Afficher la notice abrégée

Lung CT Synthesis Using GANs with Conditional Normalization on Registered Ultrashort Echo-Time MRI

hal.structure.identifierLaboratoire Bordelais de Recherche en Informatique [LaBRI]
dc.contributor.authorLONGUEFOSSE, Arthur
hal.structure.identifierCentre de recherche Cardio-Thoracique de Bordeaux [Bordeaux] [CRCTB]
dc.contributor.authorDOURNES, Gaël
hal.structure.identifierCentre de recherche Cardio-Thoracique de Bordeaux [Bordeaux] [CRCTB]
dc.contributor.authorBENLALA, Ilyes
hal.structure.identifierInstitut de Mathématiques de Bordeaux [IMB]
hal.structure.identifierModélisation Mathématique pour l'Oncologie [MONC]
dc.contributor.authorDENIS DE SENNEVILLE, Baudouin
hal.structure.identifierCentre de recherche Cardio-Thoracique de Bordeaux [Bordeaux] [CRCTB]
dc.contributor.authorLAURENT, François
hal.structure.identifierLaboratoire Bordelais de Recherche en Informatique [LaBRI]
dc.contributor.authorDESBARATS, Pascal
hal.structure.identifierLaboratoire Bordelais de Recherche en Informatique [LaBRI]
dc.contributor.authorBALDACCI, Fabien
dc.date.accessioned2024-04-04T02:32:51Z
dc.date.available2024-04-04T02:32:51Z
dc.date.issued2023-04
dc.date.conference2023-04-18
dc.identifier.urihttps://oskar-bordeaux.fr/handle/20.500.12278/190421
dc.description.abstractEnIn clinical practice, the modality of choice for lung diagnosis is usually computed tomography (CT), which exposes patients to ionizing radiations and could potentially affect patients' health. Conversely, MR scan is considered safe and non-invasive but seems challenging due to the low proton density of the lungs and respiratory artifacts. Recently, ultrashort echo-time (UTE) MRI has been developed for lung assessment and shows promising results. In this work, we propose generating 2D synthetic CT slices from UTE MR slices, to improve the image quality and interpretability. Lung MR and CT volumes of 110 patients acquired on the same day were registered using an accurate edge-based non-rigid registration method. We trained and compared paired state-of-the-art generative models based on adversarial, feature-matching and perceptual losses, and also evaluated the impact of conditional batch normalization, namely SPADE [17], on image synthesis. Quantitative and qualitative evaluations showed that this approach was able to synthesize CT images that closely approximate ground truth CT images, and also enables the use of algorithms originally designed for real CT.
dc.language.isoen
dc.publisherIEEE
dc.rights.urihttp://creativecommons.org/licenses/by/
dc.subject.enCT Synthesis
dc.subject.enLung
dc.subject.enUTE MRI
dc.subject.enGenerative Adversarial Networks
dc.title.enLung CT Synthesis Using GANs with Conditional Normalization on Registered Ultrashort Echo-Time MRI
dc.typeCommunication dans un congrès
dc.identifier.doi10.1109/ISBI53787.2023.10230331
dc.subject.halInformatique [cs]/Imagerie médicale
dc.subject.halSciences du Vivant [q-bio]/Médecine humaine et pathologie/Pneumologie et système respiratoire
bordeaux.page1-5
bordeaux.hal.laboratoriesInstitut de Mathématiques de Bordeaux (IMB) - UMR 5251*
bordeaux.institutionUniversité de Bordeaux
bordeaux.institutionBordeaux INP
bordeaux.institutionCNRS
bordeaux.conference.titleISBI 2023 - 20th IEEE International Symposium on Biomedical Imaging
bordeaux.countryCO
bordeaux.conference.cityCartagena de Indias
bordeaux.peerReviewedoui
hal.identifierhal-04268682
hal.version1
hal.invitednon
hal.proceedingsoui
hal.conference.end2023-04-21
hal.popularnon
hal.audienceInternationale
hal.origin.linkhttps://hal.archives-ouvertes.fr//hal-04268682v1
bordeaux.COinSctx_ver=Z39.88-2004&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.date=2023-04&rft.spage=1-5&rft.epage=1-5&rft.au=LONGUEFOSSE,%20Arthur&DOURNES,%20Ga%C3%ABl&BENLALA,%20Ilyes&DENIS%20DE%20SENNEVILLE,%20Baudouin&LAURENT,%20Fran%C3%A7ois&rft.genre=unknown


Fichier(s) constituant ce document

FichiersTailleFormatVue

Il n'y a pas de fichiers associés à ce document.

Ce document figure dans la(les) collection(s) suivante(s)

Afficher la notice abrégée