Zhang Ruifen, Zhang Qiyang, Wu Yin
Paul C. Lauterbur Research Center for Biomedical Imaging, Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, 1068 Xueyuan Boulevard, Xili, Nanshan, Shenzhen, 518055, Guangdong, China.
Research Center for Medical AI, Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, 1068 Xueyuan Boulevard, Xili, Nanshan, Shenzhen, 518055, Guangdong, China.
Neuroimage. 2025 May 15;312:121202. doi: 10.1016/j.neuroimage.2025.121202. Epub 2025 Apr 21.
Chemical exchange saturation transfer (CEST) magnetic resonance imaging (MRI) has emerged as a powerful tool to image endogenous or exogenous macromolecules. CEST contrast highly depends on radiofrequency irradiation B level. Spatial inhomogeneity of B field would bias CEST measurement. Conventional interpolation-based B correction method required CEST dataset acquisition under multiple B levels, substantially prolonging scan time. The recently proposed supervised deep learning approach reconstructed B inhomogeneity corrected CEST effect at the identical B as of the training data, hindering its generalization to other B levels. In this study, we proposed a Conditional Variational Autoencoder (CVAE)-based generative model to generate B inhomogeneity corrected Z spectra from single CEST acquisition. The model was trained from pixel-wise source-target paired Z spectra under multiple B with target B as a conditional variable. Numerical simulation and healthy human brain imaging at 5 T were respectively performed to evaluate the performance of proposed model in B inhomogeneity corrected CEST MRI. Results showed that the generated B-corrected Z spectra agreed well with the reference averaged from regions with subtle B inhomogeneity. Moreover, the performance of the proposed model in correcting B inhomogeneity in APT CEST effect, as measured by both MTR and [Formula: see text] at 3.5 ppm, were superior over conventional Z/contrast-B-interpolation and other deep learning methods, especially when target B were not included in sampling or training dataset. In summary, the proposed model allows generalized B inhomogeneity correction, benefiting quantitative CEST MRI in clinical routines.
化学交换饱和转移（CEST）磁共振成像（MRI）已成为一种用于对内源性或外源性大分子进行成像的强大工具。CEST对比度高度依赖于射频照射B水平。B场的空间不均匀性会使CEST测量产生偏差。传统的基于插值的B校正方法需要在多个B水平下采集CEST数据集，这大大延长了扫描时间。最近提出的监督深度学习方法在与训练数据相同的B水平下重建了经B不均匀性校正的CEST效应，阻碍了其对其他B水平的泛化。在本研究中，我们提出了一种基于条件变分自编码器（CVAE）的生成模型，用于从单次CEST采集中生成经B不均匀性校正的Z谱。该模型是根据多个B水平下像素级源 - 目标配对的Z谱进行训练的，其中目标B作为条件变量。分别进行了数值模拟和5T下的健康人脑成像，以评估所提出模型在经B不均匀性校正的CEST MRI中的性能。结果表明，生成的经B校正的Z谱与从具有细微B不均匀性的区域平均得到的参考值吻合良好。此外，所提出模型在校正APT CEST效应中的B不均匀性方面的性能，通过3.5ppm处的MTR和[公式：见原文]测量，优于传统的Z/对比度 - B插值和其他深度学习方法，特别是当目标B不包含在采样或训练数据集中时。总之，所提出的模型允许进行广义的B不均匀性校正，有利于临床常规中的定量CEST MRI。
