- W3199907666 cites W2920497957 @default.
- W3199907666 cites W3115048207 @default.
- W3199907666 cites W4211205882 @default.
- W3199907666 cites W4239157251 @default.
- W3199907666 cites W4240986128 @default.
- W3199907666 doi "https://doi.org/10.12688/f1000research.73082.1" @default.
- W3199907666 hasPublicationYear "2021" @default.
- W3199907666 type Work @default.
- W3199907666 sameAs 3199907666 @default.
- W3199907666 citedByCount "6" @default.
- W3199907666 countsByYear W31999076662022 @default.
- W3199907666 countsByYear W31999076662023 @default.
- W3199907666 crossrefType "journal-article" @default.
- W3199907666 hasAuthorship W3199907666A5007717604 @default.
- W3199907666 hasAuthorship W3199907666A5027445807 @default.
- W3199907666 hasAuthorship W3199907666A5037300629 @default.
- W3199907666 hasAuthorship W3199907666A5082635027 @default.
- W3199907666 hasAuthorship W3199907666A5085785861 @default.
- W3199907666 hasBestOaLocation W31999076661 @default.
- W3199907666 hasConcept C108583219 @default.
- W3199907666 hasConcept C119857082 @default.
- W3199907666 hasConcept C127413603 @default.
- W3199907666 hasConcept C134018914 @default.
- W3199907666 hasConcept C147176958 @default.
- W3199907666 hasConcept C153180895 @default.
- W3199907666 hasConcept C154945302 @default.
- W3199907666 hasConcept C2776214188 @default.
- W3199907666 hasConcept C2777286243 @default.
- W3199907666 hasConcept C2779829184 @default.
- W3199907666 hasConcept C41008148 @default.
- W3199907666 hasConcept C555293320 @default.
- W3199907666 hasConcept C71924100 @default.
- W3199907666 hasConcept C81363708 @default.
- W3199907666 hasConceptScore W3199907666C108583219 @default.
- W3199907666 hasConceptScore W3199907666C119857082 @default.
- W3199907666 hasConceptScore W3199907666C127413603 @default.
- W3199907666 hasConceptScore W3199907666C134018914 @default.
- W3199907666 hasConceptScore W3199907666C147176958 @default.
- W3199907666 hasConceptScore W3199907666C153180895 @default.
- W3199907666 hasConceptScore W3199907666C154945302 @default.
- W3199907666 hasConceptScore W3199907666C2776214188 @default.
- W3199907666 hasConceptScore W3199907666C2777286243 @default.
- W3199907666 hasConceptScore W3199907666C2779829184 @default.
- W3199907666 hasConceptScore W3199907666C41008148 @default.
- W3199907666 hasConceptScore W3199907666C555293320 @default.
- W3199907666 hasConceptScore W3199907666C71924100 @default.
- W3199907666 hasConceptScore W3199907666C81363708 @default.
- W3199907666 hasLocation W31999076661 @default.
- W3199907666 hasOpenAccess W3199907666 @default.
- W3199907666 hasPrimaryLocation W31999076661 @default.
- W3199907666 hasRelatedWork W1588461101 @default.
- W3199907666 hasRelatedWork W2064165679 @default.
- W3199907666 hasRelatedWork W3029198973 @default.
- W3199907666 hasRelatedWork W3133861977 @default.
- W3199907666 hasRelatedWork W3167935049 @default.
- W3199907666 hasRelatedWork W3193565141 @default.
- W3199907666 hasRelatedWork W3208525924 @default.
- W3199907666 hasRelatedWork W4226493464 @default.
- W3199907666 hasRelatedWork W4293226380 @default.
- W3199907666 hasRelatedWork W4312417841 @default.
- W3199907666 hasVolume "10" @default.
- W3199907666 isParatext "false" @default.
- W3199907666 isRetracted "false" @default.
- W3199907666 magId "3199907666" @default.
- W3199907666 workType "article" @default.