Acute exacerbation prediction of COPD based on Auto-metric graph neural network with inspiratory and expiratory chest CT images
Shicong Wang,
Wei Li,
Nanrong Zeng,
Jiaxuan Xu,
Yingjian Yang,
Xingguang Deng,
Ziran Chen,
Wenxin Duan,
Yang Liu,
Yingwei Guo,
Rongchang Chen,
Yan Kang
Affiliations
Shicong Wang
College of Health Science and Environmental Engineering, Shenzhen Technology University, Shenzhen 518118, China; School of Applied Technology, Shenzhen University, Shenzhen 518060, China
Wei Li
College of Health Science and Environmental Engineering, Shenzhen Technology University, Shenzhen 518118, China
Nanrong Zeng
College of Health Science and Environmental Engineering, Shenzhen Technology University, Shenzhen 518118, China; School of Applied Technology, Shenzhen University, Shenzhen 518060, China
Jiaxuan Xu
The First Affiliated Hospital of Guangzhou Medical University, State Key Laboratory of Respiratory Disease, National Clinical Research Center for Respiratory Disease, Guangzhou Institute of Respiratory Health, The National Center for Respiratory Medicine, Guangzhou 510120, China
Yingjian Yang
College of Health Science and Environmental Engineering, Shenzhen Technology University, Shenzhen 518118, China; College of Medicine and Biological Information Engineering, Northeastern University, Shenyang 110169, China
Xingguang Deng
College of Health Science and Environmental Engineering, Shenzhen Technology University, Shenzhen 518118, China; College of Medicine and Biological Information Engineering, Northeastern University, Shenyang 110169, China
Ziran Chen
College of Health Science and Environmental Engineering, Shenzhen Technology University, Shenzhen 518118, China
Wenxin Duan
College of Health Science and Environmental Engineering, Shenzhen Technology University, Shenzhen 518118, China; School of Applied Technology, Shenzhen University, Shenzhen 518060, China
Yang Liu
College of Health Science and Environmental Engineering, Shenzhen Technology University, Shenzhen 518118, China
Yingwei Guo
College of Health Science and Environmental Engineering, Shenzhen Technology University, Shenzhen 518118, China; College of Medicine and Biological Information Engineering, Northeastern University, Shenyang 110169, China
Rongchang Chen
The First Affiliated Hospital of Guangzhou Medical University, State Key Laboratory of Respiratory Disease, National Clinical Research Center for Respiratory Disease, Guangzhou Institute of Respiratory Health, The National Center for Respiratory Medicine, Guangzhou 510120, China; Department of Respiratory and Critical Care Medicine, First Affiliated Hospital of Southern University of Science and Technology, Second Clinical Medical College of Jinan University, Shenzhen People's Hospital, Shenzhen Institute of Respiratory Diseases, Shenzhen 518001, China
Yan Kang
College of Health Science and Environmental Engineering, Shenzhen Technology University, Shenzhen 518118, China; School of Applied Technology, Shenzhen University, Shenzhen 518060, China; College of Medicine and Biological Information Engineering, Northeastern University, Shenyang 110169, China; Engineering Research Centre of Medical Imaging and Intelligent Analysis, Ministry of Education, Shenyang 110169, China; Corresponding author. College of Health Science and Environmental Engineering, Shenzhen Technology University, Shenzhen 518118, China.
Chronic obstructive pulmonary disease (COPD) is a widely prevalent disease with significant mortality and disability rates and has become the third leading cause of death globally. Patients with acute exacerbation of COPD (AECOPD) often substantially suffer deterioration and death. Therefore, COPD patients deserve special consideration regarding treatment in this fragile population for pre-clinical health management. Based on the above, this paper proposes an AECOPD prediction model based on the Auto-Metric Graph Neural Network (AMGNN) using inspiratory and expiratory chest low-dose CT images. This study was approved by the ethics committee in the First Affiliated Hospital of Guangzhou Medical University. Subsequently, 202 COPD patients with inspiratory and expiratory chest CT Images and their annual number of AECOPD were collected after the exclusion. First, the inspiratory and expiratory lung parenchyma images of the 202 COPD patients are extracted using a trained ResU-Net. Then, inspiratory and expiratory lung Radiomics and CNN features are extracted from the 202 inspiratory and expiratory lung parenchyma images by Pyradiomics and pre-trained Med3D (a heterogeneous 3D network), respectively. Last, Radiomics and CNN features are combined and then further selected by the Lasso algorithm and generalized linear model for determining node features and risk factors of AMGNN, and then the AECOPD prediction model is established. Compared to related models, the proposed model performs best, achieving an accuracy of 0.944, precision of 0.950, F1-score of 0.944, ad area under the curve of 0.965. Therefore, it is concluded that our model may become an effective tool for AECOPD prediction.
