Dalmaz, OnatMirza, UsamaElmas, GökberkÖzbey, MuzafferDar, Salman U. HÇukur, TolgaAlbarqouni, ShadiBakas, SpyridonBano, SophiaCardoso, M. JorgeKhanal, BisheshLandman, BennettLi, Xiaoxiao2023-02-162023-02-162022-10-07978-3-031-18522-9http://hdl.handle.net/11693/111386Conference Name: 3rd MICCAI Workshop on Distributed, Collaborative, and Federated Learning, DeCaF 2022, and the 2nd MICCAI Workshop on Affordable AI and Healthcare, FAIR 2022, held in conjunction with the 25th International Conference on Medical Image Computing and Computer Assisted Intervention, MICCAI 2022Date of Conference: 22 September 2022MRI translation models learn a mapping from an acquired source contrast to an unavailable target contrast. Collaboration between institutes is essential to train translation models that can generalize across diverse datasets. That said, aggregating all imaging data and training a centralized model poses privacy problems. Recently, federated learning (FL) has emerged as a collaboration framework that enables decentralized training to avoid sharing of imaging data. However, FL-trained translation models can deteriorate by the inherent heterogeneity in the distribution of MRI data. To improve reliability against domain shifts, here we introduce a novel specificity-preserving FL method for MRI contrast translation. The proposed approach is based on an adversarial model that adaptively normalizes the feature maps across the generator based on site-specific latent variables. Comprehensive FL experiments were conducted on multi-site datasets to show the effectiveness of the proposed approach against prior federated methods in MRI contrast translation.EnglishFederated learningHeterogeneityMRISite-specificityTranslationConference Paper10.1007/978-3-031-18523-6_8978-3-031-18523-6