Federated Learning of Generative Image Priors for MRI Reconstruction

by   Gokberk Elmas, et al.

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 site-specific 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.



page 1

page 2

page 3

page 7

page 8


Federated Whole Prostate Segmentation in MRI with Personalized Neural Architectures

Building robust deep learning-based models requires diverse training dat...

Multi-institutional Collaborations for Improving Deep Learning-based Magnetic Resonance Image Reconstruction Using Federated Learning

Fast and accurate reconstruction of magnetic resonance (MR) images from ...

Scanner Invariant Representations for Diffusion MRI Harmonization

Pooled imaging data from multiple sources is subject to variation betwee...

Unsupervised MRI Reconstruction via Zero-Shot Learned Adversarial Transformers

Supervised deep learning has swiftly become a workhorse for accelerated ...

Federated Learning with Research Prototypes for Multi-Center MRI-based Detection of Prostate Cancer with Diverse Histopathology

Early prostate cancer detection and staging from MRI are extremely chall...

FedHarmony: Unlearning Scanner Bias with Distributed Data

The ability to combine data across scanners and studies is vital for neu...

MRQy: An Open-Source Tool for Quality Control of MR Imaging Data

Even as public data repositories such as The Cancer Imaging Archive (TCI...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.