Matches in SemOpenAlex for { <https://semopenalex.org/work/W3035268411> ?p ?o ?g. }
Showing items 1 to 95 of
95
with 100 items per page.
- W3035268411 endingPage "1109" @default.
- W3035268411 startingPage "1094" @default.
- W3035268411 abstract "Segmentation of lesions from fundus images is an essential prerequisite for accurate severity assessment of diabetic retinopathy. Due to variation in morphologies, number and size of lesions, the manual grading process becomes extremely challenging and time-consuming. This necessitates the need of an automatic segmentation system that can precisely define the region of interest boundaries and assist ophthalmologists in speedy diagnosis along with diabetic retinopathy severity grading. The paper presents a modified U-Net architecture based on residual network and employs periodic shuffling with sub-pixel convolution initialized to convolution nearest neighbour resize. The proposed architecture has been trained and validated for microaneurysm and hard exudate segmentation on two publicly available datasets namely IDRiD and e-ophtha. For IDRiD dataset, the network obtains 99.88% accuracy, 99.85% sensitivity, 99.95% specificity and dice score of 0.9998 for both microaneurysm and exudate segmentation. Further, when trained on e-ophtha and validated on IDRiD dataset, the network shows 99.98% accuracy, 99.88% sensitivity, 99.89% specificity and dice score of 0.9998 for microaneurysm segmentation. For exudates segmentation, the model obtained 99.98% accuracy, 99.88% sensitivity, 99.89% specificity and dice score of 0.9999, when trained on e-ophtha and validated on IDRiD dataset. In comparison to existing literature, the proposed model provides state-of-the-art results for retinal lesion segmentation." @default.
- W3035268411 created "2020-06-19" @default.
- W3035268411 creator A5049189583 @default.
- W3035268411 creator A5064567901 @default.
- W3035268411 creator A5071795195 @default.
- W3035268411 creator A5083459076 @default.
- W3035268411 date "2020-07-01" @default.
- W3035268411 modified "2023-10-03" @default.
- W3035268411 title "Modified U-Net architecture for semantic segmentation of diabetic retinopathy images" @default.
- W3035268411 cites W1901129140 @default.
- W3035268411 cites W2433157206 @default.
- W3035268411 cites W2580160609 @default.
- W3035268411 cites W2607485502 @default.
- W3035268411 cites W2741248098 @default.
- W3035268411 cites W2755044644 @default.
- W3035268411 cites W2765370814 @default.
- W3035268411 cites W2772006542 @default.
- W3035268411 cites W2790552646 @default.
- W3035268411 cites W2806211850 @default.
- W3035268411 cites W2828862258 @default.
- W3035268411 cites W2888281749 @default.
- W3035268411 cites W2894558420 @default.
- W3035268411 cites W2911970391 @default.
- W3035268411 cites W2922015385 @default.
- W3035268411 cites W2940427983 @default.
- W3035268411 cites W2968622550 @default.
- W3035268411 cites W2973003726 @default.
- W3035268411 doi "https://doi.org/10.1016/j.bbe.2020.05.006" @default.
- W3035268411 hasPublicationYear "2020" @default.
- W3035268411 type Work @default.
- W3035268411 sameAs 3035268411 @default.
- W3035268411 citedByCount "50" @default.
- W3035268411 countsByYear W30352684112021 @default.
- W3035268411 countsByYear W30352684112022 @default.
- W3035268411 countsByYear W30352684112023 @default.
- W3035268411 crossrefType "journal-article" @default.
- W3035268411 hasAuthorship W3035268411A5049189583 @default.
- W3035268411 hasAuthorship W3035268411A5064567901 @default.
- W3035268411 hasAuthorship W3035268411A5071795195 @default.
- W3035268411 hasAuthorship W3035268411A5083459076 @default.
- W3035268411 hasConcept C105795698 @default.
- W3035268411 hasConcept C124504099 @default.
- W3035268411 hasConcept C127413603 @default.
- W3035268411 hasConcept C134018914 @default.
- W3035268411 hasConcept C147176958 @default.
- W3035268411 hasConcept C148524875 @default.
- W3035268411 hasConcept C153180895 @default.
- W3035268411 hasConcept C154945302 @default.
- W3035268411 hasConcept C163892561 @default.
- W3035268411 hasConcept C22029948 @default.
- W3035268411 hasConcept C2777286243 @default.
- W3035268411 hasConcept C2779829184 @default.
- W3035268411 hasConcept C33923547 @default.
- W3035268411 hasConcept C41008148 @default.
- W3035268411 hasConcept C555293320 @default.
- W3035268411 hasConcept C71924100 @default.
- W3035268411 hasConcept C89600930 @default.
- W3035268411 hasConceptScore W3035268411C105795698 @default.
- W3035268411 hasConceptScore W3035268411C124504099 @default.
- W3035268411 hasConceptScore W3035268411C127413603 @default.
- W3035268411 hasConceptScore W3035268411C134018914 @default.
- W3035268411 hasConceptScore W3035268411C147176958 @default.
- W3035268411 hasConceptScore W3035268411C148524875 @default.
- W3035268411 hasConceptScore W3035268411C153180895 @default.
- W3035268411 hasConceptScore W3035268411C154945302 @default.
- W3035268411 hasConceptScore W3035268411C163892561 @default.
- W3035268411 hasConceptScore W3035268411C22029948 @default.
- W3035268411 hasConceptScore W3035268411C2777286243 @default.
- W3035268411 hasConceptScore W3035268411C2779829184 @default.
- W3035268411 hasConceptScore W3035268411C33923547 @default.
- W3035268411 hasConceptScore W3035268411C41008148 @default.
- W3035268411 hasConceptScore W3035268411C555293320 @default.
- W3035268411 hasConceptScore W3035268411C71924100 @default.
- W3035268411 hasConceptScore W3035268411C89600930 @default.
- W3035268411 hasIssue "3" @default.
- W3035268411 hasLocation W30352684111 @default.
- W3035268411 hasOpenAccess W3035268411 @default.
- W3035268411 hasPrimaryLocation W30352684111 @default.
- W3035268411 hasRelatedWork W2005476934 @default.
- W3035268411 hasRelatedWork W2630229246 @default.
- W3035268411 hasRelatedWork W2897195263 @default.
- W3035268411 hasRelatedWork W2973136608 @default.
- W3035268411 hasRelatedWork W2999580839 @default.
- W3035268411 hasRelatedWork W3105697449 @default.
- W3035268411 hasRelatedWork W3116883888 @default.
- W3035268411 hasRelatedWork W3152950745 @default.
- W3035268411 hasRelatedWork W4360850309 @default.
- W3035268411 hasRelatedWork W4372049117 @default.
- W3035268411 hasVolume "40" @default.
- W3035268411 isParatext "false" @default.
- W3035268411 isRetracted "false" @default.
- W3035268411 magId "3035268411" @default.
- W3035268411 workType "article" @default.