Lu Xiaoyan, Xu Yang, Yuan Wenhao
College of Big Data and Information Engineering, Guizhou University, Guiyang, Guizhou People's Republic of China.
Guiyang Aluminum Magnesium Design and Research Institute Co., Ltd, Guiyang, Guizhou People's Republic of China.
Evol Syst (Berl). 2023;14(3):519-532. doi: 10.1007/s12530-022-09466-w. Epub 2022 Sep 19.
Accurate segmentation of infected regions in lung computed tomography (CT) images is essential to improve the timeliness and effectiveness of treatment for coronavirus disease 2019 (COVID-19). However, the main difficulties in developing of lung lesion segmentation in COVID-19 are still the fuzzy boundary of the lung-infected region, the low contrast between the infected region and the normal trend region, and the difficulty in obtaining labeled data. To this end, we propose a novel dual-task consistent network framework that uses multiple inputs to continuously learn and extract lung infection region features, which is used to generate reliable label images (pseudo-labels) and expand the dataset. Specifically, we periodically feed multiple sets of raw and data-enhanced images into two trunk branches of the network; the characteristics of the lung infection region are extracted by a lightweight double convolution (LDC) module and fusiform equilibrium fusion pyramid (FEFP) convolution in the backbone. According to the learned features, the infected regions are segmented, and pseudo-labels are made based on the semi-supervised learning strategy, which effectively alleviates the semi-supervised problem of unlabeled data. Our proposed semi-supervised dual-task balanced fusion network (DBF-Net) creates pseudo-labels on the COVID-SemiSeg dataset and the COVID-19 CT segmentation dataset. Furthermore, we perform lung infection segmentation on the DBF-Net model, with a segmentation sensitivity of 70.6% and specificity of 92.8%. The results of the investigation indicate that the proposed network greatly enhances the segmentation ability of COVID-19 infection.
准确分割肺部计算机断层扫描（CT）图像中的感染区域对于提高2019冠状病毒病（COVID-19）治疗的及时性和有效性至关重要。然而，COVID-19肺部病变分割发展中的主要困难仍然是肺部感染区域边界模糊、感染区域与正常区域之间对比度低以及获取标注数据困难。为此，我们提出了一种新颖的双任务一致性网络框架，该框架使用多个输入来持续学习和提取肺部感染区域特征，用于生成可靠的标注图像（伪标签）并扩展数据集。具体来说，我们定期将多组原始图像和数据增强图像输入到网络的两个主干分支中；肺部感染区域的特征通过主干中的轻量级双卷积（LDC）模块和梭形平衡融合金字塔（FEFP）卷积来提取。根据学习到的特征分割感染区域，并基于半监督学习策略制作伪标签，有效缓解了未标注数据的半监督问题。我们提出的半监督双任务平衡融合网络（DBF-Net）在COVID-SemiSeg数据集和COVID-19 CT分割数据集上创建伪标签。此外，我们在DBF-Net模型上进行肺部感染分割，分割灵敏度为70.6%，特异性为92.8%。研究结果表明，所提出的网络大大提高了COVID-19感染的分割能力。
