{"database":"biostudies-literature","file_versions":[],"scores":null,"additional":{"submitter":["Haberl D"],"funding":["ERACoSysMed","Medical University of Vienna"],"pagination":["2532-2546"],"full_dataset_link":["https://www.ebi.ac.uk/biostudies/studies/S-EPMC11224088"],"repository":["biostudies-literature"],"omics_type":["Unknown"],"volume":["51(9)"],"pubmed_abstract":["Purpose
To improve reproducibility and predictive performance of PET radiomic features in multicentric studies by cycle-consistent generative adversarial network (GAN) harmonization approaches.Methods
GAN-harmonization was developed to harmonize whole-body PET scans to perform image style and texture translation between different centers and scanners. GAN-harmonization was evaluated by application to two retrospectively collected open datasets and different tasks. First, GAN-harmonization was performed on a dual-center lung cancer cohort (127 female, 138 male) where the reproducibility of radiomic features in healthy liver tissue was evaluated. Second, GAN-harmonization was applied to a head and neck cancer cohort (43 female, 154 male) acquired from three centers. Here, the"],"journal":["European journal of nuclear medicine and molecular imaging"],"pubmed_title":["Multicenter PET image harmonization using generative adversarial networks."],"pmcid":["PMC11224088"],"funding_grant_id":["4724-B HOLY 2020"],"pubmed_authors":["Spielvogel CP","Haug AR","Jiang Z","Buvat I","Orlhac F","Papp L","Iommi D","Carrio I","Haberl D"],"additional_accession":[]},"is_claimable":false,"name":"Multicenter PET image harmonization using generative adversarial networks.","description":"Purpose
To improve reproducibility and predictive performance of PET radiomic features in multicentric studies by cycle-consistent generative adversarial network (GAN) harmonization approaches.Methods
GAN-harmonization was developed to harmonize whole-body PET scans to perform image style and texture translation between different centers and scanners. GAN-harmonization was evaluated by application to two retrospectively collected open datasets and different tasks. First, GAN-harmonization was performed on a dual-center lung cancer cohort (127 female, 138 male) where the reproducibility of radiomic features in healthy liver tissue was evaluated. Second, GAN-harmonization was applied to a head and neck cancer cohort (43 female, 154 male) acquired from three centers. Here, the","dates":{"release":"2024-01-01T00:00:00Z","publication":"2024 Jul","modification":"2025-04-18T13:51:28.369Z","creation":"2025-04-04T12:54:42.758Z"},"accession":"S-EPMC11224088","cross_references":{"pubmed":["38696130"],"doi":["10.1007/s00259-024-06708-8"]}}