A previously proposed nonlinear inverse reconstruction for autocalibrated parallel imaging simultaneously estimates coil sensitivities and image content. This work exploits this property for real-time MRI, where coil sensitivities need to be dynamically adapted to the conditions generated by moving objects. The development comprises (i) an extension of the nonlinear inverse algorithm to non-Cartesian k-space encodings, (ii) its implementation on a graphical processing unit to reduce reconstruction times, and (iii) the use of a convolution-based iteration, which considerably simplifies the graphical processing unit implementation compared to a gridding technique. The method is validated for real-time MRI of the human heart at 3 T using radio frequency-spoiled radial FLASH (pulse repetition time/echo time = 2.0/1.3 ms, flip angle 8 degrees). The results demonstrate artifact-free reconstructions from only 65-85 spokes, with 256 oversampled data points. Acquisition times of 130-170 ms resulted in 29-38 frames per second for sliding window reconstructions (factor 5). While offline reconstructions required 1-2 sec, real-time applications with modified parameters and slightly lower image quality were achieved within 90 ms per graphical processing unit.
Abstract Robustness against data inconsistencies, imaging artifacts and acquisition speed are crucial factors limiting the possible range of applications for magnetic resonance imaging (MRI). Therefore, we report a novel calibrationless parallel imaging technique which simultaneously estimates coil profiles and image content in a relaxed forward model. Our method is robust against a wide class of data inconsistencies, minimizes imaging artifacts and is comparably fast, combining important advantages of many conceptually different state-of-the-art parallel imaging approaches. Depending on the experimental setting, data can be undersampled well below the Nyquist limit. Here, even high acceleration factors yield excellent imaging results while being robust to noise and the occurrence of phase singularities in the image domain, as we show on different data. Moreover, our method successfully reconstructs acquisitions with insufficient field-of-view. We further compare our approach to ESPIRiT and SAKE using spin-echo and gradient echo MRI data from the human head and knee. In addition, we show its applicability to non-Cartesian imaging on radial FLASH cardiac MRI data. Using theoretical considerations, we show that ENLIVE can be related to a low-rank formulation of blind multi-channel deconvolution, explaining why it inherently promotes low-rank solutions.
Purpose To develop and evaluate motion‐compensation and compressed‐sensing techniques in 4D flow MRI for anatomical assessment in a comprehensive ferumoxytol‐enhanced congenital heart disease (CHD) exam. Materials and Methods A Cartesian 4D flow sequence was developed to enable intrinsic navigation and two variable‐density sampling schemes: VDPoisson and VDRad. Four compressed‐sensing methods were developed: A) VDPoisson scan reconstructed using spatial wavelets; B) added temporal total variation to A; C) VDRad scan using the same reconstruction as in B; and D) added motion compensation to C. With Institutional Review Board (IRB) approval and Health Insurance Portability and Accountability Act (HIPAA) compliance, 23 consecutive patients (eight females, mean 6.3 years) referred for ferumoxytol‐enhanced CHD 3T MRI were recruited. Images were acquired and reconstructed using methods A–D. Two cardiovascular radiologists independently scored the images on a 5‐point scale. These readers performed a paired wall motion and functional assessment between method D and 2D balanced steady‐state free precession (bSSFP) CINE for 16 cases. Results Method D had higher diagnostic image quality for most anatomical features (mean 3.8–4.8) compared to A (2.0–3.6), B (2.2–3.7), and C (2.9–3.9) with P < 0.05 with good interobserver agreement ( κ ≥ 0.49). Method D had similar or better assessment of myocardial borders and cardiac motion compared to 2D bSSFP ( P < 0.05, κ ≥ 0.77). All methods had good internal agreement in comparing aortic with pulmonic flow (BA mean < 0.02%, r > 0.85) and compared to method A (BA mean < 0.13%, r > 0.84) with P < 0.01. Conclusion Flow, functional, and anatomical assessment in CHD with ferumoxytol‐enhanced 4D flow is feasible and can be significantly improved using motion compensation and compressed sensing. J. Magn. Reson. Imaging 2016;43:1355–1368.
The main disadvantage of Magnetic Resonance Imaging (MRI) are its long scan times and, in consequence, its sensitivity to motion. Exploiting the complementary information from multiple receive coils, parallel imaging is able to recover images from under-sampled k-space data and to accelerate the measurement. Because parallel magnetic resonance imaging can be used to accelerate basically any imaging sequence it has many important applications. Parallel imaging brought a fundamental shift in image reconstruction: Image reconstruction changed from a simple direct Fourier transform to the solution of an ill-conditioned inverse problem. This work gives an overview of image reconstruction from the perspective of inverse problems. After introducing basic concepts such as regularization, discretization, and iterative reconstruction, advanced topics are discussed including algorithms for auto-calibration, the connection to approximation theory, and the combination with compressed sensing.
Purpose: To develop generic optimization strategies for image reconstruction using graphical processing units (GPUs) in magnetic resonance imaging (MRI) and to exemplarily report about our experience with a highly accelerated implementation of the non-linear inversion algorithm (NLINV) for dynamic MRI with high frame rates. Methods: The NLINV algorithm is optimized and ported to run on an a multi-GPU single-node server. The algorithm is mapped to multiple GPUs by decomposing the data domain along the channel dimension. Furthermore, the algorithm is decomposed along the temporal domain by relaxing a temporal regularization constraint, allowing the algorithm to work on multiple frames in parallel. Finally, an autotuning method is presented that is capable of combining different decomposition variants to achieve optimal algorithm performance in different imaging scenarios. Results: The algorithm is successfully ported to a multi-GPU system and allows online image reconstruction with high frame rates. Real-time reconstruction with low latency and frame rates up to 30 frames per second is demonstrated. Conclusion: Novel parallel decomposition methods are presented which are applicable to many iterative algorithms for dynamic MRI. Using these methods to parallelize the NLINV algorithm on multiple GPUs it is possible to achieve online image reconstruction with high frame rates.
SE measurement of the knee of a healthy volunteer Sequence parameters: TR 1800ms TE 18ms Matrix Size 192x192 In Plane Resolution 0.78mmx0.78mm Slice Thickness 2mm 3T System 8 channel knee coil Florian Knoll (florian.knoll@tugraz.at) Date: 2.2.2011 Acknowledgements to Tobias Block and Martin Uecker for their support with the in vivo radial spin echo data.
To develop and clinically evaluate a pediatric knee magnetic resonance imaging (MRI) technique based on volumetric fast spin-echo (3DFSE) and compare its diagnostic performance, image quality, and imaging time to that of a conventional 2D protocol.A 3DFSE sequence was modified and combined with a compressed sensing-based reconstruction resolving multiple image contrasts, a technique termed T2 Shuffling (T2 Sh). With Institutional Review Board (IRB) approval, 28 consecutive children referred for 3T knee MRI prospectively underwent a standard clinical knee protocol followed by T2 Sh. T2 Sh performance was assessed by two readers blinded to diagnostic reports. Interpretive discrepancies were resolved by medical record chart review and consensus between the readers and an orthopedic surgeon. Image quality was evaluated by rating anatomic delineation, with 95% confidence interval. A Wilcoxon rank-sum test assessed the null hypothesis that T2 Sh structure delineation compared to conventional 2D is unchanged. Intraclass correlation coefficients were calculated for interobserver agreement. Imaging time of the conventional protocol and T2 Sh was compared.There was 81% and 87% concordance between T2 Sh reports and diagnostic reports, respectively, for each reader. Upon consensus review, T2 Sh had 93% sensitivity and 100% specificity compared to clinical reports for detection of clinically relevant findings. The 95% confidence interval of diagnostic or better rating was 95-100%, with 34-80% interobserver agreement. There was no significant difference in structure delineation between T2 Sh and 2D, except for the retinaculum (P < 0.05), where 2D was preferred. Typical imaging time for T2 Sh and the conventional exam was 7 and 13 minutes, respectively.A single-sequence pediatric knee exam is feasible with T2 Sh, providing multiplanar, reformattable 4D images.2 J. MAGN. RESON. IMAGING 2017;45:1700-1711.
