Li Haoran, Yang Xiaomin, Yang Sihan, Wang Daoyong, Jeon Gwanggil
IEEE J Biomed Health Inform. 2023 Oct;27(10):4660-4671. doi: 10.1109/JBHI.2022.3216887. Epub 2023 Oct 5.
Increasingly serious health problems have made the usage of computed tomography surge. Therefore, algorithms for processing CT images are becoming more and more abundant. These algorithms can lessen the harm of cumulative radiation in CT technology for the patient while eliminating the noise of image caused by dose reduction. However, the mainstream CNN-based algorithms are inefficient when dealing with features in broad regions. Inspired by the large receptive field of transformer framework, this paper designs an end-to-end low-dose CT (LDCT) denoising network based on the transformer. The overall network contains a main branch and dual side branches. Specifically, the overlapping-free window-based self-attention transformer block is adopted on the main branch to realize image denoising. On the dual side branches, we propose double enhancement module to enrich edge, texture, and context information of LDCT images. Meanwhile, the receptive field of network is further enlarged after processing, which is helpful for building model's long-range dependencies. The outputs of the side branches are concatenated for enhancing information and generating high-quality CT images. In addition, to better train the network, we introduce a compound loss function including mean squared error (MSE), multi-scale perceptual (MSP), and Sobel-L1 (SL) to make the denoised image closer to the targeted norm-dose CT (NDCT) image. Lastly, we conducted experiments on two clinical datasets including abdomen, head, and chest LDCT images with 25%, 25%, and 10% of the full dose, respectively. The experimental results demonstrated that the proposed DEformer achieved better denoising performance than the existing algorithms.
日益严重的健康问题使得计算机断层扫描的使用量激增。因此，用于处理CT图像的算法越来越丰富。这些算法可以减少CT技术中累积辐射对患者的危害，同时消除因剂量降低而产生的图像噪声。然而，主流的基于卷积神经网络（CNN）的算法在处理大面积区域的特征时效率低下。受Transformer框架大感受野的启发，本文设计了一种基于Transformer的端到端低剂量CT（LDCT）去噪网络。整个网络包含一个主分支和两个侧分支。具体来说，主分支采用基于无重叠窗口的自注意力Transformer模块来实现图像去噪。在两个侧分支上，我们提出了双重增强模块来丰富LDCT图像的边缘、纹理和上下文信息。同时，网络的感受野在处理后进一步扩大，这有助于建立模型的长程依赖关系。将侧分支的输出进行拼接以增强信息并生成高质量的CT图像。此外，为了更好地训练网络，我们引入了一个复合损失函数，包括均方误差（MSE）、多尺度感知（MSP）和Sobel-L1（SL），以使去噪后的图像更接近目标标准剂量CT（NDCT）图像。最后，我们在两个临床数据集上进行了实验，分别包括腹部、头部和胸部的LDCT图像，其剂量分别为全剂量的25%、25%和10%。实验结果表明，所提出的DEformer网络比现有算法具有更好的去噪性能。
