FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4308233887> ?p ?o ?g. }

• W4308233887 abstract "Recent deep learning-based contour detection studies show high accuracy in single-class boundary detection problems. However, this performance does not translate well in a multi-class scenario where continuous contours are required. Our research presents CU-Net, a U-Net-based network with residual-net encoders which can produce accurate and uninterrupted contour lines for multiple classes. The critical factor behind this concept is our continuity module, containing an interpolation layer and a novel activation function that converts discrete signals into smooth contours. We find the application of our approach in medical imaging problems like retinal layer segmentation from optical coherence tomography (OCT) scans. We applied our method to an expert annotated OCT dataset of children with sickle-cell disease. To compare with benchmarks, we evaluated our network on DME and HC-MS datasets. We achieved an overall mean absolute distance of 6.48 ± 2.04µM and 1.97 ± 0.89µM, respectively 1.03 and 1.4 times less than the current state-of-the-art." @default.
• W4308233887 created "2022-11-09" @default.
• W4308233887 creator A5015328016 @default.
• W4308233887 creator A5076482730 @default.
• W4308233887 creator A5082156574 @default.
• W4308233887 date "2022-10-16" @default.
• W4308233887 modified "2023-10-14" @default.
• W4308233887 title "Cu-Net: Towards Continuous Multi-Class Contour Detection for Retinal Layer Segmentation In Oct Images" @default.
• W4308233887 cites W1895539857 @default.
• W4308233887 cites W1901129140 @default.
• W4308233887 cites W1925219021 @default.
• W4308233887 cites W1974420926 @default.
• W4308233887 cites W2011237852 @default.
• W4308233887 cites W2038850290 @default.
• W4308233887 cites W2074598933 @default.
• W4308233887 cites W2284824960 @default.
• W4308233887 cites W2300687442 @default.
• W4308233887 cites W2463489988 @default.
• W4308233887 cites W2606534623 @default.
• W4308233887 cites W2752006103 @default.
• W4308233887 cites W2774320778 @default.
• W4308233887 cites W2808330913 @default.
• W4308233887 cites W2883254424 @default.
• W4308233887 cites W2885036741 @default.
• W4308233887 cites W2907465751 @default.
• W4308233887 cites W2928133111 @default.
• W4308233887 cites W2953881420 @default.
• W4308233887 cites W2962990471 @default.
• W4308233887 cites W2964015468 @default.
• W4308233887 cites W2966495887 @default.
• W4308233887 cites W2973920946 @default.
• W4308233887 cites W2979568061 @default.
• W4308233887 cites W3006962589 @default.
• W4308233887 cites W3009158303 @default.
• W4308233887 cites W3009223967 @default.
• W4308233887 cites W3010066814 @default.
• W4308233887 cites W3089618815 @default.
• W4308233887 cites W3092762369 @default.
• W4308233887 cites W3113225488 @default.
• W4308233887 cites W3127804597 @default.
• W4308233887 cites W3167893492 @default.
• W4308233887 cites W3199860269 @default.
• W4308233887 cites W4214774769 @default.
• W4308233887 doi "https://doi.org/10.1109/icip46576.2022.9897516" @default.
• W4308233887 hasPublicationYear "2022" @default.
• W4308233887 type Work @default.
• W4308233887 citedByCount "0" @default.
• W4308233887 crossrefType "proceedings-article" @default.
• W4308233887 hasAuthorship W4308233887A5015328016 @default.
• W4308233887 hasAuthorship W4308233887A5076482730 @default.
• W4308233887 hasAuthorship W4308233887A5082156574 @default.
• W4308233887 hasConcept C108583219 @default.
• W4308233887 hasConcept C11413529 @default.
• W4308233887 hasConcept C115961682 @default.
• W4308233887 hasConcept C120665830 @default.
• W4308233887 hasConcept C121332964 @default.
• W4308233887 hasConcept C124504099 @default.
• W4308233887 hasConcept C134306372 @default.
• W4308233887 hasConcept C137800194 @default.
• W4308233887 hasConcept C14166107 @default.
• W4308233887 hasConcept C153180895 @default.
• W4308233887 hasConcept C154945302 @default.
• W4308233887 hasConcept C155512373 @default.
• W4308233887 hasConcept C185592680 @default.
• W4308233887 hasConcept C2524010 @default.
• W4308233887 hasConcept C2777212361 @default.
• W4308233887 hasConcept C2778818243 @default.
• W4308233887 hasConcept C2780827179 @default.
• W4308233887 hasConcept C31972630 @default.
• W4308233887 hasConcept C33923547 @default.
• W4308233887 hasConcept C41008148 @default.
• W4308233887 hasConcept C55493867 @default.
• W4308233887 hasConcept C62354387 @default.
• W4308233887 hasConcept C89600930 @default.
• W4308233887 hasConceptScore W4308233887C108583219 @default.
• W4308233887 hasConceptScore W4308233887C11413529 @default.
• W4308233887 hasConceptScore W4308233887C115961682 @default.
• W4308233887 hasConceptScore W4308233887C120665830 @default.
• W4308233887 hasConceptScore W4308233887C121332964 @default.
• W4308233887 hasConceptScore W4308233887C124504099 @default.
• W4308233887 hasConceptScore W4308233887C134306372 @default.
• W4308233887 hasConceptScore W4308233887C137800194 @default.
• W4308233887 hasConceptScore W4308233887C14166107 @default.
• W4308233887 hasConceptScore W4308233887C153180895 @default.
• W4308233887 hasConceptScore W4308233887C154945302 @default.
• W4308233887 hasConceptScore W4308233887C155512373 @default.
• W4308233887 hasConceptScore W4308233887C185592680 @default.
• W4308233887 hasConceptScore W4308233887C2524010 @default.
• W4308233887 hasConceptScore W4308233887C2777212361 @default.
• W4308233887 hasConceptScore W4308233887C2778818243 @default.
• W4308233887 hasConceptScore W4308233887C2780827179 @default.
• W4308233887 hasConceptScore W4308233887C31972630 @default.
• W4308233887 hasConceptScore W4308233887C33923547 @default.
• W4308233887 hasConceptScore W4308233887C41008148 @default.
• W4308233887 hasConceptScore W4308233887C55493867 @default.
• W4308233887 hasConceptScore W4308233887C62354387 @default.
• W4308233887 hasConceptScore W4308233887C89600930 @default.
• W4308233887 hasLocation W43082338871 @default.
• W4308233887 hasOpenAccess W4308233887 @default.
• W4308233887 hasPrimaryLocation W43082338871 @default.

• next