School of Automation and Electrical Engineering, Shenyang Ligong University, Shenyang, China.
State Key Laboratory of Robotics, Shenyang Institute of Automation, Chinese Academy of Sciences, Shenyang, China.
Int J Comput Assist Radiol Surg. 2021 Sep;16(9):1425-1434. doi: 10.1007/s11548-021-02418-w. Epub 2021 Jun 5.
The global health crisis caused by coronavirus disease 2019 (COVID-19) is a common threat facing all humankind. In the process of diagnosing COVID-19 and treating patients, automatic COVID-19 lesion segmentation from computed tomography images helps doctors and patients intuitively understand lung infection. To effectively quantify lung infections, a convolutional neural network for automatic lung infection segmentation based on deep learning is proposed.
This new type of COVID-19 lesion segmentation network is based on a U-Net backbone. First, a coarse segmentation network is constructed to extract the lung areas. Second, in the encoding and decoding process of the fine segmentation network, a new soft attention mechanism, namely the dilated convolutional attention (DCA) mechanism, is introduced to enable the network to focus on better quantitative information to strengthen the network's segmentation ability in the subtle areas of the lesions.
The experimental results show that the average Dice similarity coefficient (DSC), sensitivity (SEN), specificity (SPE) and area under the curve of DUDA-Net are 87.06%, 90.85%, 99.59% and 0.965, respectively. In addition, the introduction of a cascade U-shaped network scheme and DCA mechanism can improve the DSC by 24.46% and 14.33%, respectively.
The proposed DUDA-Net approach can automatically segment COVID-19 lesions with excellent performance, which indicates that the proposed method is of great clinical significance. In addition, the introduction of a coarse segmentation network and DCA mechanism can improve the COVID-19 segmentation performance.
由 2019 年冠状病毒病（COVID-19）引起的全球卫生危机是全人类共同面临的共同威胁。在 COVID-19 的诊断和治疗过程中，从计算机断层扫描图像中自动进行 COVID-19 病变分割有助于医生和患者直观地了解肺部感染。为了有效量化肺部感染，提出了一种基于深度学习的自动肺部感染分割卷积神经网络。
这种新型 COVID-19 病变分割网络基于 U-Net 骨干网络。首先，构建一个粗分割网络以提取肺部区域。其次，在精细分割网络的编码和解码过程中，引入了一种新的软注意机制，即扩张卷积注意（DCA）机制，使网络能够更好地关注定量信息，从而增强网络在病变细微区域的分割能力。
实验结果表明，DUDA-Net 的平均 Dice 相似系数（DSC）、灵敏度（SEN）、特异性（SPE）和曲线下面积（AUC）分别为 87.06%、90.85%、99.59%和 0.965。此外，级联 U 形网络方案和 DCA 机制的引入分别可以将 DSC 提高 24.46%和 14.33%。
提出的 DUDA-Net 方法可以自动分割 COVID-19 病变，具有出色的性能，表明该方法具有重要的临床意义。此外，引入粗分割网络和 DCA 机制可以提高 COVID-19 的分割性能。
