Specificity-Preserving Federated Learning for MR Image Reconstruction

Feng, Chun-Mei; Yan, Yunlu; Fu, Huazhu; Xu, Yong; Shao, Ling

doi:10.48550/arxiv.2112.05752

Cited by 5 publications

(24 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To alleviate heterogeneity among sites, recent FL studies on MRI proposed latent-space alignment or split-network approaches based on conditional reconstruction models [34], [35]. Conditional models are trained to map undersampled to fully-sampled acquisitions.…”

Section: Discussionmentioning

confidence: 99%

“…FedMRI: A federated conditional model was trained with a shared encoder and site-specific decoders as described in [35]. The conditional architecture and losses followed GAN cond .…”

Section: B Competing Methodsmentioning

confidence: 99%

“…In addition to loss terms in GAN cond , a contrastive loss was included as in [35]. Weights of (pixel-wise, adversarial, perceptual, contrastive) losses were set as (100, 1, 100, 10).…”

Section: B Competing Methodsmentioning

confidence: 99%

“…A target site was chosen in each communication round, and representations of remaining sites were aligned to the target. In [35], a split reconstruction model was introduced to maintain site-specific and site-general representations. A global encoder and site-specific decoders were trained.…”

Section: Contributionsmentioning

confidence: 99%

“…In [34], adversarial alignment between source and target sites was proposed to improve similarity of latent-space representations in reconstruction models. In [35], reconstruction models were split into a global encoder shared across sites, followed by local decoders trained separately at each site. Despite improved performance against across-site variability, both methods are based on conditional reconstruction models that assume explicit knowledge of the imaging operator.…”

mentioning

confidence: 99%

See 4 more Smart Citations

Federated Learning of Generative Image Priors for MRI Reconstruction

Elmas¹,

Dar²,

Korkmaz³

et al. 2022

Preprint

View full text Add to dashboard Cite

Multi-institutional efforts can facilitate training of deep MRI reconstruction models, albeit privacy risks arise during cross-site sharing of imaging data. Federated learning (FL) has recently been introduced to address privacy concerns by enabling distributed training without transfer of imaging data. Existing FL methods for MRI reconstruction employ conditional models to map from undersampled to fully-sampled acquisitions via explicit knowledge of the imaging operator. Since conditional models generalize poorly across different acceleration rates or sampling densities, imaging operators must be fixed between training and testing, and they are typically matched across sites. To improve generalization and flexibility in multi-institutional collaborations, here we introduce a novel method for MRI reconstruction based on Federated learning of Generative IMage Priors (FedGIMP). FedGIMP leverages a two-stage approach: cross-site learning of a generative MRI prior, and subject-specific injection of the imaging operator. The global MRI prior is learned via an unconditional adversarial model that synthesizes high-quality MR images based on latent variables. Specificity in the prior is preserved via a mapper subnetwork that produces sitespecific latents. During inference, the prior is combined with subject-specific imaging operators to enable reconstruction, and further adapted to individual test samples by minimizing data-consistency loss. Comprehensive experiments on multi-institutional datasets clearly demonstrate enhanced generalization performance of FedGIMP against site-specific and federated methods based on conditional models, as well as traditional reconstruction methods.

show abstract

Section: Discussionmentioning

confidence: 99%

“…FedMRI: A federated conditional model was trained with a shared encoder and site-specific decoders as described in [35]. The conditional architecture and losses followed GAN cond .…”

Section: B Competing Methodsmentioning

confidence: 99%

“…In addition to loss terms in GAN cond , a contrastive loss was included as in [35]. Weights of (pixel-wise, adversarial, perceptual, contrastive) losses were set as (100, 1, 100, 10).…”

Section: B Competing Methodsmentioning

confidence: 99%

Section: Contributionsmentioning

confidence: 99%

mentioning

confidence: 99%

See 3 more Smart Citations

Federated Learning of Generative Image Priors for MRI Reconstruction

Elmas¹,

Dar²,

Korkmaz³

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

A Specificity-Preserving Generative Model for Federated MRI Translation

Dalmaz

Usama

Elmas

et al. 2022

Lecture Notes in Computer Science

View full text Add to dashboard Cite

MRI 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, FLtrained 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.

show abstract

Federated Learning of Generative Image Priors for MRI Reconstruction

Elmas

Dar

Korkmaz

et al. 2023

IEEE Trans. Med. Imaging

View full text Add to dashboard Cite

Multi-institutional efforts can facilitate training of deep MRI reconstruction models, albeit privacy risks arise during cross-site sharing of imaging data. Federated learning (FL) has recently been introduced to address privacy concerns by enabling distributed training without transfer of imaging data. Existing FL methods employ conditional reconstruction models to map from undersampled to fully-sampled acquisitions via explicit knowledge of the accelerated imaging operator. Since conditional models generalize poorly across different acceleration rates or sampling densities, imaging operators must be fixed between training and testing, and they are typically matched across sites. To improve patient privacy, performance and flexibility in multi-site collaborations, here we introduce Federated learning of Generative IMage Priors (FedGIMP) for MRI reconstruction. FedGIMP leverages a two-stage approach: cross-site learning of a generative MRI prior, and prior adaptation following injection of the imaging operator. The global MRI prior is learned via an unconditional adversarial model that synthesizes high-quality MR images based on latent variables. A novel mapper subnetwork produces site-specific latents to maintain specificity in the prior. During inference, the prior is first combined with subject-specific imaging operators to enable reconstruction, and it is then adapted to individual cross-sections by minimizing a data-consistency loss. Comprehensive experiments on multi-institutional datasets clearly demonstrate enhanced performance of FedGIMP against both centralized and FL methods based on conditional models.

show abstract

Specificity-Preserving Federated Learning for MR Image Reconstruction

Cited by 5 publications

References 31 publications

Federated Learning of Generative Image Priors for MRI Reconstruction

Federated Learning of Generative Image Priors for MRI Reconstruction

A Specificity-Preserving Generative Model for Federated MRI Translation

Federated Learning of Generative Image Priors for MRI Reconstruction

Contact Info

Product

Resources

About