Jiang Xiaoben, Zhu Yu, Zheng Bingbing, Yang Dawei
School of Information Science and Technology, East China University of Science and Technology, Shanghai, 200237 People's Republic of China.
Department of Pulmonary and Critical Care Medicine, Zhongshan Hospital, Fudan University, Shanghai, 200032 People's Republic of China.
Mach Vis Appl. 2021;32(4):100. doi: 10.1007/s00138-021-01224-3. Epub 2021 Jun 28.
Chest X-ray (CXR) is a medical imaging technology that is common and economical to use in clinical. Recently, coronavirus (COVID-19) has spread worldwide, and the second wave is rebounding strongly now with the coming winter that has a detrimental effect on the global economy and health. To make pre-diagnosis of COVID-19 as soon as possible, and reduce the work pressure of medical staff, making use of deep learning networks to detect positive CXR images of infected patients is a critical step. However, there are complex edge structures and rich texture details in the CXR images susceptible to noise that can interfere with the diagnosis of the machines and the doctors. Therefore, in this paper, we proposed a novel multi-resolution parallel residual CNN (named MPR-CNN) for CXR images denoising and special application for COVID-19 which can improve the image quality. The core of MPR-CNN consists of several essential modules. (a) Multi-resolution parallel convolution streams are utilized for extracting more reliable spatial and semantic information in multi-scale features. (b) Efficient channel and spatial attention can let the network focus more on texture details in CXR images with fewer parameters. (c) The adaptive multi-resolution feature fusion method based on attention is utilized to improve the expression of the network. On the whole, MPR-CNN can simultaneously retain spatial information in the shallow layers with high resolution and semantic information in the deep layers with low resolution. Comprehensive experiments demonstrate that our MPR-CNN can better retain the texture structure details in CXR images. Additionally, extensive experiments show that our MPR-CNN has a positive impact on CXR images classification and detection of COVID-19 cases from denoised CXR images.
胸部X光（CXR）是一种在临床中常用且经济的医学成像技术。近期，冠状病毒（COVID-19）已在全球范围内传播，随着冬季来临，第二波疫情正强劲反弹，这对全球经济和健康产生了不利影响。为了尽快对COVID-19进行预诊断，并减轻医护人员的工作压力，利用深度学习网络检测受感染患者的胸部X光阳性图像是关键一步。然而，胸部X光图像中存在复杂的边缘结构和丰富的纹理细节，容易受到噪声干扰，这可能会影响机器和医生的诊断。因此，在本文中，我们提出了一种新颖的多分辨率并行残差卷积神经网络（名为MPR-CNN）用于胸部X光图像去噪以及针对COVID-19的特殊应用，以提高图像质量。MPR-CNN的核心由几个关键模块组成。（a）多分辨率并行卷积流用于在多尺度特征中提取更可靠的空间和语义信息。（b）高效的通道和空间注意力机制可以让网络在参数较少的情况下更关注胸部X光图像中的纹理细节。（c）基于注意力的自适应多分辨率特征融合方法用于提升网络的表达能力。总体而言，MPR-CNN能够同时在高分辨率的浅层保留空间信息，在低分辨率的深层保留语义信息。综合实验表明，我们提出的MPR-CNN能够更好地保留胸部X光图像中的纹理结构细节。此外，大量实验表明，我们的MPR-CNN对胸部X光图像分类以及从去噪后的胸部X光图像中检测COVID-19病例具有积极影响。
