Center for Magnetic Resonance Research, Radiology, Medical School, University of Minnesota, Minneapolis, Minnesota, USA.
Magn Reson Med. 2022 Aug;88(2):727-741. doi: 10.1002/mrm.29238. Epub 2022 Apr 10.
To propose a novel deep learning (DL) approach to transmit-B (B )-artifact mitigation without direct use of parallel transmission (pTx), by predicting pTx images from single-channel transmission (sTx) images.
A deep encoder-decoder convolutional neural network was constructed and trained to learn the mapping from sTx to pTx images. The feasibility was demonstrated using 7 T Human-Connectome Project (HCP)-style diffusion MRI. The training dataset comprised images acquired on 5 healthy subjects using commercial Nova RF coils. Relevant hyperparameters were tuned with a nested cross-validation, and the generalization performance evaluated using a regular cross-validation.
Our DL method effectively improved the image quality for sTx images by restoring the signal dropout, with quality measures (including normalized root-mean-square error, peak SNR, and structural similarity index measure) improved in most brain regions. The improved image quality was translated into improved performances for diffusion tensor imaging analysis; our method improved accuracy for fractional anisotropy and mean diffusivity estimations, reduced the angular errors of principal eigenvectors, and improved the fiber orientation delineation relative to sTx images. Moreover, the final DL model trained on data of all 5 subjects was successfully used to predict pTx images for unseen new subjects (randomly selected from the 7 T HCP database), effectively recovering the signal dropout and improving color-coded fractional anisotropy maps with largely reduced noise levels.
The proposed DL method has potential to provide images with reduced B1 artifacts in healthy subjects even when pTx resources are inaccessible on the user side.
提出一种新的深度学习（DL）方法，通过从单通道传输（sTx）图像预测并行传输（pTx）图像，来减轻 B1 伪影。
构建并训练了一个深度编解码器卷积神经网络，以学习从 sTx 到 pTx 图像的映射。使用 7T 人类连接组计划（HCP）风格的扩散 MRI 证明了该方法的可行性。训练数据集由使用商用 Nova RF 线圈在 5 名健康受试者上采集的图像组成。使用嵌套交叉验证调整了相关超参数，并使用常规交叉验证评估了泛化性能。
我们的 DL 方法通过恢复信号缺失有效地改善了 sTx 图像的质量，在大多数脑区提高了质量度量（包括归一化均方根误差、峰值信噪比和结构相似性指数测量）。改善的图像质量转化为扩散张量成像分析性能的提高；我们的方法提高了各向异性分数和平均扩散系数的估计准确性，减少了主特征向量的角度误差，并相对于 sTx 图像改善了纤维方向描绘。此外，在所有 5 名受试者的数据上训练的最终 DL 模型成功地用于预测看不见的新受试者（从 7T HCP 数据库中随机选择）的 pTx 图像，有效地恢复了信号缺失，并改善了彩色编码各向异性分数图，同时大大降低了噪声水平。
该方法有可能为健康受试者提供减轻 B1 伪影的图像，即使在用户端无法获得 pTx 资源的情况下。
