Department of Pulmonary and Critical Care Medicine, Beijing Chao-Yang Hospital, Capital Medical University, Beijing, 100020, People's Republic of China.
Beijing Institute of Respiratory Medicine, Beijing, 100020, People's Republic of China.
Med Biol Eng Comput. 2022 Aug;60(8):2321-2333. doi: 10.1007/s11517-022-02589-x. Epub 2022 Jun 24.
Chronic obstructive pulmonary disease (COPD) is a common disease with high morbidity and mortality, where early detection benefits the population. However, the early diagnosis rate of COPD is low due to the absence or slight early symptoms. In this paper, a novel method based on graph convolution network (GCN) for early detection of COPD is proposed, which uses small and weakly labeled chest computed tomography image data from the publicly available Danish Lung Cancer Screening Trial database. The key idea is to construct a graph using regions of interest randomly selected from the segmented lung parenchyma and then input it into the GCN model for COPD detection. In this way, the model can not only extract the feature information of each region of interest but also the topological structure information between regions of interest, that is, graph structure information. The proposed GCN model achieves an acceptable performance with an accuracy of 0.77 and an area under a curve of 0.81, which is higher than the previous studies on the same dataset. GCN model also outperforms several state-of-the-art methods trained at the same time. As far as we know, it is also the first time using the GCN model on this dataset for COPD detection.
慢性阻塞性肺疾病（COPD）是一种发病率和死亡率都很高的常见疾病，早期发现对人群有益。然而，由于缺乏或轻微的早期症状，COPD 的早期诊断率较低。在本文中，我们提出了一种基于图卷积网络（GCN）的 COPD 早期检测新方法，该方法使用了来自公开的丹麦肺癌筛查试验数据库中随机选择的小而弱标记的胸部计算机断层图像数据。其主要思想是使用从分割的肺实质中随机选择的感兴趣区域构建图，然后将其输入到 GCN 模型中以进行 COPD 检测。通过这种方式，该模型不仅可以提取每个感兴趣区域的特征信息，还可以提取感兴趣区域之间的拓扑结构信息，即图结构信息。所提出的 GCN 模型在同一数据集上的先前研究中取得了可接受的性能，其准确率为 0.77，曲线下面积为 0.81。该模型还优于同时训练的几种最先进的方法。据我们所知，这也是首次在该数据集上使用 GCN 模型进行 COPD 检测。
