近年来，深度学习已被证明可以通过从无对比剂的磁共振成像 (contrast-free MRI) 序列合成无钆比增强MRI (gadolinium-free contrast-enhanced MRI, GFCE-MRI)，从而消除钆基对比剂 (GBCAs) 的使用，为医学界提供了一种摆脱钆基对比剂相关安全问题的替代方法。然而，由于MRI数据在不同机构之间存在高度异质性，再加上多机构数据的稀缺性，GFCE-MRI模型的推广能力评估一直面临重大挑战。尽管以前的研究已采用了各种数据归一化方法来解决异质性问题，但这仅限于单机构研究，并且目前没有标准的归一化方法。本研究旨在使用来自七个机构的数据，通过操作训练MRI数据的异质性，应用五种常用的归一化方法来调查GFCE-MRI模型的推广能力。我们应用了三种先进的神经网络，将T1加权和T2加权的MRI映射到对比增强MRI (contrast-enhanced MRI, CE-MRI)，用于合成患有鼻咽癌的患者的GFCE-MRI。分别使用三个机构的MRI数据生成了三个单机构模型，并联合使用三个机构的数据生成了一个三机构模型。这五种归一化方法被应用于每个模型的训练和测试数据的归一化。来自其他四个机构的MRI数据作为外部样本用于模型的推广能力评估。利用平均绝对误差 (mean absolute error, MAE) 和峰值信噪比 (peak signal-to-noise ratio, PSNR) 定量评估了GFCE-MRI与真实CE-MRI之间的质量。结果显示，所有单机构模型在外部样本上的表现显著下降。相比之下，使用Z-Score归一化的多机构数据训练的模型具有最佳的模型推广能力改进效果。

Recently, deep learning has been demonstrated to be feasible in eliminating the use of gadolinium-based contrast agents (GBCAs) through synthesizing gadolinium-free contrast-enhanced MRI (GFCE-MRI) from contrast-free MRI sequences, pro-viding the community with an alternative to get rid of GBCAs-associated safety issues in patients. Nevertheless, generalizability assessment of the GFCE-MRI model has been largely challenged by the high inter-institutional heterogeneity of MRI data, on top of the scarcity of multi-institutional data itself. Although various data normalization methods have been adopted in previous studies to address the heterogeneity issue, it has been limited to single-institutional investigation and there is no standard normalization approach presently. In this study, we aimed at investigating gener-alizability of GFCE-MRI model using data from seven institutions by manipulating heterogeneity of training MRI data under five popular normalization approaches. Three state-of-the-art neural networks were applied to map from T1-weighted and T2-weighted MRI to contrast-enhanced MRI (CE-MRI) for GFCE-MRI synthesis in patients with nasopharyngeal carcinoma. MRI data from three institutions were used separately to generate three uni-institution models and jointly for a tri-institution model. The five normalization methods were applied to normalize the training and testing data of each model. MRI data from the remaining four institutions served as external cohorts for model generalizability assessment. Quality of GFCE-MRI was quantitatively evaluated against ground-truth CE-MRI using mean absolute error (MAE) and peak signal-to-noise ratio (PSNR). Results showed that performance of all uni-institution models remarkably dropped on the external cohorts. By contrast, model trained using multi-institutional data with Z-Score normalization yielded the best model generalizability improvement.