Unsupervised MRI Reconstruction with Generative Adversarial Networks
This addresses the challenge of acquiring fully-sampled data for supervised training in MRI applications like DCE and cardiac cine, offering an incremental improvement for medical imaging.
The paper tackles the problem of MRI reconstruction without fully-sampled ground truth data, which is often difficult to acquire, and shows that their unsupervised method using generative adversarial networks recovers more anatomical structure compared to conventional methods in knee and abdominal DCE scenarios.
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.