School of Software, Yunnan University, Kunming 650091, Yunnan, China.
Engineering Research Center of Cyberspace, Yunnan University, Kunming 650000, Yunnan, China.
Comput Intell Neurosci. 2022 Aug 3;2022:2692301. doi: 10.1155/2022/2692301. eCollection 2022.
Low-dose CT (LDCT) images can reduce the radiation damage to the patients; however, the unavoidable information loss will influence the clinical diagnosis under low-dose conditions, such as noise, streak artifacts, and smooth details. LDCT image denoising is a significant topic in medical image processing to overcome the above deficits. This work proposes an improved DD-Net (DenseNet and deconvolution-based network) joint local filtered mechanism, the DD-Net is enhanced by introducing improved residual dense block to strengthen the feature representation ability, and the local filtered mechanism and gradient loss are also employed to effectively restore the subtle structures. First, the LDCT image is inputted into the network to obtain the denoised image. The original loss between the denoised image and normal-dose CT (NDCT) image is calculated, and the difference image between the NDCT image and the denoised image is obtained. Second, a mask image is generated by taking a threshold operation to the difference image, and the filtered LDCT and NDCT images are obtained by conducting an elementwise multiplication operation with LDCT and NDCT images using the mask image. Third, the filtered image is inputted into the network to obtain the filtered denoised image, and the correction loss is calculated. At last, the sum of original loss and correction loss of the improved DD-Net is used to optimize the network. Considering that it is insufficient to generate the edge information using the combination of mean square error (MSE) and multiscale structural similarity (MS-SSIM), we introduce the gradient loss that can calculate the loss of the high-frequency portion. The experimental results show that the proposed method can achieve better performance than conventional schemes and most neural networks. Our source code is made available at https://github.com/LHE-IT/Low-dose-CT-Image-Denoising/tree/main/Local Filtered Mechanism.
低剂量 CT（LDCT）图像可以减少对患者的辐射损伤；然而，在低剂量条件下，不可避免的信息丢失会影响临床诊断，例如噪声、条纹伪影和细节平滑。LDCT 图像去噪是医学图像处理中的一个重要课题，旨在克服上述缺陷。本工作提出了一种改进的 DD-Net（基于密集网络和卷积的网络）联合局部滤波机制，通过引入改进的残差密集块来增强特征表示能力，增强 DD-Net，并采用局部滤波机制和梯度损失有效地恢复细微结构。首先，将 LDCT 图像输入网络以获得去噪图像。计算去噪图像与正常剂量 CT（NDCT）图像之间的原始损失，并获得 NDCT 图像与去噪图像之间的差值图像。其次，通过对差值图像进行阈值操作生成掩模图像，并通过使用掩模图像对 LDCT 和 NDCT 图像进行逐元素乘法运算，得到滤波后的 LDCT 和 NDCT 图像。然后，将滤波后的图像输入网络以获得滤波后的去噪图像，并计算校正损失。最后，使用改进的 DD-Net 的原始损失和校正损失的总和来优化网络。考虑到使用均方误差（MSE）和多尺度结构相似性（MS-SSIM）的组合来生成边缘信息是不够的，我们引入了可以计算高频部分损失的梯度损失。实验结果表明，该方法的性能优于传统方案和大多数神经网络。我们的源代码可在 https://github.com/LHE-IT/Low-dose-CT-Image-Denoising/tree/main/Local Filtered Mechanism 获得。
