Matches in SemOpenAlex for { <https://semopenalex.org/work/W3161307971> ?p ?o ?g. }
Showing items 1 to 83 of
83
with 100 items per page.
- W3161307971 endingPage "69" @default.
- W3161307971 startingPage "69" @default.
- W3161307971 abstract "Generative adversarial networks (GANs) have become increasingly powerful, generating mind-blowing photorealistic images that mimic the content of datasets they have been trained to replicate. One recurrent theme in medical imaging, is whether GANs can also be as effective at generating workable medical data, as they are for generating realistic RGB images. In this paper, we perform a multi-GAN and multi-application study, to gauge the benefits of GANs in medical imaging. We tested various GAN architectures, from basic DCGAN to more sophisticated style-based GANs, on three medical imaging modalities and organs, namely: cardiac cine-MRI, liver CT, and RGB retina images. GANs were trained on well-known and widely utilized datasets, from which their FID scores were computed, to measure the visual acuity of their generated images. We further tested their usefulness by measuring the segmentation accuracy of a U-Net trained on these generated images and the original data. The results reveal that GANs are far from being equal, as some are ill-suited for medical imaging applications, while others performed much better. The top-performing GANs are capable of generating realistic-looking medical images by FID standards, that can fool trained experts in a visual Turing test and comply to some metrics. However, segmentation results suggest that no GAN is capable of reproducing the full richness of medical datasets." @default.
- W3161307971 created "2021-05-24" @default.
- W3161307971 creator A5014239609 @default.
- W3161307971 creator A5029910785 @default.
- W3161307971 creator A5086581005 @default.
- W3161307971 date "2023-03-16" @default.
- W3161307971 modified "2023-10-16" @default.
- W3161307971 title "GANs for Medical Image Synthesis: An Empirical Study" @default.
- W3161307971 cites W1901129140 @default.
- W3161307971 cites W2108598243 @default.
- W3161307971 cites W2522844972 @default.
- W3161307971 cites W2572730214 @default.
- W3161307971 cites W2593414223 @default.
- W3161307971 cites W2765253680 @default.
- W3161307971 cites W2781600508 @default.
- W3161307971 cites W2804047627 @default.
- W3161307971 cites W2828862258 @default.
- W3161307971 cites W2884805522 @default.
- W3161307971 cites W2889326414 @default.
- W3161307971 cites W2962770929 @default.
- W3161307971 cites W2962785568 @default.
- W3161307971 cites W2962974533 @default.
- W3161307971 cites W2963021791 @default.
- W3161307971 cites W2963073614 @default.
- W3161307971 cites W2963185411 @default.
- W3161307971 cites W2964261464 @default.
- W3161307971 cites W2974031746 @default.
- W3161307971 cites W3035574324 @default.
- W3161307971 cites W3047625747 @default.
- W3161307971 cites W3109809751 @default.
- W3161307971 cites W3154686965 @default.
- W3161307971 cites W4206958764 @default.
- W3161307971 doi "https://doi.org/10.3390/jimaging9030069" @default.
- W3161307971 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/36976120" @default.
- W3161307971 hasPublicationYear "2023" @default.
- W3161307971 type Work @default.
- W3161307971 sameAs 3161307971 @default.
- W3161307971 citedByCount "16" @default.
- W3161307971 countsByYear W31613079712021 @default.
- W3161307971 countsByYear W31613079712023 @default.
- W3161307971 crossrefType "journal-article" @default.
- W3161307971 hasAuthorship W3161307971A5014239609 @default.
- W3161307971 hasAuthorship W3161307971A5029910785 @default.
- W3161307971 hasAuthorship W3161307971A5086581005 @default.
- W3161307971 hasBestOaLocation W31613079711 @default.
- W3161307971 hasConcept C153180895 @default.
- W3161307971 hasConcept C154945302 @default.
- W3161307971 hasConcept C31601959 @default.
- W3161307971 hasConcept C31972630 @default.
- W3161307971 hasConcept C41008148 @default.
- W3161307971 hasConcept C82990744 @default.
- W3161307971 hasConcept C89600930 @default.
- W3161307971 hasConceptScore W3161307971C153180895 @default.
- W3161307971 hasConceptScore W3161307971C154945302 @default.
- W3161307971 hasConceptScore W3161307971C31601959 @default.
- W3161307971 hasConceptScore W3161307971C31972630 @default.
- W3161307971 hasConceptScore W3161307971C41008148 @default.
- W3161307971 hasConceptScore W3161307971C82990744 @default.
- W3161307971 hasConceptScore W3161307971C89600930 @default.
- W3161307971 hasIssue "3" @default.
- W3161307971 hasLocation W31613079711 @default.
- W3161307971 hasLocation W31613079712 @default.
- W3161307971 hasLocation W31613079713 @default.
- W3161307971 hasLocation W31613079714 @default.
- W3161307971 hasOpenAccess W3161307971 @default.
- W3161307971 hasPrimaryLocation W31613079711 @default.
- W3161307971 hasRelatedWork W1669643531 @default.
- W3161307971 hasRelatedWork W2005437358 @default.
- W3161307971 hasRelatedWork W2052518016 @default.
- W3161307971 hasRelatedWork W2085956791 @default.
- W3161307971 hasRelatedWork W2283162247 @default.
- W3161307971 hasRelatedWork W2314488738 @default.
- W3161307971 hasRelatedWork W2517104666 @default.
- W3161307971 hasRelatedWork W2524507886 @default.
- W3161307971 hasRelatedWork W2771653066 @default.
- W3161307971 hasRelatedWork W4212983513 @default.
- W3161307971 hasVolume "9" @default.
- W3161307971 isParatext "false" @default.
- W3161307971 isRetracted "false" @default.
- W3161307971 magId "3161307971" @default.
- W3161307971 workType "article" @default.