English

Improving Multi-Center Generalizability of GAN-Based Fat Suppression using Federated Learning

Image and Video Processing 2024-04-12 v1 Computer Vision and Pattern Recognition Machine Learning

Abstract

Generative Adversarial Network (GAN)-based synthesis of fat suppressed (FS) MRIs from non-FS proton density sequences has the potential to accelerate acquisition of knee MRIs. However, GANs trained on single-site data have poor generalizability to external data. We show that federated learning can improve multi-center generalizability of GANs for synthesizing FS MRIs, while facilitating privacy-preserving multi-institutional collaborations.

Keywords

Cite

@article{arxiv.2404.07374,
  title  = {Improving Multi-Center Generalizability of GAN-Based Fat Suppression using Federated Learning},
  author = {Pranav Kulkarni and Adway Kanhere and Harshita Kukreja and Vivian Zhang and Paul H. Yi and Vishwa S. Parekh},
  journal= {arXiv preprint arXiv:2404.07374},
  year   = {2024}
}

Comments

5 pages, 2 figures

R2 v1 2026-06-28T15:50:33.552Z