Unsupervised MRI Reconstruction with Generative Adversarial Networks

作者：Elizabeth K. Cole, John M. Pauly, Shreyas Vasanawala, Frank Ong · 发表于：arXiv (Cornell University) · 年份：2020 · DOI：10.48550/arxiv.2008.13065 · 被引用次数：33 · 研究领域：Advanced MRI Techniques and Applications、Medical Imaging Techniques and Applications、Advanced Neuroimaging Techniques and Applications

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.