Unsupervised deep learning with convolutional neural networks for static parallel transmit design: A retrospective study.

PURPOSE: To mitigate B 1 + $$ {B}_1^{+} $$ inhomogeneity at 7T for multi-channel transmit arrays using unsupervised deep learning with convolutional neural networks (CNNs). METHODS: Deep learning parallel transmit (pTx) pulse design has received attention, but such methods have relied on supervised training and did not use CNNs for multi-channel B 1 + $$ {B}_1^{+} $$ maps. In this work, we introduce an alternative approach that facilitates the use of CNNs with multi-channel B 1 + $$ {B}_1^{+} $$ maps while performing unsupervised training. The multi-channel B 1 + $$ {B}_1^{+} $$ maps are concatenated along the spatial dimension to enable shift-equivariant processing amenable to CNNs. Training is performed in an unsupervised manner using a physics-driven loss function that minimizes the discrepancy of the Bloch simulation with the target magnetization, which eliminates the calculation of reference transmit RF weights. The training database comprises 3824 2D sagittal, multi-channel B 1 + $$ {B}_1^{+} $$ maps of the healthy human brain from 143 subjects. B 1 + $$ {B}_1^{+} $$ data were acquired at 7T using an 8Tx/32Rx head coil. The proposed method is compared to the unregularized magnitude least-squares (MLS) solution for the target magnetization in static pTx design. RESULTS: The proposed method outperformed the unregularized MLS solution for RMS error and coefficient-of-variation and had comparable energy consumption. Additionally, the proposed method did not show local phase singularities leading to distinct holes in the resulting magnetization unlike the unregularized MLS solution. CONCLUSION: Proposed unsupervised deep learning with CNNs performs better than unregularized MLS in static pTx for speed and robustness.

Accelerated B 1 + $$ {\mathrm{B}}_1

PURPOSE: To investigate the impact of reduced k-space sampling on B 1 + $$ {\mathrm{B}}_1^{+} $$ mapping and the resulting impact on phase shimming and dynamic/universal parallel transmit (pTx) RF pulse design. METHODS: Channel-wise 3D B 1 + $$ {\mathrm{B}}_1^{+} $$ maps were measured at 7 T in 35 and 23 healthy subjects for the heart and prostate region, respectively. With these B 1 + $$ {\mathrm{B}}_1^{+} $$ maps, universal phase shims optimizing homogeneity and B 1 + $$ {\mathrm{B}}_1^{+} $$ efficiency were designed for heart and prostate imaging. In addition, universal 4kT-point pulses were designed for the heart. Subsequently, individual phase shims and individual 4kT-pulses were designed based on B 1 + $$ {\mathrm{B}}_1^{+} $$ maps with different acceleration factors and tested on the original maps. The performance of the pulses was compared by evaluating their coefficients of variation (CoV), B 1 + $$ {\mathrm{B}}_1^{+} $$ efficiencies and specific energy doses (SED). Furthermore, validation measurements were carried out for one heart and one prostate subject. RESULTS: For both organs, the universal phase shims showed significantly higher B 1 + $$ {\mathrm{B}}_1^{+} $$ efficiencies and lower CoVs compared to the vendor provided default shim, but could still be improved with individual phase shims based on accelerated B 1 + $$ {\mathrm{B}}_1^{+} $$ maps (acquisition time = 30 s). In the heart, the universal 4kT-pulse achieved significantly lower CoVs than tailored phase shims. Tailored 4kT-pulses based on accelerated B 1 + $$ {\mathrm{B}}_1^{+} $$ maps resulted in even further reduced CoVs or a 2.5-fold reduction in SED at the same CoVs as the universal 4kT-pulse. CONCLUSION: Accelerated B 1 + $$ {\mathrm{B}}_1^{+} $$ maps can be used for the design of tailored pTx pulses for prostate and cardiac imaging at 7 T, which further improve homogeneity, B 1 + $$ {\mathrm{B}}_1^{+} $$ efficiency, or SED compared to universal pulses.

Fast online spectral-spatial pulse design for subject-specific fat saturation in cervical spine and foot imaging at 1.5 T.

OBJECTIVE: To compensate subject-specific field inhomogeneities and enhance fat pre-saturation with a fast online individual spectral-spatial (SPSP) single-channel pulse design. METHODS: The RF shape is calculated online using subject-specific field maps and a predefined excitation k-space trajectory. Calculation acceleration options are explored to increase clinical viability. Four optimization configurations are compared to a standard Gaussian spectral selective pre-saturation pulse and to a Dixon acquisition using phantom and volunteer (N = 5) data at 1.5 T with a turbo spin echo (TSE) sequence. Measurements and simulations are conducted across various body parts and image orientations. RESULTS: Phantom measurements demonstrate up to a 3.5-fold reduction in residual fat signal compared to Gaussian fat saturation. In vivo evaluations show improvements up to sixfold for dorsal subcutaneous fat in sagittal cervical spine acquisitions. The versatility of the tailored trajectory is confirmed through sagittal foot/ankle, coronal, and transversal cervical spine experiments. Additional measurements indicate that excitation field (B1) information can be disregarded at 1.5 T. Acceleration methods reduce computation time to a few seconds. DISCUSSION: An individual pulse design that primarily compensates for main field (B0) inhomogeneities in fat pre-saturation is successfully implemented within an online "push-button" workflow. Both fat saturation homogeneity and the level of suppression are improved.

Clinically compatible subject-specific dynamic parallel transmit pulse design for homogeneous fat saturation and water-excitation at 7T: Proof-of-concept for CEST MRI of the brain.

PURPOSE: To evaluate the benefits and challenges of dynamic parallel transmit (pTx) pulses for fat saturation (FS) and water-excitation (WE), in the context of CEST MRI. METHODS: "Universal" kT -points (for FS) and spiral non-selective (for WE) trajectories were optimized offline for flip angle (FA) homogeneity. Routines to optimize the pulse shape online, based on the subject's fields maps, were implemented (target FA of 110°/0° for FS, 0°/5° for WE at fat/water frequencies). The pulses were inserted in a CEST sequence with a pTx readout. The different fat suppression schemes and their effects on CEST contrasts were compared in 12 volunteers at 7T. RESULTS: With a 25%-shorter pulse duration, pTx FS largely improved the FA homogeneity (root-mean-square-error (RMSE) = 12.3° vs. 53.4° with circularly-polarized mode, at the fat frequency). However, the spectral selectivity was degraded mainly in the cerebellum and close to the sinuses (RMSE = 5.8° vs. 0.2° at the water frequency). Similarly, pTx WE showed a trade-off between FA homogeneity and spectral selectivity compared to pTx non-selective pulses (RMSE = 0.9° and 1.1° at the fat and water frequencies, vs. 4.6° and 0.5°). In the brain, CEST metrics were reduced by up to 31.9% at -3.3 ppm with pTx FS, suggesting a mitigated lipid-induced bias. CONCLUSION: This clinically compatible implementation of dynamic pTx pulses improved the fat suppression homogeneity at 7T taking into account the subject-specific B0 heterogeneities online. This study highlights the lipid-induced biases on the CEST z-spectrum. The results are promising for body applications where B0 heterogeneities and fat are more substantial.

The effects of RF coils and SAR supervision strategies for clinically applicable nonselective parallel-transmit pulses at 7 T.

PURPOSE: To investigate the effects of using different parallel-transmit (pTx) head coils and specific absorption rate (SAR) supervision strategies on pTx pulse design for ultrahigh-field MRI using a 3D-MPRAGE sequence. METHODS: The PTx universal pulses (UPs) and fast online-customized (FOCUS) pulses were designed with pre-acquired data sets (B0 , B1 + maps, specific absorption rate [SAR] supervision data) from two different 8 transmit/32 receive head coils on two 7T whole-body MR systems. For one coil, the SAR supervision model consisted of per-channel RF power limits. In the other coil, SAR estimations were done with both per-channel RF power limits as well as virtual observation points (VOPs) derived from electromagnetic field (EMF) simulations using three virtual human body models at three different positions. All pulses were made for nonselective excitation and inversion and evaluated on 132 B0 , B1 + , and SAR supervision datasets obtained with one coil and 12 from the other. At both sites, 3 subjects were examined using MPRAGE sequences that used UP/FOCUS pulses generated for both coils. RESULTS: For some subjects, the UPs underperformed when simulated on a different coil from which they were derived, whereas FOCUS pulses still showed acceptable performance in that case. FOCUS inversion pulses outperformed adiabatic pulses when scaled to the same local SAR level. For the self-built coil, the use of VOPs showed reliable overestimation compared with the ground-truth EMF simulations, predicting about 52% lower local SAR for inversion pulses compared with per-channel power limits. CONCLUSION: FOCUS inversion pulses offer a low-SAR alternative to adiabatic pulses and benefit from using EMF-based VOPs for SAR estimation.

Hybrid B1+ -shimming and gradient adaptions for improved pseudo-continuous arterial spin labeling at 7 Tesla.

PURPOSE: To improve pseudo-continuous arterial spin labeling (pcASL) at 7T by exploiting a hybrid homogeneity- and efficiency-optimized B1+ -shim with adapted gradient strength as well as background suppression. METHODS: The following three experiments were performed at 7T, each employing five volunteers: (1) A hybrid (ie, homogeneity-efficiency optimized) B1+ -shim was introduced and evaluated for variable-rate selective excitation pcASL labeling. Therefore, B1+ -maps in the V3 segment and time-of-flight images were acquired to identify the feeding arteries. For validation, a gradient-echo sequence was applied in circular polarized (CP) mode and with the hybrid B1+ -shim. Additionally, the gray matter (temporal) signal-to-noise ratio (tSNR) in pcASL perfusion images was evaluated. (2) Bloch simulations for the pcASL labeling were conducted and validated experimentally, with a focus on the slice-selective gradients. (3) Background suppression was added to the B1+ -shimmed, gradient-adapted 7T sequence and this was then compared to a matched sequence at 3T. RESULTS: The B1+ -shim improved the signal within the labeling plane (23.6%) and the SNR/tSNR increased (+11%/+11%) compared to its value in CP mode; however, the increase was not significant. In accordance with the simulations, the adapted gradients increased the tSNR (35%) and SNR (45%) significantly. Background suppression further improved the perfusion images at 7T, and this protocol performed as well as a resolution-matched protocol at 3T. CONCLUSION: The combination of the proposed hybrid B1+ -phase-shim with the adapted slice-selective gradients and background suppression shows great potential for improved pcASL labeling under suboptimal B1+ conditions at 7T.

Brain tissues have single-voxel signatures in multi-spectral MRI.

Since the seminal works by Brodmann and contemporaries, it is well-known that different brain regions exhibit unique cytoarchitectonic and myeloarchitectonic features. Transferring the approach of classifying brain tissues - and other tissues - based on their intrinsic features to the realm of magnetic resonance (MR) is a longstanding endeavor. In the 1990s, atlas-based segmentation replaced earlier multi-spectral classification approaches because of the large overlap between the class distributions. Here, we explored the feasibility of performing global brain classification based on intrinsic MR features, and used several technological advances: ultra-high field MRI, q-space trajectory diffusion imaging revealing voxel-intrinsic diffusion properties, chemical exchange saturation transfer and semi-solid magnetization transfer imaging as a marker of myelination and neurochemistry, and current neural network architectures to analyze the data. In particular, we used the raw image data as well to increase the number of input features. We found that a global brain classification of roughly 97 brain regions was feasible with gross classification accuracy of 60%; and that mapping from voxel-intrinsic MR data to the brain region to which the data belongs is possible. This indicates the presence of unique MR signals of different brain regions, similar to their cytoarchitectonic and myeloarchitectonic fingerprints.

Fast online-customized (FOCUS) parallel transmission pulses: A combination of universal pulses and individual optimization.

PURPOSE: To mitigate spatial flip angle (FA) variations under strict specific absorption rate (SAR) constraints for ultra-high field MRI using a combination of universal parallel transmit (pTx) pulses and fast subject-specific optimization. METHODS: Data sets consisting of B0 , B1+ maps, and virtual observation point (VOP) data were acquired from 72 subjects (study groups of 48/12 healthy Europeans/Asians and 12 Europeans with pathological or incidental findings) using an 8Tx/32Rx head coil on a 7T whole-body MR system. Combined optimization values (COV) were defined as combination of spiral-nonselective (SPINS) trajectory parameters and an energy regularization weight. A set of COV was optimized universally by simulating the individual RF pulse optimizations of 12 training data sets (healthy Europeans). Subsequently, corresponding universal pulses (UPs) were calculated. Using COV and UPs, individually optimized pulses (IOPs) were calculated during the sequence preparation phase (maximum 15 s). Two different UPs and IOPs were evaluated by calculating their normalized root-mean-square error (NRMSE) of the FA and SAR in simulations of all data sets. Seven additional subjects were examined using an MPRAGE sequence that uses the designed pTx excitation pulses and a conventional adiabatic inversion. RESULTS: All pTx pulses resulted in decreased mean NRMSE compared to a circularly polarized (CP) pulse (CP = ~28%, UPs = ~17%, and IOPs = ~12%). UPs and IOPs improved homogeneity for all subjects. Differences in NRMSE between study groups were much lower than differences between different pulse types. CONCLUSION: UPs can be used to generate fast online-customized (FOCUS) pulses gaining lower NRMSE and/or lower SAR values.

Whole-brain quantitative CEST MRI at 7T using parallel transmission methods and B1+ correction.

PURPOSE: To enable whole-brain quantitative CEST MRI at ultra-high magnetic field strengths (B0 ≥ 7T) within short acquisition times. METHODS: Multiple interleaved mode saturation (MIMOSA) was combined with fast online-customized (FOCUS) parallel transmission (pTx) excitation pulses and B1+ correction to achieve homogenous whole-brain coverage. Examinations of 13 volunteers were performed on a 7T MRI system with 3 different types of pulse sequences: (1) saturation in circular polarized (CP) mode and CP mode readout, (2) MIMOSA and CP readout, and (3) MIMOSA and FOCUS readout. For comparison, the inverse magnetic transfer ratio metric for relayed nuclear Overhauser effect and amide proton transfer were calculated. To investigate the number of required acquisitions for a good B1+ correction, 4 volunteers were measured with 6 different B1 amplitudes. Finally, time point repeatability was investigated for 6 volunteers. RESULTS: MIMOSA FOCUS sequence using B1+ correction, with both single and multiple points, reduced inhomogeneity of the CEST contrasts around the occipital lobe and cerebellum. Results indicate that the most stable inter-subject coefficient of variation was achieved using the MIMOSA FOCUS sequence. Time point repeatability of MIMOSA FOCUS with single-point B1+ correction showed a maximum coefficient of variation below 8% for 3 measurements in a single volunteer. CONCLUSION: A combination of MIMOSA FOCUS with a single-point B1+ correction can be used to achieve quantitative CEST measurements at ultra-high magnetic field strengths. Compared to previous B1+ correction methods, acquisition time can be reduced as additional scans required for B1+ correction can be omitted.