Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userHigh-resolution neural network-driven mapping of multiple diffusion metrics leveraging asymmetries in the balanced SSFP frequency profile
216
0
0.0
(
0
)
Ask ChatGPT about the research
No Arabic abstract
We suggest to utilize the rich information content about microstructural tissue properties entangled in asymmetric balanced steady-state free precession (bSSFP) profiles to estimate multiple diffusion metrics simultaneously by neural network (NN) parameter quantification. A 12-point bSSFP phase-cycling scheme with high-resolution whole-brain coverage is employed at 3 T and 9.4 T for NN input. Low-resolution target diffusion data are derived based on diffusion-weighted spin-echo echo-planar-imaging (SE-EPI) scans, i.e., mean, axial, and radial diffusivity (MD, AD, RD), fractional anisotropy (FA) as well as the spherical coordinates (azimuth ${Phi}$ and inclination ${Theta}$) of the principal diffusion eigenvector. A feedforward NN is trained with incorporated probabilistic uncertainty estimation. The NN predictions yielded highly reliable results in white matter (WM) and gray matter (GM) structures for MD. The quantification of FA, AD, and RD was overall in good agreement with the reference but the dependence of these parameters on WM anisotropy was somewhat biased, e.g., in corpus callosum. The inclination ${Theta}$ was well predicted for anisotropic WM structures while the azimuth ${Phi}$ was overall poorly predicted. The findings were highly consistent across both field strengths. Application of the optimized NN to high-resolution input data provided whole-brain maps with rich structural details. In conclusion, the proposed NN-driven approach showed potential to provide distortion-free high-resolution whole-brain maps of multiple diffusion metrics at high to ultra-high field strengths in clinically relevant scan times.
rate research
Read More
Head motion is inevitable in the acquisition of diffusion-weighted images, especially for certain motion-prone subjects and for data gathering of advanced diffusion models with prolonged scan times. Deficient accuracy of motion correction cause deterioration in the quality of diffusion model reconstruction, thus affecting the derived measures. This results in either loss of data, or introducing bias in outcomes from data of different motion levels, or both. Hence minimizing motion effects and reutilizing motion-contaminated data becomes vital to quantitative studies. We have previously developed a 3-dimensional hierarchical convolution neural network (3D H-CNN) for robust diffusion kurtosis mapping from under-sampled data. In this study, we propose to extend this method to motion-contaminated data for robust recovery of diffusion model-derived measures with a process of motion assessment and corrupted volume rejection. We validate the proposed pipeline in two in-vivo datasets. Results from the first dataset of individual subjects show that all the diffusion tensor and kurtosis tensor-derived measures from the new pipeline are minimally sensitive to motion effects, and are comparable to the motion-free reference with as few as eight volumes retained from the motion-contaminated data. Results from the second dataset of a group of children with attention deficit hyperactivity disorder demonstrate the ability of our approach in ameliorating spurious group differences due to head motion. This method shows great potential for exploiting some valuable but motion-corrupted DWI data which are likely to be discarded otherwise, and applying to data with different motion level thus improving their utilization and statistic power.
Purpose: To develop a novel quantitative method for detection of different tissue compartments based on bSSFP signal profile asymmetries (SPARCQ) and to provide a validation and proof-of-concept for voxel-wise water-fat separation and fat fraction mapping. Methods: The SPARCQ framework uses phase-cycled bSSFP acquisitions to obtain bSSFP signal profiles. For each voxel, the profile is decomposed into a weighted sum of simulated profiles with specific off-resonance and relaxation time ratios. From the obtained set of weights, voxel-wise estimations of the fractions of the different components and their equilibrium magnetization are extracted. For the entire image volume, component-specific quantitative maps as well as banding-artifact-free images are generated. A SPARCQ proof-of-concept was provided for water-fat separation and fat fraction mapping. Noise robustness was assessed using simulations. A dedicated water-fat phantom was used to validate fat fractions estimated with SPARCQ against gold-standard 1H MRS. Quantitative maps were obtained in knees of six healthy volunteers, and SPARCQ repeatability was evaluated in scan rescan experiments. Results: Simulations showed that fat fraction estimations are accurate and robust for signal-to-noise ratios above 20. Phantom experiments showed good agreement between SPARCQ and gold-standard (GS) fat fractions (fF(SPARCQ) = 1.02*fF(GS) + 0.00235). In volunteers, quantitative maps and banding-artifact-free water-fat-separated images obtained with SPARCQ demonstrated the expected contrast between fatty and non-fatty tissues. The coefficient of repeatability of SPARCQ fat fraction was 0.0512. Conclusion: The SPARCQ framework was proposed as a novel quantitative mapping technique for detecting different tissue compartments, and its potential was demonstrated for quantitative water-fat separation.
An approach to reduce motion artifacts in Quantitative Susceptibility Mapping using deep learning is proposed. We use an affine motion model with randomly created motion profiles to simulate motion-corrupted QSM images. The simulated QSM image is paired with its motion-free reference to train a neural network using supervised learning. The trained network is tested on unseen simulated motion-corrupted QSM images, in healthy volunteers and in Parkinsons disease patients. The results show that motion artifacts, such as ringing and ghosting, were successfully suppressed.
Physics-informed neural networks (NN) are an emerging technique to improve spatial resolution and enforce physical consistency of data from physics models or satellite observations. A super-resolution (SR) technique is explored to reconstruct high-resolution images ($4times$) from lower resolution images in an advection-diffusion model of atmospheric pollution plumes. SR performance is generally increased when the advection-diffusion equation constrains the NN in addition to conventional pixel-based constraints. The ability of SR techniques to also reconstruct missing data is investigated by randomly removing image pixels from the simulations and allowing the system to learn the content of missing data. Improvements in S/N of $11%$ are demonstrated when physics equations are included in SR with $40%$ pixel loss. Physics-informed NNs accurately reconstruct corrupted images and generate better results compared to the standard SR approaches.
Purpose: B1+ and T1 corrections and dynamic multi-coil shimming approaches were proposed to improve the fidelity of high isotropic resolution Generalized slice dithered enhanced resolution (gSlider) diffusion imaging. Methods: An extended reconstruction incorporating B1+ inhomogeneity and T1 recovery information was developed to mitigate slab-boundary artifacts in short-TR gSlider acquisitions. Slab-by-slab dynamic B0 shimming using a multi-coil integrated {Delta}B0/Rx shim-array, and high in-plane acceleration (Rinplane=4) achieved with virtual-coil GRAPPA were also incorporated into a 1 mm isotropic resolution gSlider acquisition/reconstruction framework to achieve an 8-11 fold reduction in geometric distortion compared to single-shot EPI. Results: The slab-boundary artifacts were alleviated by the proposed B1+ and T1 corrections compared to the standard gSlider reconstruction pipeline for short-TR acquisitions. Dynamic shimming provided >50% reduction in geometric distortion compared to conventional global 2nd order shimming. 1 mm isotropic resolution diffusion data show that the typically problematic temporal and frontal lobes of the brain can be imaged with high geometric fidelity using dynamic shimming. Conclusions: The proposed B1+ and T1 corrections and local-field control substantially improved the fidelity of high isotropic resolution diffusion imaging, with reduced slab-boundary artifacts and geometric distortion compared to conventional gSlider acquisition and reconstruction. This enabled high-fidelity whole-brain 1 mm isotropic diffusion imaging with 64 diffusion-directions in 20 minutes using a 3T clinical scanner.
Log in to be able to interact and post comments
comments
Fetching comments
Sign in to be able to follow your search criteria
