Laboratory of FMRI Technology (LOFT), USC Stevens Neuroimaging and Informatics Institute, Keck School of Medicine, University of Southern California, Los Angeles, California, USA.
Siemens Medical Solutions USA, Los Angeles, California, USA.
Magn Reson Med. 2023 Dec;90(6):2524-2538. doi: 10.1002/mrm.29797. Epub 2023 Jul 19.
To predict subject-specific local specific absorption rate (SAR) distributions of the human head for parallel transmission (pTx) systems at 7 T.
Electromagnetic energy deposition in tissues is nonuniform at 7 T, and interference patterns due to individual channels of pTx systems may result in increased local SAR values, which can only be estimated with very high safety margins. We proposed, designed, and demonstrated a multichannel 3D convolutional neural network (CNN) architecture to predict local SAR maps as well as peak-spatial SAR (ps-SAR) levels. We hypothesized that utilizing a three-channel 3D CNN, in which each channel is fed by a map, a phase-reversed map, and an MR image, would improve prediction accuracies and decrease uncertainties in the predictions. We generated 10 new head-neck body models, along with 389 3D pTx MRI data having different RF shim settings, with their B and local SAR maps to support efforts in this field.
The proposed three-channel 3D CNN predicted ps-SAR levels with an average overestimation error of 20%, which was better than the virtual observation points-based estimation error (i.e., 152% average overestimation). The proposed method decreased prediction uncertainties over 20% (i.e., 22.5%-17.7%) compared to other methods. A safety factor of 1.20 would be enough to avoid underestimations for the dataset generated in this work.
Multichannel 3D CNN networks can be promising in predicting local SAR values and perform predictions within a second, making them clinically useful as an alternative to virtual observation points-based methods.
预测 7T 并行传输（pTx）系统中人体头部的特定部位比吸收率（SAR）分布。
在 7T 时，电磁能量在组织中的沉积是不均匀的，pTx 系统的各个通道的干扰模式可能导致局部 SAR 值增加，而这些增加的 SAR 值只能通过非常高的安全裕度来估计。我们提出、设计并演示了一种多通道 3D 卷积神经网络（CNN）架构，用于预测局部 SAR 图和峰值空间 SAR（ps-SAR）水平。我们假设，利用三通道 3D CNN，其中每个通道由一个相位反转图、一个 图和一个磁共振图像输入，可以提高预测精度并降低预测中的不确定性。我们生成了 10 个新的头颈部体模，以及 389 个具有不同射频调谐设置的 3D pTx MRI 数据，以及它们的 B 和局部 SAR 图，以支持该领域的研究。
所提出的三通道 3D CNN 预测 ps-SAR 水平的平均高估误差为 20%，优于基于虚拟观察点的估计误差（即平均高估 152%）。与其他方法相比，该方法降低了 20%以上的预测不确定性（即 22.5%-17.7%）。对于在这项工作中生成的数据集，安全系数为 1.20 就足以避免低估。
多通道 3D CNN 网络在预测局部 SAR 值方面具有很大的潜力，并且可以在一秒钟内完成预测，因此作为基于虚拟观察点的方法的替代方法，在临床上具有很大的应用价值。
