Health Research Alliance
Browse
nihms-1701116.pdf (1.93 MB)

nihms-1701116.pdf

Download (1.93 MB)
journal contribution
posted on 2023-01-15, 17:25 authored by Mohamad Abdi, Xue Feng, Changyu Sun, Kenneth C. Bilchick, Craig H. Meyer, Frederick H. Epstein

    

Purpose: To employ deep learning for suppression of the artifact-generating T1-relaxation echo in cine displacement encoding with stimulated echoes (DENSE) for the purpose of reducing the scan time. 

Methods: A U-Net was trained to suppress the artifact-generating T1-relaxation echo using complementary phase-cycled data as the ground truth. A data augmentation method was developed that generates synthetic DENSE images with arbitrary displacement encoding frequencies to suppress the T1-relaxation echo modulated for a range of frequencies. The resulting U-Net (DAS- Net) was compared to a k-space zero-filling as an alternative method. Non-phase-cycled DENSE images acquired in shorter breath-holds were processed by DAS-Net and compared to DENSE images acquired with phase-cycling for the quantification of myocardial strain. 

Results: DAS-Net effectively suppressed the T1-relaxation echo and its artifacts, and achieved root mean square error (RMSE) = 5.5±0.8 and structural similarity index (SSIM) = 0.85±0.02 for DENSE images acquired with a displacement encoding frequency of 0.10 cycles/mm. DAS-Net outperformed zero-filling (RMSE = 5.8±1.5 vs 13.5±1.5, DAS-Net vs zero-filling, p<0.01 and SSIM = 0.83±0.04 vs 0.66±0.03, DAS-Net vs zero-filling, p<0.01). Strain data for non-phase- cycled DENSE images with DAS-Net showed close agreement with strain from phase-cycled DENSE. 

Conclusion: DAS-Net provides an effective alternative approach for suppression of the artifact- generating T1-relaxation echo in DENSE MRI, enabling a 42% reduction in scan time compared to DENSE with phase-cycling. 

History

Grant ID

19AIML35210327

Usage metrics

    American Heart Association

    Licence

    Exports

    RefWorks
    BibTeX
    Ref. manager
    Endnote
    DataCite
    NLM
    DC