Deep Separable Spatiotemporal Learning for Fast Dynamic Cardiac MRI

TL;DR

This paper introduces DeepSSL, a novel deep learning approach for fast cardiac MRI reconstruction that effectively reduces training data requirements by leveraging spatiotemporal priors and a separable learning scheme, improving image quality and interpretability.

Contribution

The work presents a new Deep Separable Spatiotemporal Learning network that unrolls a 2D spatiotemporal model, enabling high-quality MRI reconstruction with limited training data.

Findings

Outperforms state-of-the-art methods visually and quantitatively.

Reduces training data needs by up to 75%.

Improves downstream cardiac segmentation accuracy.

Abstract

Dynamic magnetic resonance imaging (MRI) plays an indispensable role in cardiac diagnosis. To enable fast imaging, the k-space data can be undersampled but the image reconstruction poses a great challenge of high-dimensional processing. This challenge necessitates extensive training data in deep learning reconstruction methods. In this work, we propose a novel and efficient approach, leveraging a dimension-reduced separable learning scheme that can perform exceptionally well even with highly limited training data. We design this new approach by incorporating spatiotemporal priors into the development of a Deep Separable Spatiotemporal Learning network (DeepSSL), which unrolls an iteration process of a 2D spatiotemporal reconstruction model with both temporal low-rankness and spatial sparsity. Intermediate outputs can also be visualized to provide insights into the network behavior and enhance interpretability. Extensive results on cardiac cine datasets demonstrate that the proposed DeepSSL surpasses state-of-the-art methods both visually and quantitatively, while reducing the demand for training cases by up to 75%. Additionally, its preliminary adaptability to unseen cardiac patients has been verified through a blind reader study conducted by experienced radiologists and cardiologists. Furthermore, DeepSSL enhances the accuracy of the downstream task of cardiac segmentation and exhibits robustness in prospectively undersampled real-time cardiac MRI.