Low-Dose CT Image Synthesis for Domain Adaptation Imaging Using a Generative Adversarial Network With Noise Encoding Transfer Learning
Low-Dose CT Image Synthesis for Domain Adaptation Imaging Using a Generative Adversarial Network With Noise Encoding Transfer Learning
复制标题
基于带噪声编码传递学习的生成性对抗网络的领域适应成像低剂量CT图像合成
DOI：
10.1109/tmi.2023.3261822
复制
发表时间：
2023-09-01
影响因子：
10.6
通讯作者：
Tsui, Benjamin M. W.
中科院分区：
文献类型：
--
作者：
Li, Ming;Wang, Jiping;Tsui, Benjamin M. W.
基于训练数据的特征分布与测试数据的特征分布一致的假设，基于深度学习（DL）的图像处理方法已成功应用于低剂量X射线图像。然而，来自不同商用扫描仪的低剂量计算机断层扫描 (LDCT) 图像可能包含不同数量和类型的图像噪声，这违反了这一假设。此外，在将基于深度学习的图像处理方法应用于LDCT时，模拟和临床CT检查的LDCT图像的特征分布可能有很大不同。因此，使用来自一台特定扫描仪的模拟图像数据或 LDCT 图像训练的网络模型可能不适用于另一台 CT 扫描仪和图像处理任务。为了解决此类域适应问题，在本研究中，提出了一种具有噪声编码转移学习（NETL）的新型生成对抗网络（GAN）（或 GAN-NETL）来生成具有不同噪声风格的配对数据集。具体来说，我们提出了一种执行噪声编码算子并将其合并到生成器中以提取噪声风格的方法。同时，通过迁移学习（TL）方法，图像噪声编码算子将源域的噪声类型转换为目标域的噪声类型，以生成真实的噪声。使用一个公共数据集和两个私有数据集来评估所提出的方法。实验结果证明了我们提出的 GAN-NETL 模型在 LDCT 图像合成中的可行性和有效性。此外，我们使用合成的临床 LDCT 数据进行了额外的图像去噪研究，验证了所提出的合成方法在提高基于 DL 的 LDCT 处理方法性能方面的优点。
Deep learning (DL) based image processing methods have been successfully applied to low-dose x-ray images based on the assumption that the feature distribution of the training data is consistent with that of the test data. However, low-dose computed tomography (LDCT) images from different commercial scanners may contain different amounts and types of image noise, violating this assumption. Moreover, in the application of DL based image processing methods to LDCT, the feature distributions of LDCT images from simulation and clinical CT examination can be quite different. Therefore, the network models trained with simulated image data or LDCT images from one specific scanner may not work well for another CT scanner and image processing task. To solve such domain adaptation problem, in this study, a novel generative adversarial network (GAN) with noise encoding transfer learning (NETL), or GAN-NETL, is proposed to generate a paired dataset with a different noise style. Specifically, we proposed a method to perform noise encoding operator and incorporate it into the generator to extract a noise style. Meanwhile, with a transfer learning (TL) approach, the image noise encoding operator transformed the noise type of the source domain to that of the target domain for realistic noise generation. One public and two private datasets are used to evaluate the proposed method. Experiment results demonstrated the feasibility and effectiveness of our proposed GAN-NETL model in LDCT image synthesis. In addition, we conduct additional image denoising study using the synthesized clinical LDCT data, which verified the merit of the proposed synthesis in improving the performance of the DL based LDCT processing method.