Rigid motion-resolved B 1 + prediction using deep learning for real-time parallel-transmission pulse design

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.

Actual patient position versus safety models: Specific Absorption Rate implications of initial head position for Ultrahigh Field Magnetic Resonance Imaging

Specific absorption rate (SAR) relates power absorption to tissue heating, and therefore is used as a safety constraint in magnetic resonance imaging (MRI). This study investigates the implications of initial head positioning on local and whole-head SAR. A virtual body model was simulated at 161 positions inside an eight-channel parallel-transmit (pTx) array. On-axis displacements and rotations of up to 20 mm/degrees and off-axis axial/coronal translations were investigated. Single-channel, radiofrequency (RF) shimming (i.e., single-spoke pTx) and multispoke pTx pulses were designed for seven axial, five coronal and five sagittal slices at each position (the slices were consistent across all positions). Whole-head and local SAR were calculated using safety models consisting of a single (centred) body position, multiple representative positions and all simulated body positions. Positional mismatches between safety models and actual positions cause SAR underestimation. For axial imaging, the actual peak local SAR was up to 4.2-fold higher for both single-channel and 5-spoke pTx, 3.5-fold higher for 3-/4-spoke pTx, and 2-fold higher for RF shimming and 2-spoke pTx, compared with that calculated using the centred body position. For sagittal and coronal imaging, the underestimation of peak local SAR was up to 5.2-fold and 3.8-fold, respectively. Using all body positions to estimate SAR prevented SAR underestimation but yielded up to 11-fold SAR overestimation for RF shimming. Local SAR of single-channel and pTx multispoke pulses showed considerable dependence on the initial patient position. RF shimming yielded much lower sensitivity to positional mismatches for axial imaging but not for sagittal and coronal imaging. This was deemed attributable to the higher degrees-of-freedom of control offered by the investigated coil array for axial imaging. Whole-head SAR is less sensitive to positional mismatches compared with local SAR. Nevertheless, whole-head SAR increased by up to 80% for sagittal imaging. Local and whole-head SAR were observed to be more sensitive to positional mismatches in the axial plane, because of larger variations in coil-tissue proximity. Using all possible body positions in the safety model may become substantially over-conservative and limit imaging performance, especially for the RF shimming mode for axial imaging.

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.

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

PURPOSE

Subject-tailored parallel transmission pulses for ultra-high fields body applications are typically calculated based on subject-specific B 1 + $$ {\mathrm{B}}_1^{+} $$ -maps of all transmit channels, which require lengthy adjustment times. This study investigates the feasibility of using deep learning to estimate complex, channel-wise, relative 2D B 1 + $$ {\mathrm{B}}_1^{+} $$ -maps from a single gradient echo localizer to overcome long calibration times.

METHODS

126 channel-wise, complex, relative 2D B 1 + $$ {\mathrm{B}}_1^{+} $$ -maps of the human heart from 44 subjects were acquired at 7T using a Cartesian, cardiac gradient-echo sequence obtained under breath-hold to create a library for network training and cross-validation. The deep learning predicted maps were qualitatively compared to the ground truth. Phase-only B 1 + $$ {\mathrm{B}}_1^{+} $$ -shimming was subsequently performed on the estimated B 1 + $$ {\mathrm{B}}_1^{+} $$ -maps for a region of interest covering the heart. The proposed network was applied at 7T to 3 unseen test subjects.

RESULTS

The deep learning-based B 1 + $$ {\mathrm{B}}_1^{+} $$ -maps, derived in approximately 0.2 seconds, match the ground truth for the magnitude and phase. The static, phase-only pulse design performs best when maximizing the mean transmission efficiency. In-vivo application of the proposed network to unseen subjects demonstrates the feasibility of this approach: the network yields predicted B 1 + $$ {\mathrm{B}}_1^{+} $$ -maps comparable to the acquired ground truth and anatomical scans reflect the resulting B 1 + $$ {\mathrm{B}}_1^{+} $$ -pattern using the deep learning-based maps.

CONCLUSION

The feasibility of estimating 2D relative B 1 + $$ {\mathrm{B}}_1^{+} $$ -maps from initial localizer scans of the human heart at 7T using deep learning is successfully demonstrated. Because the technique requires only sub-seconds to derive channel-wise B 1 + $$ {\mathrm{B}}_1^{+} $$ -maps, it offers high potential for advancing clinical body imaging at ultra-high fields.

Ultra-high field MRI: parallel-transmit arrays and RF pulse design

This paper reviews the field of multiple or parallel radiofrequency (RF) transmission for magnetic resonance imaging (MRI). Currently the use of ultra-high field (UHF) MRI at 7 tesla and above is gaining popularity, yet faces challenges with non-uniformity of the RF field and higher RF power deposition. Since its introduction in the early 2000s, parallel transmission (pTx) has been recognized as a powerful tool for accelerating spatially selective RF pulses and combating the challenges associated with RF inhomogeneity at UHF. We provide a survey of the types of dedicated RF coils used commonly for pTx and the important modeling of the coil behavior by electromagnetic (EM) field simulations. We also discuss the additional safety considerations involved with pTx such as the specific absorption rate (SAR) and how to manage them. We then describe the application of pTx with RF pulse design, including a practical guide to popular methods. Finally, we conclude with a description of the current and future prospects for pTx, particularly its potential for routine clinical use.