当前位置: X-MOL 学术IEEE Trans. Comput. Imaging › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
CaGAN: a Cycle-consistent Generative Adversarial Network with Attention for Low-Dose CT Imaging
IEEE Transactions on Computational Imaging ( IF 4.2 ) Pub Date : 2020-01-01 , DOI: 10.1109/tci.2020.3012928
Zhiyuan Huang , Zixiang Chen , Qiyang Zhang , Guotao Quan , Min Ji , Chengjin Zhang , Yongfeng Yang , Xin Liu , Dong Liang , Hairong Zheng , Zhanli Hu

Although lowering X-ray radiation helps reduce the risk of cancer in patients, low-dose computed tomography (LDCT) technology usually leads to poor image quality, such as amplified mottle noise and streak artifacts, which severely impact the diagnostic results. To improve diagnostic performance, we propose an algorithm based on a cycle-consistent generative adversarial network (CycleGAN) to suppress noise and reduce artifacts. In addition, we include attention mechanisms in the proposed network to expand the receptive field and capture richer contextual dependencies. Unlike traditional methods that manually match similar local blocks, our proposed method can autonomously learn the relationship between local features and their global dependencies. Specifically, two different types of attention modules (criss-cross self-attention (CCSA) and channel attention (CA)) are adopted to enhance feature interdependencies in the spatial and channel dimensions separately. Because of the CCSA mechanism, noise and artifacts can be restored using cues from all local feature locations; the CA mechanism adaptively reassigns the weights of each feature map. Furthermore, we also performed a diagnostic quality assessment of the results and ablation studies of the loss functions and the structural modules, which showed the validity of our proposed method. Extensive experiments show that our proposed method achieves better metrics and visual effects than state-of-the-art methods.

中文翻译:

CaGAN:一个循环一致的生成对抗网络,注意低剂量 CT 成像

尽管降低 X 射线辐射有助于降低患者患癌症的风险,但低剂量计算机断层扫描 (LDCT) 技术通常会导致图像质量不佳,例如放大的斑驳噪声和条纹伪影,严重影响诊断结果。为了提高诊断性能,我们提出了一种基于循环一致生成对抗网络(CycleGAN)的算法来抑制噪声并减少伪影。此外,我们在提议的网络中包含注意力机制以扩展感受野并捕获更丰富的上下文依赖关系。与手动匹配相似局部块的传统方法不同,我们提出的方法可以自主学习局部特征与其全局依赖关系之间的关系。具体来说,采用两种不同类型的注意力模块(交叉自注意力(CCSA)和通道注意力(CA))分别增强空间和通道维度上的特征相互依赖性。由于 CCSA 机制,可以使用来自所有局部特征位置的线索来恢复噪声和伪影;CA 机制自适应地重新分配每个特征图的权重。此外,我们还对损失函数和结构模块的结果和消融研究进行了诊断质量评估,这表明了我们提出的方法的有效性。大量实验表明,我们提出的方法比最先进的方法实现了更好的度量和视觉效果。可以使用来自所有局部特征位置的线索来恢复噪声和伪影;CA 机制自适应地重新分配每个特征图的权重。此外,我们还对损失函数和结构模块的结果和消融研究进行了诊断质量评估,这表明了我们提出的方法的有效性。大量实验表明,我们提出的方法比最先进的方法实现了更好的度量和视觉效果。可以使用来自所有局部特征位置的线索来恢复噪声和伪影;CA 机制自适应地重新分配每个特征图的权重。此外,我们还对损失函数和结构模块的结果和消融研究进行了诊断质量评估,这表明了我们提出的方法的有效性。大量实验表明,我们提出的方法比最先进的方法实现了更好的度量和视觉效果。
更新日期:2020-01-01
down
wechat
bug