Ferumoxytol-Enhanced Cardiac Cine MRI Reconstruction Using a Variable-Splitting Spatiotemporal Network

被引：1

作者：

Gao, Chang ^{[1
,2
]}

Ming, Zhengyang ^{[1
,2
]}

Nguyen, Kim-Lien ^{[1
,2
,3
,4
]}

Pang, Jianing ^{[5
]}

Bedayat, Arash ^{[2
]}

Dale, Brian M. ^{[6
]}

Zhong, Xiaodong ^{[7
]}

Finn, J. Paul ^{[1
,2
,8
]}

机构：

[1] Univ Calif Angeles, Dept Phys & Biol Med, Los Angeles, CA USA

[2] Univ Calif Los Angeles, Dept Radiol Sci, Los Angeles, CA USA

[3] Univ Calif Los Angeles, Div Cardiol, Los Angeles, CA 90024 USA

[4] VA Greater Los Angeles Healthcare Syst, Los Angeles, CA USA

[5] Siemens Med Solut USA Inc, MR R&D Collaborat, Chicago, IL USA

[6] Siemens Med Solut USA Inc, MR R&D Collaborat, Cary, NC USA

[7] Siemens Med Solut USA Inc, MR R&D Collaborat, Los Angeles, CA USA

[8] Peter V Ueberroth Bldg,Suite 3371,10945 Le Conte A, Los Angeles, CA 90095 USA

来源：

JOURNAL OF MAGNETIC RESONANCE IMAGING | 2024年 / 60卷 / 06期

关键词：

cardiac GRE cine MRI; ferumoxytol; deep learning; image reconstruction; congenital heart disease; ACQUISITION; ANGIOGRAPHY; HEART; MASS;

D O I：

10.1002/jmri.29295

中图分类号：

R8 [特种医学]; R445 [影像诊断学];

学科分类号：

1002 ; 100207 ; 1009 ;

摘要：

Background: Balanced steady-state free precession (bSSFP) imaging is commonly used in cardiac cine MRI but prone to image artifacts. Ferumoxytol-enhanced (FE) gradient echo (GRE) has been proposed as an alternative. Utilizing the abundance of bSSFP images to develop a computationally efficient network that is applicable to FE GRE cine would benefit future network development. Purpose: To develop a variable-splitting spatiotemporal network (VSNet) for image reconstruction, trained on bSSFP cine images and applicable to FE GRE cine images. Study Type: Retrospective and prospective. Subjects: 41 patients (26 female, 53 +/- 19 y/o) for network training, 31 patients (19 female, 49 +/- 17 y/o) and 5 healthy subjects (5 female, 30 +/- 7 y/o) for testing. Field Strength/Sequence: 1.5T and 3T, bSSFP and GRE. Assessment: VSNet was compared to VSNet with total variation loss, compressed sensing and low rank methods for 14x accelerated data. The GRAPPAx2/x3 images served as the reference. Peak signal-to-noise-ratio (PSNR), structural similarity index (SSIM), left ventricular (LV) and right ventricular (RV) end-diastolic volume (EDV), end-systolic volume (ESV), and ejection fraction (EF) were measured. Qualitative image ranking and scoring were independently performed by three readers. Latent scores were calculated based on scores of each method relative to the reference. Statistics: Linear mixed-effects regression, Tukey method, Fleiss' Kappa, Bland-Altman analysis, and Bayesian categorical cumulative probit model. A P-value <0.05 was considered statistically significant. Results: VSNet achieved significantly higher PSNR (32.7 +/- 0.2), SSIM (0.880 +/- 0.004), rank (2.14 +/- 0.06), and latent scores (-1.72 +/- 0.22) compared to other methods (rank >2.90, latent score < -2.63). Fleiss' Kappa was 0.52 for scoring and 0.61 for ranking. VSNet showed no significantly different LV and RV ESV (P = 0.938) and EF (P = 0.143) measurements, but statistically significant different (2.62 mL) EDV measurements compared to the reference. Conclusion: VSNet produced the highest image quality and the most accurate functional measurements for FE GRE cine images among the tested 14x accelerated reconstruction methods. Level of Evidence: 3 Technical Efficacy: Stage 1

引用

页码：2356 / 2368

页数：13