arXiv subjects

Jerome Yerly

Publications and source records attributed to Jerome Yerly.

3 recordsLinked to original sources

arXiv2025

VPAL: A novel method to reduce reconstruction time for 5D free-running imaging

Purpose: Ferumoxytal-enhanced 5D free-running whole heart CMR provides image quality comparable to CTA, but requires hours-long reconstruction time, preventing clinical usage. This study developed a variable projection augmented Lagrangian (VPAL) method for 5D motion-resolved image reconstruction and compared it with alternating direction method of multipliers (ADMM) in five numerical simulations and 15 in-vivo pediatric data set. Approach: Relative error of the reconstructed images against the ground-truth images was assessed in numerical simulations. In-vivo analysis compared reconstruction time, mid-short axis (SA) blood-myocardium sharpness, left ventricular ejection fraction (LVEF), and a radiologist's image quality ratings between VPAL and ADMM. A paired t-test (p<0.05) was used to determine statistical significance, while linear regression and Bland-Altman analysis for agreement assessments. Results: VPAL and ADMM had similar relative errors compared to the ground truth, p = 0.07. In in-vivo datasets, VPAL reduced the reconstruction time from 16.3 +/- 3.6 hours (ADMM) to 4.7 +/- 1.1 hours (VPAL), p=1e-10. Blood-myocardium border sharpness in VPAL closely correlates to ADMM , R^2 = 0.97. The LVEFs values measured by VPAL and ADMM reconstructions are largely similar, 56 +/- 6 % in ADMM and 56 +/- 6 % in VPAL, p=0.55. Both VPAL and ADMM reconstructions have good to excellent diagnostic ratings (VPAL vs. ADMM: 3.9 +/- 0.3 vs. 3.8 +/- 0.4 in 2-chamber; 3.9 +/- 0.4 vs. 3.9 +/- in 4-chamber; 3.7 +/- 0.5 vs. 3.7 +/- 0.5 in mid-SA reformatted views. Conclusion: VPAL enables faster reconstruction than ADMM while maintaining equivalent image quality for functional assessments, supporting its potential for clinical use.

physics.med-ph↗

arXiv2021

Time-Dependent Deep Image Prior for Dynamic MRI

We propose a novel unsupervised deep-learning-based algorithm for dynamic magnetic resonance imaging (MRI) reconstruction. Dynamic MRI requires rapid data acquisition for the study of moving organs such as the heart. Existing reconstruction methods suffer from restrictions either in the model design or in the absence of ground-truth data, resulting in low image quality. We introduce a generalized version of the deep-image-prior approach, which optimizes the network weights to fit a sequence of sparsely acquired dynamic MRI measurements. Our method needs neither prior training nor additional data. In particular, for cardiac images, it does not require the marking of heartbeats or the reordering of spokes. The key ingredients of our method are threefold: 1) a fixed low-dimensional manifold that encodes the temporal variations of images; 2) a network that maps the manifold into a more expressive latent space; and 3) a convolutional neural network that generates a dynamic series of MRI images from the latent variables and that favors their consistency with the measurements in k-space. Our method outperforms the state-of-the-art methods quantitatively and qualitatively in both retrospective and real fetal cardiac datasets. To the best of our knowledge, this is the first unsupervised deep-learning-based method that can reconstruct the continuous variation of dynamic MRI sequences with high spatial resolution.

eess.IV↗

arXiv2019

Natively Fat-Suppressed 5D Whole-Heart MRI with a Radial Free-Running Fast-Interrupted Steady-State (FISS) Sequence at 1.5T and 3T

Purpose: To implement, optimize and test fast interrupted steady-state (FISS) for natively fat-suppressed free-running 5D whole-heart MRI at 1.5T and 3T. Methods: FISS was implemented for fully self-gated free-running cardiac- and respiratory-motion-resolved radial imaging of the heart at 1.5T and 3T. Numerical simulations and phantom scans were performed to compare fat suppression characteristics and to determine parameter ranges (readouts per FISS module (NR) and repetition time (TR)) for effective fat suppression. Subsequently, free-running FISS data were collected in ten healthy volunteers. All acquisitions were compared with a continuous bSSFP version of the same sequence, and both fat suppression and scan times were analyzed. Results: Simulations demonstrate a variable width and location of suppression bands in FISS that was dependent on TR and NR. For a fat suppression bandwidth of 100Hz and NR below 8, simulations demonstrated that a TR between 2.2ms and 3.0ms is required at 1.5T while a range of 3.0ms to 3.5ms applies at 3T. Fat signal increases with NR. These findings were corroborated in phantom experiments. In volunteers, fat SNR was significantly decreased using FISS compared with bSSPF at both field strengths. After protocol optimization, high-resolution (1.1mm x 1.1mm x 1.1mm) 5D whole-heart free-running FISS can be performed with effective fat suppression in under 8 min at 1.5T and 3T at a modest scan time increase compared to bSSFP.Conclusion: An optimal FISS parameter range was determined enabling natively fat-suppressed 5D whole-heart free-running MRI with a single continuous scan at 1.5T and 3T, demonstrating potential for cardiac imaging and noncontrast angiography.

physics.med-ph↗