Tan Chaoqun, Yang Mingming, You Zhisheng, Chen Hu, Zhang Yi
National Key Laboratory of Fundamental Science on Synthetic Vision, Sichuan University, Chengdu 610065, China.
College of Computer Science, Sichuan University, Chengdu 610065, China.
Precis Clin Med. 2022 May 25;5(2):pbac011. doi: 10.1093/pcmedi/pbac011. eCollection 2022 Jun.
Low-dose computed tomography (LDCT) denoising is an indispensable procedure in the medical imaging field, which not only improves image quality, but can mitigate the potential hazard to patients caused by routine doses. Despite the improvement in performance of the cycle-consistent generative adversarial network (CycleGAN) due to the well-paired CT images shortage, there is still a need to further reduce image noise while retaining detailed features. Inspired by the residual encoder-decoder convolutional neural network (RED-CNN) and U-Net, we propose a novel unsupervised model using CycleGAN for LDCT imaging, which injects a two-sided network into selective kernel networks (SK-NET) to adaptively select features, and uses the patchGAN discriminator to generate CT images with more detail maintenance, aided by added perceptual loss. Based on patch-based training, the experimental results demonstrated that the proposed SKFCycleGAN outperforms competing methods in both a clinical dataset and the Mayo dataset. The main advantages of our method lie in noise suppression and edge preservation.
低剂量计算机断层扫描（LDCT）去噪是医学成像领域不可或缺的一项操作，它不仅能提高图像质量，还能减轻常规剂量对患者造成的潜在危害。尽管由于配对良好的CT图像短缺，循环一致生成对抗网络（CycleGAN）的性能有所提升，但仍需要在保留细节特征的同时进一步降低图像噪声。受残差编码器-解码器卷积神经网络（RED-CNN）和U-Net的启发，我们提出了一种用于LDCT成像的新型无监督模型，该模型使用CycleGAN，将双边网络注入选择性内核网络（SK-NET）以自适应选择特征，并使用PatchGAN鉴别器生成具有更多细节保留的CT图像，同时添加感知损失作为辅助。基于基于补丁的训练，实验结果表明，所提出的SKFCycleGAN在临床数据集和梅奥数据集中均优于竞争方法。我们方法的主要优点在于噪声抑制和边缘保留。
