English

Unsupervised MRI Reconstruction with Generative Adversarial Networks

Image and Video Processing 2020-09-01 v1 Machine Learning Machine Learning

Abstract

Deep learning-based image reconstruction methods have achieved promising results across multiple MRI applications. However, most approaches require large-scale fully-sampled ground truth data for supervised training. Acquiring fully-sampled data is often either difficult or impossible, particularly for dynamic contrast enhancement (DCE), 3D cardiac cine, and 4D flow. We present a deep learning framework for MRI reconstruction without any fully-sampled data using generative adversarial networks. We test the proposed method in two scenarios: retrospectively undersampled fast spin echo knee exams and prospectively undersampled abdominal DCE. The method recovers more anatomical structure compared to conventional methods.

Keywords

Cite

@article{arxiv.2008.13065,
  title  = {Unsupervised MRI Reconstruction with Generative Adversarial Networks},
  author = {Elizabeth K. Cole and John M. Pauly and Shreyas S. Vasanawala and Frank Ong},
  journal= {arXiv preprint arXiv:2008.13065},
  year   = {2020}
}
R2 v1 2026-06-23T18:11:07.238Z