Zhang Haowen, Zhang Pengcheng, Cheng Weiting, Li Shu, Yan Rongbiao, Hou Ruifeng, Gui Zhiguo, Liu Yi, Chen Yang
State Key Laboratory of Dynamic Testing Technology, North University of China, Taiyuan 030051, People's Republic of China.
Key Laboratory of Computer Network and Information Integration (Southeast University), Ministry of Education, Nanjing 210096, People's Republic of China.
Phys Med Biol. 2023 Dec 11;68(24). doi: 10.1088/1361-6560/aced33.
Various deep learning methods have recently been used for low dose CT (LDCT) denoising. Aggressive denoising may destroy the edge and fine anatomical structures of CT images. Therefore a key issue in LDCT denoising tasks is the difficulty of balancing noise/artifact suppression and edge/structure preservation.We proposed an LDCT denoising network based on the encoder-decoder structure, namely the Learnable PM diffusion coefficient and efficient attention network (PMA-Net). First, using the powerful feature modeling capability of partial differential equations, we constructed a multiple learnable edge module to generate precise edge information, incorporating the anisotropic image processing idea of Perona-Malik (PM) model into the neural network. Second, a multiscale reformative coordinate attention module was designed to extract multiscale information. Non-overlapping dilated convolution capturing abundant contextual content was combined with coordinate attention which could embed the spatial location information of important features into the channel attention map. Finally, we imposed additional constraints on the edge information using edge-enhanced multiscale perceptual loss to avoid structure loss and over-smoothing.Experiments are conducted on simulated and real datasets. The quantitative and qualitative results show that the proposed method has better performance in suppressing noise/artifacts and preserving edges/structures.This work proposes a novel edge feature extraction method that unfolds partial differential equation into neural networks, which contributes to the interpretability and clinical application value of neural network.
近年来，各种深度学习方法已被用于低剂量CT（LDCT）去噪。过度去噪可能会破坏CT图像的边缘和精细解剖结构。因此，LDCT去噪任务中的一个关键问题是难以平衡噪声/伪影抑制与边缘/结构保留。我们提出了一种基于编码器-解码器结构的LDCT去噪网络，即可学习的PM扩散系数和高效注意力网络（PMA-Net）。首先，利用偏微分方程强大的特征建模能力，我们构建了一个多可学习边缘模块来生成精确的边缘信息，将Perona-Malik（PM）模型的各向异性图像处理思想融入神经网络。其次，设计了一个多尺度改进坐标注意力模块来提取多尺度信息。捕捉丰富上下文内容的非重叠扩张卷积与坐标注意力相结合，坐标注意力可以将重要特征的空间位置信息嵌入通道注意力图中。最后，我们使用边缘增强多尺度感知损失对边缘信息施加额外约束，以避免结构损失和过度平滑。在模拟和真实数据集上进行了实验。定量和定性结果表明，所提出的方法在抑制噪声/伪影和保留边缘/结构方面具有更好的性能。这项工作提出了一种将偏微分方程展开到神经网络中的新颖边缘特征提取方法，这有助于提高神经网络的可解释性和临床应用价值。
