Rapid estimation of 2D relative B 1 + -maps from localizers in the human heart at 7T using deep learning

Accelerated 3D multi-channel B 1 + mapping at 7 T for the brain and heart

PURPOSE

To acquire accurate volumetric multi-channelB 1 + $$ {\mathrm{B}}_1^{+} $$ maps in under 14 s whole-brain or 23 heartbeats whole-heart for parallel transmit (pTx) applications at 7 T.

THEORY AND METHODS

We evaluate the combination of three recently proposed techniques. The acquisition of multi-channel transmit arrayB 1 + $$ {\mathrm{B}}_1^{+} $$ maps is accelerated using transmit low rank (TxLR) with absoluteB 1 + $$ {\mathrm{B}}_1^{+} $$ mapping (Sandwich) acquired in aB 1 + $$ {\mathrm{B}}_1^{+} $$ time-interleaved acquisition of modes (B1TIAMO) fashion. Simulations using synthetic body images derived from Sim4Life were used to test the achievable acceleration for small scan matrices of 24 × 24. Next, we evaluated the method by retrospectively undersampling a fully sampledB 1 + $$ {\mathrm{B}}_1^{+} $$ library of nine subjects in the brain. Finally, Cartesian undersampled phantom and in vivo images were acquired in both the brain of three subjects (8Tx/32 receive [Rx]) and the heart of another three subjects (8Tx/8Rx) at 7 T.

RESULTS

Simulation and in vivo results show that volumetric multi-channelB 1 + $$ {\mathrm{B}}_1^{+} $$ maps can be acquired using acceleration factors of 4 in the body, reducing the acquisition time to within 23 heartbeats, which was previously not possible. In silico heart simulations demonstrated a RMS error to the fully sampled native resolution ground truth of 4.2° when combined in first-order circularly polarized mode (mean flip angle 66°) at an acceleration factor of 4. The 14 s 3DB 1 + $$ {\mathrm{B}}_1^{+} $$ maps acquired in the brain have a RMS error of 1.9° to the fully sampled (mean flip angle 86°).

CONCLUSION

The proposed method is demonstrated as a fast pTx calibration technique in the brain and a promising method for pTx calibration in the body.

Accelerated B 1 + $$ {\mathrm{B}}_1^{+} $$ mapping and robust parallel transmit pulse design for heart and prostate imaging at 7 T

PURPOSE

To investigate the impact of reduced k-space sampling onB 1 + $$ {\mathrm{B}}_1^{+} $$ mapping and the resulting impact on phase shimming and dynamic/universal parallel transmit (pTx) RF pulse design.

METHODS

Channel-wise 3DB 1 + $$ {\mathrm{B}}_1^{+} $$ maps were measured at 7 T in 35 and 23 healthy subjects for the heart and prostate region, respectively. With theseB 1 + $$ {\mathrm{B}}_1^{+} $$ maps, universal phase shims optimizing homogeneity andB 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 onB 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 higherB 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 acceleratedB 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 acceleratedB 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

AcceleratedB 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.

High dynamic range B 1 + mapping for the evaluation of parallel transmit arrays

PURPOSE

Demonstration of a high dynamic-range and high SNR method for acquiring absoluteB 1 + $$ {\mathrm{B}}_1^{+} $$ maps from a combination of gradient echo and actual-flip-angle measurements that is especially useful during the construction of parallel-transmit arrays.

METHODS

Low flip angle gradient echo images, acquired when transmitting with each channel individually, are used to compute relativeB 1 + $$ {\mathrm{B}}_1^{+} $$ maps. Instead of computing these in a conventional manner, the equivalence of the problem to the ESPIRiT parallel image reconstruction method is used to computeB 1 + $$ {\mathrm{B}}_1^{+} $$ maps with a higher SNR. Absolute maps are generated by calibration against a single actual flip-angle acquisition when transmitting on all channels simultaneously.

RESULTS

Depending on the number of receiver channels and the location of the receive elements with respect to the subject being investigated, moderate to high gains in the SNR of the acquiredB 1 + $$ {\mathrm{B}}_1^{+} $$ maps can be achieved.

CONCLUSIONS

The proposed method is especially suited for the acquisition ofB 1 + $$ {\mathrm{B}}_1^{+} $$ maps during the construction of transceiver arrays. Compared to the original method, maps with higher SNR can be computed without the need for additional measurements, and maps can also be generated using previously acquired data. Furthermore, easy adoption and fast estimation of receiver channels is possible because of existing highly optimized open-source implementations of ESPIRiT, such as in the BART toolbox.

Deep learning-based whole-brain B1 +-mapping at 7T

PURPOSE

This study investigates the feasibility of using complex-valued neural networks (NNs) to estimate quantitative transmit magnetic RF field (B1 +) maps from multi-slice localizer scans with different slice orientations in the human head at 7T, aiming to accelerate subject-specific B1 +-calibration using parallel transmission (pTx).

METHODS

Datasets containing channel-wise B1 +-maps and corresponding multi-slice localizers were acquired in axial, sagittal, and coronal orientation in 15 healthy subjects utilizing an eight-channel pTx transceiver head coil. Training included five-fold cross-validation for four network configurations:NN cx tra $$ {\mathrm{NN}}_{\mathrm{cx}}^{\mathrm{tra}} $$ used transversal,NN cx sag $$ {\mathrm{NN}}_{\mathrm{cx}}^{\mathrm{sag}} $$ sagittal,NN cx cor $$ {\mathrm{NN}}_{\mathrm{cx}}^{\mathrm{cor}} $$ coronal data, andNN cx all $$ {\mathrm{NN}}_{\mathrm{cx}}^{\mathrm{all}} $$ was trained on all slice orientations. The resulting maps were compared to B1 +-reference scans using different quality metrics. The proposed network was applied in-vivo at 7T in two unseen test subjects using dynamic kt-point pulses.

RESULTS

Predicted B1 +-maps demonstrated a high similarity with measured B1 +-maps across multiple orientations. The estimation matched the reference with a mean relative error in the magnitude of (2.70 ± 2.86)% and mean absolute phase difference of (6.70 ± 1.99)° for transversal, (1.82 ± 0.69)% and (4.25 ± 1.62)° for sagittal (NN cx sag $$ {\mathrm{NN}}_{\mathrm{cx}}^{\mathrm{sag}} $$ ), as well as (1.33 ± 0.27)% and (2.66 ± 0.60)° for coronal slices (NN cx cor $$ {\mathrm{NN}}_{\mathrm{cx}}^{\mathrm{cor}} $$ ) considering brain tissue.NN cx all $$ {\mathrm{NN}}_{\mathrm{cx}}^{\mathrm{all}} $$ trained on all orientations enables a robust prediction of B1 +-maps across different orientations. Achieving a homogenous excitation over the whole brain for an in-vivo application displayed the approach's feasibility.

CONCLUSION

This study demonstrates the feasibility of utilizing complex-valued NNs to estimate multi-slice B1 +-maps in different slice orientations from localizer scans in the human brain at 7T.

Tailored and universal parallel transmit broadband pulses for homogeneous 3D excitation of the human heart at 7T

PURPOSE

To research and evaluate the performance of broadband tailored kT-point pulses (TP) and universal pulses (UP) for homogeneous excitation of the human heart at 7T.

METHODS

Relative 3DB 1 + $$ {\mathrm{B}}_1^{+} $$ -maps of the thorax were acquired from 29 healthy volunteers. TP and UP were designed using the small-tip-angle approximation for a different composition of up to seven resonance frequencies. TP were computed for each of the 29B 1 + $$ {\mathrm{B}}_1^{+} $$ -maps, and UPs were calculated using 22B 1 + $$ {\mathrm{B}}_1^{+} $$ -maps and tested in seven testcases. The performance of the pulses was analyzed using the coefficient of variation (CV) in the 3D heart volumes. The 3D gradient-echo (GRE) scans were acquired for the seven testcases to qualitatively validate theB 1 + $$ {\mathrm{B}}_1^{+} $$ -predictions.

RESULTS

Single- and double-frequency optimized pulses achieved homogeneity in flip angle (FA) for the frequencies they were optimized for, while the broadband pulses achieved uniformity in FA across a 1300 Hz frequency range.

CONCLUSION

Broadband TP and UP can be used for homogeneous excitation of the heart volume across a 1300 Hz frequency range, including the water and the main six fat peaks, or with longer pulse durations and higher FAs for a smaller transmit bandwidth. Moreover, despite large inter-volunteer variations, broadband UP can be used for calibration-free 3D heart FA homogenization in time-critical situations.

Artificial intelligence for neuro MRI acquisition: a review

OBJECT

To review recent advances of artificial intelligence (AI) in enhancing the efficiency and throughput of the MRI acquisition workflow in neuroimaging, including planning, sequence design, and correction of acquisition artifacts.

MATERIALS AND METHODS

A comprehensive analysis was conducted on recent AI-based methods in neuro MRI acquisition. The study focused on key technological advances, their impact on clinical practice, and potential risks associated with these methods.

RESULTS

The findings indicate that AI-based algorithms have a substantial positive impact on the MRI acquisition process, improving both efficiency and throughput. Specific algorithms were identified as particularly effective in optimizing acquisition steps, with reported improvements in workflow efficiency.

DISCUSSION

The review highlights the transformative potential of AI in neuro MRI acquisition, emphasizing the technological advances and clinical benefits. However, it also discusses potential risks and challenges, suggesting areas for future research to mitigate these concerns and further enhance AI integration in MRI acquisition.

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

PURPOSE

To mitigateB 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-channelB 1 + $$ {B}_1^{+} $$ maps. In this work, we introduce an alternative approach that facilitates the use of CNNs with multi-channelB 1 + $$ {B}_1^{+} $$ maps while performing unsupervised training. The multi-channelB 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-channelB 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.

Whole-liver flip-angle shimming at 7 T using parallel-transmit kT -point pulses and Fourier phase-encoded DREAM B 1 + mapping

PURPOSE

To obtain homogeneous signal throughout the human liver at 7 T. Flip angle (FA) shimming in 7T whole-liver imaging was performed through parallel-transmit kT -point pulses based on subject-specific multichannel absoluteB 1 + $$ {\mathrm{B}}_1^{+} $$ maps from Fourier phase-encoded dual refocusing echo acquisition mode (PE-DREAM).

METHODS

The optimal number of Fourier phase-encoding steps for PE-DREAMB 1 + $$ {\mathrm{B}}_1^{+} $$ mapping was determined for a 7T eight-channel parallel-transmission system. FA shimming experiments were performed in the liver of 7 healthy subjects with varying body mass index. In these subjects, firstB 0 $$ {\mathrm{B}}_0 $$ shimming and Fourier PE-DREAMB 1 + $$ {\mathrm{B}}_1^{+} $$ mapping were performed. Subsequently, three small-flip-angle 3D gradient-echo scans were acquired, comparing a circularly polarized (CP) mode, a phase shim, and a kT -point pulse. Resulting homogeneity was assessed and compared with estimated FA maps and distributions.

RESULTS

Fourier PE-DREAM with 13 phase-encoding steps resulted in a good tradeoff betweenB 1 + $$ {\mathrm{B}}_1^{+} $$ accuracy and scan time. Lower coefficient of variation values (average [min-max] across subjects) of the estimated FA in the volume of interest were observed using kT -points (7.4 [6.6%-8.0%]), compared with phase shimming (18.8 [12.9%-23.4%], p < 0.001) and CP (43.2 [39.4%-47.1%], p < 0.001). kT -points delivered whole-liver images with the nominal FA and the highest degree of homogeneity. CP and phase shimming resulted in either inaccurate or imprecise FA distributions. Here, locations having suboptimal FA in the estimated FA maps corresponded to liver areas suffering from inconsistent signal intensity and T1 -weighting in the gradient-echo scans.

CONCLUSION

Homogeneous whole-liver 3D gradient-echo acquisitions at 7 T can be obtained with eight-channel kT -point pulses calculated based on subject-specific multichannel absolute Fourier PE-DREAMB 1 + $$ {\mathrm{B}}_1^{+} $$ maps.

Wirelessly interfacing sensor-equipped implants and MR scanners for improved safety and imaging

PURPOSE

To investigate a novel reduced RF heating method for imaging in the presence of active implanted medical devices (AIMDs) which employs a sensor-equipped implant that provides wireless feedback.

METHODS

The implant, consisting of a generator case and a lead, measures RF-inducedE $$ E $$ -fields at the implant tip using a simple sensor in the generator case and transmits these values wirelessly to the MR scanner. Based on the sensor signal alone, parallel transmission (pTx) excitation vectors were calculated to suppress tip heating and maintain image quality. A sensor-based imaging metric was introduced to assess the image quality. The methodology was studied at 7T in testbed experiments, and at a 3T scanner in an ASTM phantom containing AIMDs instrumented with six realistic deep brain stimulation (DBS) lead configurations adapted from patients.

RESULTS

The implant successfully measured RF-inducedE $$ E $$ -fields (Pearson correlation coefficient squared [R2 ] = 0.93) and temperature rises (R2  = 0.95) at the implant tip. The implant acquired the relevant data needed to calculate the pTx excitation vectors and transmitted them wirelessly to the MR scanner within a single shot RF sequence (<60 ms). Temperature rises for six realistic DBS lead configurations were reduced to 0.03-0.14 K for heating suppression modes compared to 0.52-3.33 K for the worst-case heating, while imaging quality remained comparable (five of six lead imaging scores were ≥0.80/1.00) to conventional circular polarization (CP) images.

CONCLUSION

Implants with sensors that can communicate with an MR scanner can substantially improve safety for patients in a fast and automated manner, easing the current burden for MR personnel.