A specificity-preserving generative model for federated MRI translation

Simple item page
buir.contributor.authorDalmaz, Onat
buir.contributor.authorMirza, Usama
buir.contributor.authorElmas, Gökberk
buir.contributor.authorÖzbey, Muzaffer
buir.contributor.authorDar, Salman U. H
buir.contributor.authorÇukur, Tolga
buir.contributor.orcidDalmaz, Onat|0000-0001-7978-5311
buir.contributor.orcidÖzbey, Muzaffer|0000-0002-6262-8915
buir.contributor.orcidÇukur, Tolga|0000-0002-2296-851X
dc.citation.epage88en_US
dc.citation.spage79en_US
dc.citation.volumeNumber13573en_US
dc.contributor.authorDalmaz, Onat
dc.contributor.authorMirza, Usama
dc.contributor.authorElmas, Gökberk
dc.contributor.authorÖzbey, Muzaffer
dc.contributor.authorDar, Salman U. H
dc.contributor.authorÇukur, Tolga
dc.contributor.editorAlbarqouni, Shadi
dc.contributor.editorBakas, Spyridon
dc.contributor.editorBano, Sophia
dc.contributor.editorCardoso, M. Jorge
dc.contributor.editorKhanal, Bishesh
dc.contributor.editorLandman, Bennett
dc.contributor.editorLi, Xiaoxiao
dc.coverage.spatialSingapore, Singaporeen_US
dc.date.accessioned2023-02-16T06:46:53Z
dc.date.available2023-02-16T06:46:53Z
dc.date.issued2022-10-07
dc.departmentDepartment of Electrical and Electronics Engineeringen_US
dc.departmentNational Magnetic Resonance Research Center (UMRAM)en_US
dc.descriptionConference 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 2022en_US
dc.descriptionDate of Conference: 22 September 2022en_US
dc.description.abstractMRI 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.en_US
dc.identifier.doi10.1007/978-3-031-18523-6_8en_US
dc.identifier.eisbn978-3-031-18523-6
dc.identifier.isbn978-3-031-18522-9
dc.identifier.urihttp://hdl.handle.net/11693/111386
dc.language.isoEnglishen_US
dc.publisherSpringer Chamen_US
dc.relation.ispartofseriesLecture Notes in Computer Science;
dc.relation.isversionofhttps://doi.org/10.1007/978-3-031-18523-6_8en_US
dc.source.titleDistributed, Collaborative, and Federated Learning, and Affordable AI and Healthcare for Resource Diverse Global Healthen_US
dc.subjectFederated learningen_US
dc.subjectHeterogeneityen_US
dc.subjectMRIen_US
dc.subjectSite-specificityen_US
dc.subjectTranslationen_US
dc.titleA specificity-preserving generative model for federated MRI translationen_US
dc.typeConference Paperen_US

Files

Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
A_specificity-preserving_generative_model_for_federated_MRI_translation.pdf
Size:
4.2 MB
Format:
Adobe Portable Document Format
Description:
Download
License bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
1.69 KB
Format:
Item-specific license agreed upon to submission
Description:
Download

Collections

Department of Electrical and Electronics Engineering
National Magnetic Resonance Research Center (UMRAM)