FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3009223967> ?p ?o ?g. }

• W3009223967 endingPage "43553" @default.
• W3009223967 startingPage "43537" @default.
• W3009223967 abstract "Deep learning methods provide a platform to segment boundaries within the retina and choroid in OCT images of the posterior eye, with the ultimate goal of having a robust model that works well across a wide range of different datasets. However, since most studies of deep learning methods use datasets exhibiting similar image quality for both training and evaluation, the effect of varied image quality on such methods is not normally explored in the context of OCT image segmentation. An understanding of the effects of image quality factors is vital to determine the robustness of the methods and their ability to be applied in clinical practice where images exhibiting a range of different qualities are encountered. This study examined a range of factors that can affect standard OCT image quality and determined how and why the performance of an existing neural network based segmentation method can subsequently degrade as a result. Three image quality factors (noise, contrast reduction, and gamma correction) all had a negative impact upon performance, while more robust performance was maintained in the presence of both JPEG and JPEG2000 image compression. Improving the method's robustness to each of these degradations is also demonstrated with marked performance improvements identified by applying a fine-tuning approach to the network. This study improves our understanding of the effect of OCT image degradation on neural network performance, the effect that fine-tuning with poor-image quality data has on the network and highlights the benefit and importance of training resilient models using data augmentation." @default.
• W3009223967 created "2020-03-13" @default.
• W3009223967 creator A5002372452 @default.
• W3009223967 creator A5022009973 @default.
• W3009223967 creator A5026925842 @default.
• W3009223967 creator A5041138389 @default.
• W3009223967 creator A5045316705 @default.
• W3009223967 creator A5074839699 @default.
• W3009223967 date "2020-01-01" @default.
• W3009223967 modified "2023-10-14" @default.
• W3009223967 title "Effect of Altered OCT Image Quality on Deep Learning Boundary Segmentation" @default.
• W3009223967 cites W1900665324 @default.
• W3009223967 cites W1996144177 @default.
• W3009223967 cites W1997547727 @default.
• W3009223967 cites W1999377661 @default.
• W3009223967 cites W2006290260 @default.
• W3009223967 cites W2009195969 @default.
• W3009223967 cites W2010310750 @default.
• W3009223967 cites W2011237852 @default.
• W3009223967 cites W2013436069 @default.
• W3009223967 cites W2026431811 @default.
• W3009223967 cites W2043724999 @default.
• W3009223967 cites W2051362212 @default.
• W3009223967 cites W2061240737 @default.
• W3009223967 cites W2074598933 @default.
• W3009223967 cites W2079390326 @default.
• W3009223967 cites W2099430002 @default.
• W3009223967 cites W2118686815 @default.
• W3009223967 cites W2123576638 @default.
• W3009223967 cites W2123842573 @default.
• W3009223967 cites W2141771435 @default.
• W3009223967 cites W2153189592 @default.
• W3009223967 cites W2156706485 @default.
• W3009223967 cites W2157979199 @default.
• W3009223967 cites W2164774194 @default.
• W3009223967 cites W2165733437 @default.
• W3009223967 cites W2194775991 @default.
• W3009223967 cites W2300511734 @default.
• W3009223967 cites W2326799156 @default.
• W3009223967 cites W2414755904 @default.
• W3009223967 cites W2463489988 @default.
• W3009223967 cites W2606534623 @default.
• W3009223967 cites W2608854843 @default.
• W3009223967 cites W2625039771 @default.
• W3009223967 cites W2725994366 @default.
• W3009223967 cites W2742820103 @default.
• W3009223967 cites W2754313360 @default.
• W3009223967 cites W2792141483 @default.
• W3009223967 cites W2803921547 @default.
• W3009223967 cites W2806407713 @default.
• W3009223967 cites W2808330913 @default.
• W3009223967 cites W2883235649 @default.
• W3009223967 cites W2888867330 @default.
• W3009223967 cites W2888905826 @default.
• W3009223967 cites W2890936063 @default.
• W3009223967 cites W2898575988 @default.
• W3009223967 cites W2905660188 @default.
• W3009223967 cites W2963980515 @default.
• W3009223967 cites W2973920946 @default.
• W3009223967 doi "https://doi.org/10.1109/access.2020.2977355" @default.
• W3009223967 hasPublicationYear "2020" @default.
• W3009223967 type Work @default.
• W3009223967 sameAs 3009223967 @default.
• W3009223967 citedByCount "17" @default.
• W3009223967 countsByYear W30092239672021 @default.
• W3009223967 countsByYear W30092239672022 @default.
• W3009223967 countsByYear W30092239672023 @default.
• W3009223967 crossrefType "journal-article" @default.
• W3009223967 hasAuthorship W3009223967A5002372452 @default.
• W3009223967 hasAuthorship W3009223967A5022009973 @default.
• W3009223967 hasAuthorship W3009223967A5026925842 @default.
• W3009223967 hasAuthorship W3009223967A5041138389 @default.
• W3009223967 hasAuthorship W3009223967A5045316705 @default.
• W3009223967 hasAuthorship W3009223967A5074839699 @default.
• W3009223967 hasBestOaLocation W30092239671 @default.
• W3009223967 hasConcept C104317684 @default.
• W3009223967 hasConcept C108583219 @default.
• W3009223967 hasConcept C115961682 @default.
• W3009223967 hasConcept C124504099 @default.
• W3009223967 hasConcept C13481523 @default.
• W3009223967 hasConcept C153180895 @default.
• W3009223967 hasConcept C154945302 @default.
• W3009223967 hasConcept C185592680 @default.
• W3009223967 hasConcept C31972630 @default.
• W3009223967 hasConcept C41008148 @default.
• W3009223967 hasConcept C50644808 @default.
• W3009223967 hasConcept C55020928 @default.
• W3009223967 hasConcept C55493867 @default.
• W3009223967 hasConcept C63479239 @default.
• W3009223967 hasConcept C69216139 @default.
• W3009223967 hasConcept C89600930 @default.
• W3009223967 hasConcept C9417928 @default.
• W3009223967 hasConceptScore W3009223967C104317684 @default.
• W3009223967 hasConceptScore W3009223967C108583219 @default.
• W3009223967 hasConceptScore W3009223967C115961682 @default.
• W3009223967 hasConceptScore W3009223967C124504099 @default.
• W3009223967 hasConceptScore W3009223967C13481523 @default.
• W3009223967 hasConceptScore W3009223967C153180895 @default.

• next