Accelerated chemical shift encoded cardiovascular magnetic resonance imaging with use of a resolution enhancement network

Abstract

ABSTRACT: Background: Cardiovascular magnetic resonance (CMR) chemical shift encoding (CSE) enables myocardial fat imaging. We sought to develop a deep learning network (fast chemical shift encoding [FastCSE]) to accelerate CSE. Methods: FastCSE was built on a super-resolution generative adversarial network extended to enhance complex-valued image sharpness. FastCSE enhances each echo image independently before water-fat separation. FastCSE was trained with retrospectively identified cines from 1519 patients (56 ± 16 years; 866 men) referred for clinical 3T CMR. In a prospective study of 16 participants (58 ± 19 years; 7 females) and 5 healthy individuals (32 ± 17 years; 5 females), dual-echo CSE images were collected with 1.5 × 1.5 mm2, 2.5 × 1.5 mm2, and 3.8 × 1.9 mm2 resolution using generalized autocalibrating partially parallel acquisition (GRAPPA). FastCSE was applied to images collected with resolution of 2.5 × 1.5 mm2 and 3.8 × 1.9 mm2 to restore sharpness. Fat images obtained from two-point Dixon reconstruction were evaluated using a quantitative blur metric and analyzed with a five-way analysis of variance. Results: FastCSE successfully reconstructed CSE images inline. FastCSE acquisition, with a resolution of 2.5 × 1.5 mm2 and 3.8 × 1.9 mm2, reduced the number of breath-holds without impacting visualization of fat by approximately 1.5-fold and 3-fold compared to GRAPPA acquisition with a resolution of 1.5 × 1.5 mm2, from 3.0 ± 0.8 breath-holds to 2.0 ± 0.2 and 1.1 ± 0.4 breath-holds, respectively. FastCSE improved image sharpness and removed ringing artifacts in GRAPPA fat images acquired with a resolution of 2.5 × 1.5 mm2 (0.32 ± 0.03 vs 0.35 ± 0.04, P < 0.001) and 3.8 × 1.9 mm2 (0.32 ± 0.03 vs 0.43 ± 0.06, P < 0.001). Blurring in FastCSE images was similar to blurring in images with 1.5 × 1.5 mm2 resolution (0.32 ± 0.03 vs 0.31 ± 0.03, P = 0.57; 0.32 ± 0.03 vs 0.31 ± 0.03, P = 0.66). Conclusion: We showed that a deep learning-accelerated CSE technique based on complex-valued resolution enhancement can reduce the number of breath-holds in CSE imaging without impacting the visualization of fat. FastCSE showed similar image sharpness compared to a standardized parallel imaging method.

Keywords

• Deep learning
• Chemical shift encoding
• Super-resolution
• Dixon
• Myocardial fat