Low-dose computed tomography (LDCT) technology has attracted more and more attention in the field of medical imaging because of the reduction of radiation damage to the human body. However, the large amount of quantum noise contained in LDCT images can affect physicians’ judgment. To solve the problem of large amounts of quantum noise and artifacts in LDCT images, a convolutional neural network denoising model based on cartoon texture decomposition of images (CATCNN) is developed in this study based on deep learning. The model first uses a U-Net-based image decomposition sub-network to decompose LDCT images into cartoon images and texture images. The texture images are then denoised using a texture denoising sub-network based on edge protection and Efficient Channel Attention, finally, cartoon images are summed with the denoised texture images to obtain images with improved quality. Our experimental results demonstrate that the proposed model outperforms existing technologies, achieving a peak signal-to-noise ratio value of 33.4666 dB and a structural similarity value of 0.9193. The visual and quantitative evaluation results suggest that the CATCNN model effectively improves the quality of LDCT images.

低剂量计算机断层扫描（LDCT）技术由于减少了对人体的辐射损伤，在医学影像领域受到越来越多的关注。然而，LDCT图像中包含的大量量子噪声会影响医生的判断。针对LDCT图像中存在大量量子噪声和伪影的问题，本研究基于深度学习，提出了一种基于卡通图像纹理分解的卷积神经网络去噪模型（CATCNN）。该模型首先使用基于U-Net的图像分解子网络将LDCT图像分解为卡通图像和纹理图像。然后使用基于边缘保护和高效通道注意的纹理去噪子网络对纹理图像进行去噪，最后将卡通图像与去噪后的纹理图像相加以获得质量提高的图像。我们的实验结果表明，所提出的模型优于现有技术，达到了 33.4666 dB 的峰值信噪比值和 0.9193 的结构相似度值。视觉和定量评估结果表明CATCNN模型有效提高了LDCT图像的质量。