FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2999796716> ?p ?o ?g. }

• W2999796716 abstract "The generalization performance in deep learning is linked to the size and the variations of the samples available during training. This is apparent in the domain of computer-aided gastrointestinal tract abnormality detection, where the lesions can vary a lot from each other and the number of available samples is limited, mainly due to personal data protection legislations. In this work we present a novel approach of tackling the problem of limited training data availability by making use of artificially generated images. More specifically we trained a Generative Adversarial Network (GAN) using Wireless Capsule Endoscopy (WCE) images to generate fake but realistic images from the small bowel. The generated images were then used to train a Convolutional Neural Network (CNN) to identify inflammatory conditions on real WCE images. To evaluate the performance of our approach, in our experiments we compare the generalization performance of the same CNN architecture trained separately with real and fake images, obtaining 90.9% and 79.1% Area Under Receiver Operating Characteristic (AUC), respectively. The results show that training using solely artificially generated data can be effective in cases where real training data are inaccessible." @default.
• W2999796716 created "2020-01-23" @default.
• W2999796716 creator A5012331471 @default.
• W2999796716 creator A5020655974 @default.
• W2999796716 creator A5038222167 @default.
• W2999796716 creator A5072299664 @default.
• W2999796716 date "2019-10-01" @default.
• W2999796716 modified "2023-09-26" @default.
• W2999796716 title "Towards the Substitution of Real with Artificially Generated Endoscopic Images for CNN Training" @default.
• W2999796716 cites W1485415000 @default.
• W2999796716 cites W1993527699 @default.
• W2999796716 cites W1994612766 @default.
• W2999796716 cites W1996143085 @default.
• W2999796716 cites W2058068043 @default.
• W2999796716 cites W2099471712 @default.
• W2999796716 cites W2116013899 @default.
• W2999796716 cites W2125389028 @default.
• W2999796716 cites W2127006916 @default.
• W2999796716 cites W2163605009 @default.
• W2999796716 cites W2194775991 @default.
• W2999796716 cites W2295130376 @default.
• W2999796716 cites W2331128040 @default.
• W2999796716 cites W2531409750 @default.
• W2999796716 cites W2548275288 @default.
• W2999796716 cites W2557969682 @default.
• W2999796716 cites W2567079332 @default.
• W2999796716 cites W2590219438 @default.
• W2999796716 cites W2620841913 @default.
• W2999796716 cites W2739748921 @default.
• W2999796716 cites W2744999500 @default.
• W2999796716 cites W2752237898 @default.
• W2999796716 cites W2761299546 @default.
• W2999796716 cites W2789713147 @default.
• W2999796716 cites W2794022343 @default.
• W2999796716 cites W2801495938 @default.
• W2999796716 cites W2803469628 @default.
• W2999796716 cites W2806118840 @default.
• W2999796716 cites W2904144652 @default.
• W2999796716 cites W2919115771 @default.
• W2999796716 cites W2945765801 @default.
• W2999796716 cites W2949117887 @default.
• W2999796716 cites W2951523806 @default.
• W2999796716 cites W2963073614 @default.
• W2999796716 cites W2963382180 @default.
• W2999796716 cites W2963739978 @default.
• W2999796716 cites W2964193438 @default.
• W2999796716 cites W3103042993 @default.
• W2999796716 cites W2603901205 @default.
• W2999796716 doi "https://doi.org/10.1109/bibe.2019.00100" @default.
• W2999796716 hasPublicationYear "2019" @default.
• W2999796716 type Work @default.
• W2999796716 sameAs 2999796716 @default.
• W2999796716 citedByCount "4" @default.
• W2999796716 countsByYear W29997967162021 @default.
• W2999796716 countsByYear W29997967162022 @default.
• W2999796716 crossrefType "proceedings-article" @default.
• W2999796716 hasAuthorship W2999796716A5012331471 @default.
• W2999796716 hasAuthorship W2999796716A5020655974 @default.
• W2999796716 hasAuthorship W2999796716A5038222167 @default.
• W2999796716 hasAuthorship W2999796716A5072299664 @default.
• W2999796716 hasConcept C108583219 @default.
• W2999796716 hasConcept C121332964 @default.
• W2999796716 hasConcept C126838900 @default.
• W2999796716 hasConcept C134306372 @default.
• W2999796716 hasConcept C153180895 @default.
• W2999796716 hasConcept C153294291 @default.
• W2999796716 hasConcept C154945302 @default.
• W2999796716 hasConcept C177148314 @default.
• W2999796716 hasConcept C2777211547 @default.
• W2999796716 hasConcept C2777333622 @default.
• W2999796716 hasConcept C31972630 @default.
• W2999796716 hasConcept C33923547 @default.
• W2999796716 hasConcept C41008148 @default.
• W2999796716 hasConcept C51632099 @default.
• W2999796716 hasConcept C71924100 @default.
• W2999796716 hasConcept C81363708 @default.
• W2999796716 hasConceptScore W2999796716C108583219 @default.
• W2999796716 hasConceptScore W2999796716C121332964 @default.
• W2999796716 hasConceptScore W2999796716C126838900 @default.
• W2999796716 hasConceptScore W2999796716C134306372 @default.
• W2999796716 hasConceptScore W2999796716C153180895 @default.
• W2999796716 hasConceptScore W2999796716C153294291 @default.
• W2999796716 hasConceptScore W2999796716C154945302 @default.
• W2999796716 hasConceptScore W2999796716C177148314 @default.
• W2999796716 hasConceptScore W2999796716C2777211547 @default.
• W2999796716 hasConceptScore W2999796716C2777333622 @default.
• W2999796716 hasConceptScore W2999796716C31972630 @default.
• W2999796716 hasConceptScore W2999796716C33923547 @default.
• W2999796716 hasConceptScore W2999796716C41008148 @default.
• W2999796716 hasConceptScore W2999796716C51632099 @default.
• W2999796716 hasConceptScore W2999796716C71924100 @default.
• W2999796716 hasConceptScore W2999796716C81363708 @default.
• W2999796716 hasLocation W29997967161 @default.
• W2999796716 hasOpenAccess W2999796716 @default.
• W2999796716 hasPrimaryLocation W29997967161 @default.
• W2999796716 hasRelatedWork W2731899572 @default.
• W2999796716 hasRelatedWork W2732542196 @default.
• W2999796716 hasRelatedWork W2738221750 @default.
• W2999796716 hasRelatedWork W2900725142 @default.
• W2999796716 hasRelatedWork W3144574764 @default.

• next