A Universal Intensity Standardization Method Based on a Many-to-One Weak-Paired Cycle Generative Adversarial Network for Magnetic Resonance Images
A Universal Intensity Standardization Method Based on a Many-to-One Weak-Paired Cycle Generative Adversarial Network for Magnetic Resonance Images
复制标题
DOI：
10.1109/tmi.2019.2894692
复制
发表时间：
2019-09-01
影响因子：
10.6
通讯作者：
Yu, Jinhua
中科院分区：
文献类型：
--
作者：
Gao, Yuan;Liu, Yingchao;Yu, Jinhua
在磁共振成像（MRI）中，不同的成像设置导致特定成像对象的强度分布不同，这给数据驱动的医疗应用带来了巨大的多样性。为了使多中心、多机器的磁共振图像强度分布标准化，提出了一种基于循环生成对抗网络（CycleGAN）的框架。它利用一个统一的前向生成对抗网络（GAN）路径和多个独立的后向生成对抗网络路径，将不同组的图像转换为单个参考图像。为了保留图像细节和防止分辨率损失，在CycleGAN生成器中应用了两个跳转连接。为了充分利用器官结构的先验知识，提高gan的性能，设计了弱对策略。实验在t2flair图像数据库中进行，该数据库包含489例患者的8192张切片。该数据库来自4家医院和5台MRI扫描仪，并根据不同的成像参数分为9组。与代表性算法相比，峰值信噪比、直方图相关性和结构相似度平均分别提高3.7%、5.1%和0.1%；梯度幅度相似偏差、均方误差和平均差异分别平均降低19.0%、15.7%和9.9%。实验还表明，在不同的训练集配置下，所提出的模型具有鲁棒性，并且与原始的CycleGAN相比，所提出的框架具有有效性。因此，该方法可以有效地对不同成像设置的MR图像进行标准化，有利于各种数据驱动的应用。
In magnetic resonance imaging (MRI), different imaging settings lead to various intensity distributions for a specific imaging object, which brings huge diversity to data-driven medical applications. To standardize the intensity distribution of magnetic resonance (MR) images from multiple centers and multiple machines using one model, a cycle generative adversarial network (CycleGAN)-based framework is proposed. It utilizes a unified forward generative adversarial network (GAN) path and multiple independent backward GAN paths to transform images in different groups into a single reference one. To preserve image details and prevent resolution loss, two jump connections are applied in the CycleGAN generators. A weak-pair strategy is designed to fully utilize the prior knowledge of the organ structure and promote the performance of the GANs. The experiments were conducted on a T2-FLAIR image database with 8192 slices from 489 patients. The database was obtained from four hospitals and five MRI scanners and was divided into nine groups with different imaging parameters. Compared with the representative algorithms, the peak signal-to-noise ratio, the histogram correlation, and the structural similarity were increased by 3.7%, 5.1%, and 0.1% on average, respectively; the gradient magnitude similarity deviation, the mean square error, and the average disparity were reduced by 19.0%, 15.7%, and 9.9% on average, respectively. Experiments also showed the robustness of the proposed model with a different training set configuration and effectiveness of the proposed framework over the original CycleGAN. Therefore, the MR images with different imaging settings could be efficiently standardized by the proposed method, which would benefit various data-driven applications.