biostudies-literatureHaberl DERACoSysMedMedical University of Vienna2532-2546https://www.ebi.ac.uk/biostudies/studies/S-EPMC11224088biostudies-literatureUnknown51(9)<h4>Purpose</h4>To improve reproducibility and predictive performance of PET radiomic features in multicentric studies by cycle-consistent generative adversarial network (GAN) harmonization approaches.<h4>Methods</h4>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, theEuropean journal of nuclear medicine and molecular imagingMulticenter PET image harmonization using generative adversarial networks.PMC112240884724-B HOLY 2020Spielvogel CPHaug ARJiang ZBuvat IOrlhac FPapp LIommi DCarrio IHaberl DfalseMulticenter PET image harmonization using generative adversarial networks.<h4>Purpose</h4>To improve reproducibility and predictive performance of PET radiomic features in multicentric studies by cycle-consistent generative adversarial network (GAN) harmonization approaches.<h4>Methods</h4>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, the2024-01-01T00:00:00Z2024 Jul2025-04-18T13:51:28.369Z2025-04-04T12:54:42.758ZS-EPMC112240883869613010.1007/s00259-024-06708-8