Efficient and Phase-aware Video Super-resolution for Cardiac MRI

TL;DR

This paper introduces a novel, end-to-end trainable video super-resolution network for cardiac MRI that leverages cardiac cycle knowledge and residual learning to enhance image quality without hardware changes.

Contribution

It presents a phase-aware, cyclic knowledge-based model with residual of residual learning for improved cardiac MRI super-resolution.

Findings

Outperforms state-of-the-art methods on large-scale datasets.

Effectively utilizes cardiac cycle information for super-resolution.

Adaptive refinement improves reconstruction quality.

Abstract

Cardiac Magnetic Resonance Imaging (CMR) is widely used since it can illustrate the structure and function of heart in a non-invasive and painless way. However, it is time-consuming and high-cost to acquire the high-quality scans due to the hardware limitation. To this end, we propose a novel end-to-end trainable network to solve CMR video super-resolution problem without the hardware upgrade and the scanning protocol modifications. We incorporate the cardiac knowledge into our model to assist in utilizing the temporal information. Specifically, we formulate the cardiac knowledge as the periodic function, which is tailored to meet the cyclic characteristic of CMR. In addition, the proposed residual of residual learning scheme facilitates the network to learn the LR-HR mapping in a progressive refinement fashion. This mechanism enables the network to have the adaptive capability by adjusting refinement iterations depending on the difficulty of the task. Extensive experimental results on large-scale datasets demonstrate the superiority of the proposed method compared with numerous state-of-the-art methods.