Cargando…

Federated End-to-End Unrolled Models for Magnetic Resonance Image Reconstruction

Image reconstruction is the process of recovering an image from raw, under-sampled signal measurements, and is a critical step in diagnostic medical imaging, such as magnetic resonance imaging (MRI). Recently, data-driven methods have led to improved image quality in MRI reconstruction using a limit...

Descripción completa

Detalles Bibliográficos
Autores principales: Levac, Brett R., Arvinte, Marius, Tamir, Jonathan I.
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2023
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10045102/
https://www.ncbi.nlm.nih.gov/pubmed/36978755
http://dx.doi.org/10.3390/bioengineering10030364
_version_ 1784913516984008704
author Levac, Brett R.
Arvinte, Marius
Tamir, Jonathan I.
author_facet Levac, Brett R.
Arvinte, Marius
Tamir, Jonathan I.
author_sort Levac, Brett R.
collection PubMed
description Image reconstruction is the process of recovering an image from raw, under-sampled signal measurements, and is a critical step in diagnostic medical imaging, such as magnetic resonance imaging (MRI). Recently, data-driven methods have led to improved image quality in MRI reconstruction using a limited number of measurements, but these methods typically rely on the existence of a large, centralized database of fully sampled scans for training. In this work, we investigate federated learning for MRI reconstruction using end-to-end unrolled deep learning models as a means of training global models across multiple clients (data sites), while keeping individual scans local. We empirically identify a low-data regime across a large number of heterogeneous scans, where a small number of training samples per client are available and non-collaborative models lead to performance drops. In this regime, we investigate the performance of adaptive federated optimization algorithms as a function of client data distribution and communication budget. Experimental results show that adaptive optimization algorithms are well suited for the federated learning of unrolled models, even in a limited-data regime (50 slices per data site), and that client-sided personalization can improve reconstruction quality for clients that did not participate in training.
format Online
Article
Text
id pubmed-10045102
institution National Center for Biotechnology Information
language English
publishDate 2023
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-100451022023-03-29 Federated End-to-End Unrolled Models for Magnetic Resonance Image Reconstruction Levac, Brett R. Arvinte, Marius Tamir, Jonathan I. Bioengineering (Basel) Article Image reconstruction is the process of recovering an image from raw, under-sampled signal measurements, and is a critical step in diagnostic medical imaging, such as magnetic resonance imaging (MRI). Recently, data-driven methods have led to improved image quality in MRI reconstruction using a limited number of measurements, but these methods typically rely on the existence of a large, centralized database of fully sampled scans for training. In this work, we investigate federated learning for MRI reconstruction using end-to-end unrolled deep learning models as a means of training global models across multiple clients (data sites), while keeping individual scans local. We empirically identify a low-data regime across a large number of heterogeneous scans, where a small number of training samples per client are available and non-collaborative models lead to performance drops. In this regime, we investigate the performance of adaptive federated optimization algorithms as a function of client data distribution and communication budget. Experimental results show that adaptive optimization algorithms are well suited for the federated learning of unrolled models, even in a limited-data regime (50 slices per data site), and that client-sided personalization can improve reconstruction quality for clients that did not participate in training. MDPI 2023-03-16 /pmc/articles/PMC10045102/ /pubmed/36978755 http://dx.doi.org/10.3390/bioengineering10030364 Text en © 2023 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Levac, Brett R.
Arvinte, Marius
Tamir, Jonathan I.
Federated End-to-End Unrolled Models for Magnetic Resonance Image Reconstruction
title Federated End-to-End Unrolled Models for Magnetic Resonance Image Reconstruction
title_full Federated End-to-End Unrolled Models for Magnetic Resonance Image Reconstruction
title_fullStr Federated End-to-End Unrolled Models for Magnetic Resonance Image Reconstruction
title_full_unstemmed Federated End-to-End Unrolled Models for Magnetic Resonance Image Reconstruction
title_short Federated End-to-End Unrolled Models for Magnetic Resonance Image Reconstruction
title_sort federated end-to-end unrolled models for magnetic resonance image reconstruction
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10045102/
https://www.ncbi.nlm.nih.gov/pubmed/36978755
http://dx.doi.org/10.3390/bioengineering10030364
work_keys_str_mv AT levacbrettr federatedendtoendunrolledmodelsformagneticresonanceimagereconstruction
AT arvintemarius federatedendtoendunrolledmodelsformagneticresonanceimagereconstruction
AT tamirjonathani federatedendtoendunrolledmodelsformagneticresonanceimagereconstruction