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.
@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}
}