FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3202183041> ?p ?o ?g. }

• W3202183041 endingPage "1820" @default.
• W3202183041 startingPage "1820" @default.
• W3202183041 abstract "The segmentation of retinal vessels is critical for the diagnosis of some fundus diseases. Retinal vessel segmentation requires abundant spatial information and receptive fields with different sizes while existing methods usually sacrifice spatial resolution to achieve real-time reasoning speed, resulting in inadequate vessel segmentation of low-contrast regions and weak anti-noise interference ability. The asymmetry of capillaries in fundus images also increases the difficulty of segmentation. In this paper, we proposed a two-branch network based on multi-scale attention to alleviate the above problem. First, a coarse network with multi-scale U-Net as the backbone is designed to capture more semantic information and to generate high-resolution features. A multi-scale attention module is used to obtain enough receptive fields. The other branch is a fine network, which uses the residual block of a small convolution kernel to make up for the deficiency of spatial information. Finally, we use the feature fusion module to aggregate the information of the coarse and fine networks. The experiments were performed on the DRIVE, CHASE, and STARE datasets. Respectively, the accuracy reached 96.93%, 97.58%, and 97.70%. The specificity reached 97.72%, 98.52%, and 98.94%. The F-measure reached 83.82%, 81.39%, and 84.36%. Experimental results show that compared with some state-of-art methods such as Sine-Net, SA-Net, our proposed method has better performance on three datasets." @default.
• W3202183041 created "2021-10-11" @default.
• W3202183041 creator A5005516772 @default.
• W3202183041 creator A5035199580 @default.
• W3202183041 creator A5071911692 @default.
• W3202183041 creator A5089136469 @default.
• W3202183041 date "2021-09-29" @default.
• W3202183041 modified "2023-09-29" @default.
• W3202183041 title "Bi-SANet—Bilateral Network with Scale Attention for Retinal Vessel Segmentation" @default.
• W3202183041 cites W1971803524 @default.
• W3202183041 cites W2051578148 @default.
• W3202183041 cites W2072130234 @default.
• W3202183041 cites W2073244572 @default.
• W3202183041 cites W2105685332 @default.
• W3202183041 cites W2109037308 @default.
• W3202183041 cites W2145305441 @default.
• W3202183041 cites W2148284840 @default.
• W3202183041 cites W2150769593 @default.
• W3202183041 cites W2152990105 @default.
• W3202183041 cites W2168932490 @default.
• W3202183041 cites W2327793514 @default.
• W3202183041 cites W2436226714 @default.
• W3202183041 cites W2620722267 @default.
• W3202183041 cites W2893691907 @default.
• W3202183041 cites W2898910301 @default.
• W3202183041 cites W2941942490 @default.
• W3202183041 cites W2942076346 @default.
• W3202183041 cites W2972096900 @default.
• W3202183041 cites W3008973472 @default.
• W3202183041 cites W3036827192 @default.
• W3202183041 cites W3092308655 @default.
• W3202183041 cites W3096812112 @default.
• W3202183041 cites W3116525667 @default.
• W3202183041 doi "https://doi.org/10.3390/sym13101820" @default.
• W3202183041 hasPublicationYear "2021" @default.
• W3202183041 type Work @default.
• W3202183041 sameAs 3202183041 @default.
• W3202183041 citedByCount "3" @default.
• W3202183041 countsByYear W32021830412022 @default.
• W3202183041 countsByYear W32021830412023 @default.
• W3202183041 crossrefType "journal-article" @default.
• W3202183041 hasAuthorship W3202183041A5005516772 @default.
• W3202183041 hasAuthorship W3202183041A5035199580 @default.
• W3202183041 hasAuthorship W3202183041A5071911692 @default.
• W3202183041 hasAuthorship W3202183041A5089136469 @default.
• W3202183041 hasBestOaLocation W32021830411 @default.
• W3202183041 hasConcept C11413529 @default.
• W3202183041 hasConcept C114614502 @default.
• W3202183041 hasConcept C118487528 @default.
• W3202183041 hasConcept C121332964 @default.
• W3202183041 hasConcept C138885662 @default.
• W3202183041 hasConcept C153180895 @default.
• W3202183041 hasConcept C154945302 @default.
• W3202183041 hasConcept C155512373 @default.
• W3202183041 hasConcept C2776391266 @default.
• W3202183041 hasConcept C2776401178 @default.
• W3202183041 hasConcept C2776502983 @default.
• W3202183041 hasConcept C2778755073 @default.
• W3202183041 hasConcept C31972630 @default.
• W3202183041 hasConcept C33923547 @default.
• W3202183041 hasConcept C41008148 @default.
• W3202183041 hasConcept C41895202 @default.
• W3202183041 hasConcept C62520636 @default.
• W3202183041 hasConcept C71924100 @default.
• W3202183041 hasConcept C74193536 @default.
• W3202183041 hasConcept C89600930 @default.
• W3202183041 hasConceptScore W3202183041C11413529 @default.
• W3202183041 hasConceptScore W3202183041C114614502 @default.
• W3202183041 hasConceptScore W3202183041C118487528 @default.
• W3202183041 hasConceptScore W3202183041C121332964 @default.
• W3202183041 hasConceptScore W3202183041C138885662 @default.
• W3202183041 hasConceptScore W3202183041C153180895 @default.
• W3202183041 hasConceptScore W3202183041C154945302 @default.
• W3202183041 hasConceptScore W3202183041C155512373 @default.
• W3202183041 hasConceptScore W3202183041C2776391266 @default.
• W3202183041 hasConceptScore W3202183041C2776401178 @default.
• W3202183041 hasConceptScore W3202183041C2776502983 @default.
• W3202183041 hasConceptScore W3202183041C2778755073 @default.
• W3202183041 hasConceptScore W3202183041C31972630 @default.
• W3202183041 hasConceptScore W3202183041C33923547 @default.
• W3202183041 hasConceptScore W3202183041C41008148 @default.
• W3202183041 hasConceptScore W3202183041C41895202 @default.
• W3202183041 hasConceptScore W3202183041C62520636 @default.
• W3202183041 hasConceptScore W3202183041C71924100 @default.
• W3202183041 hasConceptScore W3202183041C74193536 @default.
• W3202183041 hasConceptScore W3202183041C89600930 @default.
• W3202183041 hasIssue "10" @default.
• W3202183041 hasLocation W32021830411 @default.
• W3202183041 hasLocation W32021830412 @default.
• W3202183041 hasOpenAccess W3202183041 @default.
• W3202183041 hasPrimaryLocation W32021830411 @default.
• W3202183041 hasRelatedWork W1669643531 @default.
• W3202183041 hasRelatedWork W1987421842 @default.
• W3202183041 hasRelatedWork W2005437358 @default.
• W3202183041 hasRelatedWork W2008656436 @default.
• W3202183041 hasRelatedWork W2023558673 @default.
• W3202183041 hasRelatedWork W2039154422 @default.
• W3202183041 hasRelatedWork W2122581818 @default.

• next