Purpose For ultrahigh field (UHF) MRI, the expected local specific absorption rate (SAR) distribution is usually calculated by numerical simulations using a limited number of generic body models and adding a safety margin to take into account intersubject variability. Assessment of this variability with a large model database would be desirable. In this study, a procedure to create such a database with accurate subject‐specific models is presented. Using 23 models, intersubject variability is investigated for prostate imaging at 7T with an 8‐channel fractionated dipole antenna array with 16 receive loops. Method From Dixon images of a volunteer acquired at 1.5T with a mockup array in place, an accurate dielectric model is built. Following this procedure, 23 subject‐specific models for local SAR assessment at 7T were created enabling an extensive analysis of the intersubject B1+ and peak local SAR variability. Results For the investigated setup, the maximum possible peak local SAR ranges from 2.6 to 4.6 W/kg for 8 × 1 W input power. The expected peak local SAR values represent a Gaussian distribution (μ/σ=2.29/0.29 W/kg) with realistic prostate‐shimmed phase settings and a gamma distribution Γ(24,0.09) with multidimensional radiofrequency pulses. Prostate‐shimmed phase settings are similar for all models. Using 1 generic phase setting, average B1+ reduction is 7%. Using only 1 model, the required safety margin for intersubject variability is 1.6 to 1.8. Conclusion The presented procedure allows for the creation of a customized model database. The results provide valuable insights into B1+ and local SAR variability. Recommended power thresholds per channel are 3.1 W with phase shimming on prostate or 2.6 W for multidimensional pulses.

In the radiofrequency (RF) range, the electrical properties of tissues (EPs: conductivity and permittivity) are modulated by the ionic and water content, which change for pathological conditions. Information on tissues EPs can be used e.g. in oncology as a biomarker. The inability of MR-Electrical Properties Tomography techniques (MR-EPT) to accurately reconstruct tissue EPs by relating MR measurements of the transmit RF field to the EPs limits their clinical applicability. Instead of employing electromagnetic models posing strict requirements on the measured MRI quantities, we propose a data driven approach where the electrical properties reconstruction problem can be casted as a supervised deep learning task (DL-EPT). DL-EPT reconstructions for simulations and MR measurements at 3 Tesla on phantoms and human brains using a conditional generative adversarial network demonstrate high quality EPs reconstructions and greatly improved precision compared to conventional MR-EPT. The supervised learning approach leverages the strength of electromagnetic simulations, allowing circumvention of inaccessible MR electromagnetic quantities. Since DL-EPT is more noise-robust than MR-EPT, the requirements for MR acquisitions can be relaxed. This could be a major step forward to turn electrical properties tomography into a reliable biomarker where pathological conditions can be revealed and characterized by abnormalities in tissue electrical properties.

No abstract

Purpose: Local specific absorption rate (SAR) cannot be measured and is usually evaluated by offline numerical simulations using generic body models that of course will differ from the patient's anatomy. An additional safety margin is needed to include this intersubject variability. In this work, we present a deep learning-based method for image-based subject-specific local SAR assessment. We propose to train a convolutional neural network to learn a "surrogate SAR model" to map the relation between subject-specific B + 1 maps and the corresponding local SAR. Method: Our database of 23 subject-specific models with an 8-transmit channel body array for prostate imaging at 7 T was used to build 5750 training samples.These synthetic complex B + 1 maps and local SAR distributions were used to train a conditional generative adversarial network. Extra penalization for local SAR underestimation errors was included in the loss function. In silico and in vivo validation were performed. Results: In silico cross-validation shows a good qualitative and quantitative match between predicted and ground-truth local SAR distributions. The peak local SAR estimation error distribution shows a mean overestimation error of 15% with 13% probability of underestimation. The higher accuracy of the proposed method allows the use of less conservative safety factors compared with standard procedures. In vivo validation shows that the method is applicable with realistic measurement data with impressively good qualitative and quantitative agreement to simulations. Conclusion: The proposed deep learning method allows online image-based subjectspecific local SAR assessment. It greatly reduces the uncertainty in current state-ofthe-art SAR assessment methods, reducing the time in the examination protocol by almost 25%. 696 | MELIADÒ Et AL. K E Y W O R D S convolutional neural network, deep learning, parallel transmit, specific absorption rate, subject-specific SAR assessment, ultrahigh-field MRI F I G U R E 1 A, Twenty-three body models (muscle, fat, skin, and cortical bone) are present in the database and the body array setup for prostate imaging at 7 T. B, Each of the 23 × 250 training samples consists of an input block of 5 complex B + 1 maps and 1 ground-truth 10-g averaged local SAR (SAR 10g ) distribution. Regions of low B + 1 (<0.25 µT) are excluded, as they provide inaccurate data in measured B + 1 maps

The purpose of this work is to propose a tier‐based formalism for safety assessment of custom‐built radio‐frequency (RF) coils that balances validation effort with the effort put in determinating the safety factor. The formalism has three tier levels. Higher tiers require increased effort when validating electromagnetic simulation results but allow for less conservative safety factors. In addition, we propose a new method to calculate modeling uncertainty between simulations and measurements and a new method to propagate uncertainties in the simulation into a safety factor that minimizes the risk of underestimating the peak specific absorption rate (SAR). The new safety assessment procedure was completed for all tier levels for an eight‐channel dipole array for prostate imaging at 7 T and an eight‐channel dipole array for head imaging at 10.5 T, using data from two different research sites. For the 7 T body array, the validation procedure resulted in a modeling uncertainty of 77% between measured and simulated local SAR distributions. For a situation where RF shimming is performed on the prostate, average power limits of 2.4 and 4.5 W/channel were found for tiers 2 and 3, respectively. When the worst‐case peak SAR among all phase settings was calculated, power limits of 1.4 and 2.7 W/channel were found for tiers 2 and 3, respectively. For the 10.5 T head array, a modeling uncertainty of 21% was found based on B1+ mapping. For the tier 2 validation, a power limit of 2.6 W/channel was calculated. The demonstrated tier system provides a strategy for evaluating modeling inaccuracy, allowing for the rapid translation of novel coil designs with conservative safety factors and the implementation of less conservative safety factors for frequently used coil arrays at the expense of increased validation effort.