FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4288049163> ?p ?o ?g. }

• W4288049163 endingPage "2251" @default.
• W4288049163 startingPage "2238" @default.
• W4288049163 abstract "The morphology of retinal vessels is closely associated with many kinds of ophthalmic diseases. Although huge progress in retinal vessel segmentation has been achieved with the advancement of deep learning, some challenging issues remain. For example, vessels can be disturbed or covered by other components presented in the retina (such as optic disc or lesions). Moreover, some thin vessels are also easily missed by current methods. In addition, existing fundus image datasets are generally tiny, due to the difficulty of vessel labeling. In this work, a new network called SkelCon is proposed to deal with these problems by introducing skeletal prior and contrastive loss. A skeleton fitting module is developed to preserve the morphology of the vessels and improve the completeness and continuity of thin vessels. A contrastive loss is employed to enhance the discrimination between vessels and background. In addition, a new data augmentation method is proposed to enrich the training samples and improve the robustness of the proposed model. Extensive validations were performed on several popular datasets (DRIVE, STARE, CHASE, and HRF), recently developed datasets (UoA-DR, IOSTAR, and RC-SLO), and some challenging clinical images (from RFMiD and JSIEC39 datasets). In addition, some specially designed metrics for vessel segmentation, including connectivity, overlapping area, consistency of vessel length, revised sensitivity, specificity, and accuracy were used for quantitative evaluation. The experimental results show that, the proposed model achieves state-of-the-art performance and significantly outperforms compared methods when extracting thin vessels in the regions of lesions or optic disc. Source code is available at <uri xmlns:mml=http://www.w3.org/1998/Math/MathML xmlns:xlink=http://www.w3.org/1999/xlink>https://www.github.com/tyb311/SkelCon</uri> ." @default.
• W4288049163 created "2022-07-27" @default.
• W4288049163 creator A5000472060 @default.
• W4288049163 creator A5008138882 @default.
• W4288049163 creator A5010207793 @default.
• W4288049163 creator A5090244595 @default.
• W4288049163 date "2022-09-01" @default.
• W4288049163 modified "2023-10-16" @default.
• W4288049163 title "Retinal Vessel Segmentation With Skeletal Prior and Contrastive Loss" @default.
• W4288049163 cites W1199446928 @default.
• W4288049163 cites W1924902684 @default.
• W4288049163 cites W2033723371 @default.
• W4288049163 cites W2034513030 @default.
• W4288049163 cites W2051578148 @default.
• W4288049163 cites W2053771279 @default.
• W4288049163 cites W2093545979 @default.
• W4288049163 cites W2105685332 @default.
• W4288049163 cites W2105923875 @default.
• W4288049163 cites W2112783556 @default.
• W4288049163 cites W2115680416 @default.
• W4288049163 cites W2116628223 @default.
• W4288049163 cites W2121913681 @default.
• W4288049163 cites W2129587342 @default.
• W4288049163 cites W2145305441 @default.
• W4288049163 cites W2150769593 @default.
• W4288049163 cites W2163344010 @default.
• W4288049163 cites W2166524747 @default.
• W4288049163 cites W2170092083 @default.
• W4288049163 cites W2194775991 @default.
• W4288049163 cites W2197648668 @default.
• W4288049163 cites W2206167351 @default.
• W4288049163 cites W2320230300 @default.
• W4288049163 cites W2327793514 @default.
• W4288049163 cites W2396282411 @default.
• W4288049163 cites W2404019942 @default.
• W4288049163 cites W2488605601 @default.
• W4288049163 cites W2527341761 @default.
• W4288049163 cites W2556022279 @default.
• W4288049163 cites W2611590631 @default.
• W4288049163 cites W2620722267 @default.
• W4288049163 cites W2626807635 @default.
• W4288049163 cites W2728997353 @default.
• W4288049163 cites W2752747624 @default.
• W4288049163 cites W2755938060 @default.
• W4288049163 cites W2774949955 @default.
• W4288049163 cites W2791338647 @default.
• W4288049163 cites W2802388893 @default.
• W4288049163 cites W2804236617 @default.
• W4288049163 cites W2809144587 @default.
• W4288049163 cites W2884292375 @default.
• W4288049163 cites W2893691907 @default.
• W4288049163 cites W2895202718 @default.
• W4288049163 cites W2942760134 @default.
• W4288049163 cites W2955571529 @default.
• W4288049163 cites W2963351448 @default.
• W4288049163 cites W2966989968 @default.
• W4288049163 cites W2972096900 @default.
• W4288049163 cites W2980524126 @default.
• W4288049163 cites W2982364173 @default.
• W4288049163 cites W3008536643 @default.
• W4288049163 cites W3010373058 @default.
• W4288049163 cites W3024471355 @default.
• W4288049163 cites W3030832441 @default.
• W4288049163 cites W3035524453 @default.
• W4288049163 cites W3048209253 @default.
• W4288049163 cites W3048610712 @default.
• W4288049163 cites W3096368178 @default.
• W4288049163 cites W3098547059 @default.
• W4288049163 cites W3103010481 @default.
• W4288049163 cites W3103835616 @default.
• W4288049163 cites W3111978277 @default.
• W4288049163 cites W3122431193 @default.
• W4288049163 cites W3128220181 @default.
• W4288049163 cites W3171007011 @default.
• W4288049163 cites W3191934798 @default.
• W4288049163 cites W3202228554 @default.
• W4288049163 cites W3213168093 @default.
• W4288049163 cites W32702003 @default.
• W4288049163 cites W845365781 @default.
• W4288049163 doi "https://doi.org/10.1109/tmi.2022.3161681" @default.
• W4288049163 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/35320091" @default.
• W4288049163 hasPublicationYear "2022" @default.
• W4288049163 type Work @default.
• W4288049163 citedByCount "13" @default.
• W4288049163 countsByYear W42880491632022 @default.
• W4288049163 countsByYear W42880491632023 @default.
• W4288049163 crossrefType "journal-article" @default.
• W4288049163 hasAuthorship W4288049163A5000472060 @default.
• W4288049163 hasAuthorship W4288049163A5008138882 @default.
• W4288049163 hasAuthorship W4288049163A5010207793 @default.
• W4288049163 hasAuthorship W4288049163A5090244595 @default.
• W4288049163 hasConcept C104317684 @default.
• W4288049163 hasConcept C118487528 @default.
• W4288049163 hasConcept C153180895 @default.
• W4288049163 hasConcept C154945302 @default.
• W4288049163 hasConcept C185592680 @default.
• W4288049163 hasConcept C2776391266 @default.
• W4288049163 hasConcept C2776436953 @default.

• next