Skip to main content
SpringerLink
Log in

COPD stage detection: leveraging the auto-metric graph neural network with inspiratory and expiratory chest CT images

  • Original Article
  • Published:
Medical & Biological Engineering & Computing Aims and scope Submit manuscript

Abstract

Chronic obstructive pulmonary disease (COPD) is a common lung disease that can lead to restricted airflow and respiratory problems, causing a significant health, economic, and social burden. Detecting the COPD stage can provide a timely warning for prompt intervention in COPD patients. However, existing methods based on inspiratory (IN) and expiratory (EX) chest CT images are not sufficiently accurate and efficient in COPD stage detection. The lung region images are autonomously segmented from IN and EX chest CT images to extract the \(1,781\times 2\) lung radiomics and \(13,824\times 2\) 3D CNN features. Furthermore, a strategy for concatenating and selecting features was employed in COPD stage detection based on radiomics and 3D CNN features. Finally, we combine all the radiomics, 3D CNN features, and factor risks (age, gender, and smoking history) to detect the COPD stage based on the Auto-Metric Graph Neural Network (AMGNN). The AMGNN with radiomics and 3D CNN features achieves the best performance at 89.7\(\%\) of accuracy, 90.9\(\%\) of precision, 89.5\(\%\) of F1-score, and 95.8\(\%\) of AUC compared to six classic machine learning (ML) classifiers. Our proposed approach demonstrates high accuracy in detecting the stage of COPD using both IN and EX chest CT images. This method can potentially establish an efficient diagnostic tool for patients with COPD. Additionally, we have identified radiomics and 3D CNN as more appropriate biomarkers than Parametric Response Mapping (PRM). Moreover, our findings indicate that expiration yields better results than inspiration in detecting the stage of COPD.

Graphical Abstract

The workflow of this study. (a) The IN and EX lung region is segmented using a well trained U Net (R231). (b) Radiomics features are obtained through the PyRadiomics tool, and 3D CNN features are extracted using the frozen encoder in the pre trained Med3D model. (c) The IN+EX radiomics and IN+EX 3D CNN features are concatenated, and the Lasso algorithm is subsequently applied to screen for useful data. (d) The selected features and ri sk factors are sent to the AMGNN, resulting in COPD multi classification outcomes.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9

Similar content being viewed by others

Notes

  1. https://www.clinicaltrials.gov

  2. https://www.imbio.com/products/lung-density-analysis-functional/

References

  1. Singh D, Agusti A, Anzueto A, Barnes PJ, Bourbeau J, Celli BR, Criner GJ, Frith P, Halpin DM, Han M, et al (2019) Global strategy for the diagnosis, management, and prevention of chronic obstructive lung disease: the gold science committee report 2019. Eur Respir J 53(5)

  2. Naghavi M, Abajobir AA, Abbafati C, Abbas KM, Abd-Allah F, Abera SF, Aboyans V, Adetokunboh O, Afshin A, Agrawal A, et al (2017) Global, regional, and national age-sex specific mortality for 264 causes of death, 1980–2016: a systematic analysis for the global burden of disease study 2016. The Lancet 390(10100):1151–1210

  3. Fabbri L, Pauwels R, Hurd S (2007) Global strategy for the diagnosis, management, and prevention of chronic obstructive pulmonary disease: gold executive summary updated 2003. COPD: J Chron Obstruct Pulmon Dis 1(1):105–141. https://doi.org/10.1081/copd-120030163

  4. Fortis S, Comellas A, Make BJ, Hersh CP, Bodduluri S, Georgopoulos D, Kim V, Criner GJ, Dransfield MT, Bhatt SP (2019) Combined forced expiratory volume in 1 second and forced vital capacity bronchodilator response, exacerbations, and mortality in chronic obstructive pulmonary disease. Ann Am Thorac Soc 16(7):826–835

  5. Flesch JD, Dine CJ (2012) Lung volumes: measurement, clinical use, and coding. Chest 142(2):506–510

  6. Fan L, Xia Y, Guan Y, Zhang T-f, Liu S-y (2014) Characteristic features of pulmonary function test, CT volume analysis and MR perfusion imaging in COPD patients with different HRCT phenotypes. Clin Respir J 8(1):45–54

  7. Lynch DA, Austin JH, Hogg JC, Grenier PA, Kauczor H-U, Bankier AA, Barr RG, Colby TV, Galvin JR, Gevenois PA et al (2015) Ct-definable subtypes of chronic obstructive pulmonary disease: a statement of the Fleischner Society. Radiology 277(1):192–205

    Article  PubMed  Google Scholar 

  8. Lynch DA (2014) Progress in imaging COPD, 2004-2014. Chronic Obstr Pulm Dis J COPD Found 1(1):73

  9. Schroeder JD, McKenzie AS, Zach JA, Wilson CG, Curran-Everett D, Stinson DS, Newell Jr JD, Lynch DA (2013) Relationships between airflow obstruction and quantitative CT measurements of emphysema, air trapping, and airways in subjects with and without chronic obstructive pulmonary disease. AJR Am J Roentgenol 201(3):460

  10. Bhatt SP, Washko GR, Hoffman EA, Newell Jr JD, Bodduluri S, Diaz AA, Galban CJ, Silverman EK, San José Estépar R, Lynch DA (2019) Imaging advances in chronic obstructive pulmonary disease. insights from the genetic epidemiology of chronic obstructive pulmonary disease (copdgene) study. Am J Respir Crit Care Med 199(3):286–301

  11. Subramanian DR, Gupta S, Burggraf D, Vom Silberberg SJ, Heimbeck I, Heiss-Neumann MS, Haeussinger K, Newby C, Hargadon B, Raj V, et al (2016) Emphysema-and airway-dominant COPD phenotypes defined by standardised quantitative computed tomography. Eur Respir J 48(1):92–103

  12. McDonough JE, Yuan R, Suzuki M, Seyednejad N, Elliott WM, Sanchez PG, Wright AC, Gefter WB, Litzky L, Coxson HO, et al (2011) Small-airway obstruction and emphysema in chronic obstructive pulmonary disease. N Engl J Med 365(17):1567–1575

  13. Fujimoto K, Kitaguchi Y, Kubo K (2006) Honda T. Clinical analysis of chronic obstructive pulmonary disease phenotypes classified using high-resolution computed tomography. Respirology 11(6):731–740

    Article  PubMed  Google Scholar 

  14. Cho JL, Villacreses R, Nagpal P, Guo J, Pezzulo AA, Thurman AL, Hamzeh NY, Blount RJ, Fortis S, Hoffman EA, et al (2022) Quantitative chest CT assessment of small airways disease in post-acute sars-cov-2 infection. Radiology 304(1):185–192

  15. Wu F, Chen L, Huang J, Fan W, Yang J, Zhang X, Jin Y, Yang F (2021) Zheng C. Total lung and lobar quantitative assessment based on paired inspiratory-expiratory chest CT in healthy adults: correlation with pulmonary ventilatory function. Diagnostics 11(10):1791

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  16. Galbán CJ, Han MK, Boes JL, Chughtai KA, Meyer CR, Johnson TD, Galbán S, Rehemtulla A, Kazerooni EA, Martinez FJ et al (2012) Computed tomography-based biomarker provides unique signature for diagnosis of COPD phenotypes and disease progression. Nat Med 18(11):1711–1715

    Article  PubMed  PubMed Central  Google Scholar 

  17. Konietzke P, Wielpütz MO, Wagner WL, Wuennemann F, Kauczor H-U, Heussel CP, Eichinger M, Eberhardt R, Gompelmann D (2020) Weinheimer O. Quantitative CT detects progression in COPD patients with severe emphysema in a 3-month interval. Eur Radiol 30:2502–2512

    Article  PubMed  Google Scholar 

  18. Ho TT, Kim T, Kim WJ, Lee CH, Chae KJ, Bak SH, Kwon SO, Jin GY, Park E-K (2021) Choi S. A 3D-CNN model with CT-based parametric response mapping for classifying COPD subjects. Sci Rep 11(1):1–12

    Article  Google Scholar 

  19. Lambin P, Rios-Velazquez E, Leijenaar R, Carvalho S, Van Stiphout R.G, Granton P, Zegers CM, Gillies R, Boellard R, Dekker A, et al (2012) Radiomics: extracting more information from medical images using advanced feature analysis. Eur J Cancer 48(4):441–446

  20. Yun J, Cho YH, Lee SM, Hwang J, Lee JS, Oh Y-M, Lee S-D, Loh L-C, Ong C-K, Seo JB, et al (2021) Deep radiomics-based survival prediction in patients with chronic obstructive pulmonary disease. Sci Rep 11(1):15144

  21. Cho YH, Seo JB, Lee SM, Kim N, Yun J, Hwang JE, Lee JS, Oh Y-M, Do Lee S, Loh L-C, et al (2021) Radiomics approach for survival prediction in chronic obstructive pulmonary disease. Eur Radiol 31:7316–7324

  22. Liang C, Xu J, Wang F, Chen H, Tang J, Chen D, Li Q, Jian W, Tang G, Zheng J, et al (2021) Development of a radiomics model for predicting COPD exacerbations based on complementary visual information. In: TP41. TP041 diagnosis and risk assessment in COPD, pp 2296–2296. American Thoracic Society

  23. Yang Y, Li W, Guo Y, Liu Y, Li Q, Yang K, Wang S, Zeng N, Duan W, Chen Z, et al (2022) Early COPD risk decision for adults aged from 40 to 79 years based on lung radiomics features. Frontiers in Medicine 9

  24. Yang Y, Li W, Guo Y, Zeng N, Wang S, Chen Z, Liu Y, Chen H, Duan W, Li X, et al (2022) Lung radiomics features for characterizing and classifying COPD stage based on feature combination strategy and multi-layer perceptron classifier. Math Biosci Eng 19(8):7826–7855

  25. Li Z, Liu L, Zhang Z, Yang X, Li X, Gao Y (2022) Huang K. A novel CT-based radiomics features analysis for identification and severity staging of COPD. Acad Radiol 29(5):663–673

    Article  PubMed  Google Scholar 

  26. Chen S, Ma K, Zheng Y (1904) Transfer learning for 3D medical image analysis. arXiv preprint arXiv

  27. Anwar SM, Majid M, Qayyum A, Awais M, Alnowami M, Khan MK (2018) Medical image analysis using convolutional neural networks: a review. J Med Syst 42:1–13

    Article  Google Scholar 

  28. Tajbakhsh N, Jeyaseelan L, Li Q, Chiang JN, Wu Z (2020) Ding X. Embracing imperfect datasets: a review of deep learning solutions for medical image segmentation. Med Image Anal 63:101693

    Article  PubMed  Google Scholar 

  29. Zhou J, Cui G, Hu S, Zhang Z, Yang C, Liu Z, Wang L, Li C (2020) Sun M. Graph neural networks: a review of methods and applications. AI open 1:57–81

    Article  Google Scholar 

  30. Wu Z, Pan S, Chen F, Long G, Zhang C, Philip SY (2020) A comprehensive survey on graph neural networks. IEEE Trans Neural Netw Learn Syst 32(1):4–24

  31. Song X, Mao M (2021) Qian X. Auto-metric graph neural network based on a meta-learning strategy for the diagnosis of Alzheimer’s disease. IEEE J Biomed Health Inform 25(8):3141–3152

    Article  PubMed  Google Scholar 

  32. McCombe N, Bamrah J, Sanchez-Bornot JM, Finn DP, McClean PL, Wong-Lin K, (ADNI) ADNI (2022) Alzheimer’s disease classification using cluster-based labelling for graph neural network on heterogeneous data. Healthc Technol Lett 9(6):102–109

  33. Hofmanninger J, Prayer F, Pan J, Röhrich S, Prosch H (2020) Langs G. Automatic lung segmentation in routine imaging is primarily a data diversity problem, not a methodology problem. Eur Radiol Exp 4(1):1–13

    Article  Google Scholar 

  34. Van Griethuysen JJ, Fedorov A, Parmar C, Hosny A, Aucoin N, Narayan V, Beets-Tan RG, Fillion-Robin J-C, Pieper S, Aerts HJ. Computational radiomics system to decode the radiographic phenotype. Cancer Res 77(21):104–107 (2017)

  35. Yang Y, Li W, Kang Y, Guo Y, Yang K, Li Q, Liu Y, Yang C, Chen R, Chen H et al (2022) A novel lung radiomics feature for characterizing resting heart rate and COPD stage evolution based on radiomics feature combination strategy. Math Biosci Eng 19:4145–4165

    Article  PubMed  Google Scholar 

  36. Yang Y, Chen Z, Li W, Zeng N, Guo Y, Wang S, Duan W, Liu Y, Chen H, Li X, et al (2022) Multi-modal data combination strategy based on chest HRCT images and PFT parameters for intelligent dyspnea identification in COPD. Frontiers in Medicine 9

  37. Qi Y (2012) Random forest for bioinformatics. In: Ensemble machine learning: methods and applications, pp 307–323. Springer

  38. Jakkula V (2006) Tutorial on support vector machine (SVM). School of EECS, Washington State University 37(2.5):3

  39. Wan S, Liang Y, Zhang Y, Guizani M (2018) Deep multi-layer perceptron classifier for behavior analysis to estimate Parkinson’s disease severity using smartphones. IEEE Access 6:36825–36833

    Article  Google Scholar 

  40. LaValley MP (2008) Logistic regression. Circulation 117(18):2395–2399

    Article  PubMed  Google Scholar 

  41. Ayyadevara VK (2018) Gradient boosting machine. Pro machine learning algorithms: a hands-on approach to implementing algorithms in python and R, pp 117–134

  42. Balakrishnama S (1998) Ganapathiraju A. Linear discriminant analysis-a brief tutorial. Inst Signal Inf Process 18(1998):1–8

    Google Scholar 

Download references

Acknowledgements

Thanks to the Department of Radiology, the First Affiliated Hospital of Guangzhou Medical University, for providing the dataset.

Funding

This work was supported by the National Key Research and Development Program of China [grant numbers 2022YFF0710800, 2022YFF0710802]; the National Natural Science Foundation of China [grant number 62071311]; the Stable Support Plan for Colleges and Universities in Shenzhen of China [grant number SZWD2021010]; and the Special Program for Key Fields of Colleges and Universities in Guangdong Province (Biomedicine and Health) of China [grant number 2021ZDZX2008].

Author information

Authors and Affiliations

  1. College of Medicine and Biological Information Engineering, Northeastern University, Shenyang, 110169, China

    Xingguang Deng, Ziran Chen, Xiaoqiang Miao & Yan Kang

  2. College of Health Science and Environmental Engineering, Shenzhen Technology University, Shenzhen, 518118, China

    Xingguang Deng, Wei Li, Shicong Wang, Nanrong Zeng, Haseeb Hassan, Ziran Chen, Yang Liu, Xiaoqiang Miao & Yan Kang

  3. Department of radiology, Shenzhen Lanmage Medical Technology Co., Ltd, No.103, Baguang Service Center, Shenzhen, Guangdong, 518119, People’s Republic of China

    Yingjian Yang & Yan Kang

  4. School of Applied Technology, Shenzhen University, Shenzhen, 518060, China

    Shicong Wang & Nanrong Zeng

  5. The First Affiliated Hospital of Guangzhou Medical University, State Key Laboratory of Respiratory Disease, Nation Clinical Research Center for Respiratory Disease, Guangzhou Institute of Respiratory Health, The National Center for Respiratory Medicine, Guangzhou, 510120, China

    Jiaxuan Xu

  6. School of Electrical and Information Engineering, Northeast Petroleum University, Daqing, 163318, China

    Yingwei Guo

  7. 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 Disease, Shenzhen, 518001, China

    Rongchang Chen

  8. Engineering Research Centre of Medical Imaging and Intelligent Analysis, Ministry of Education, Shenyang, 110169, China

    Yan Kang

Authors
  1. Xingguang Deng
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Wei Li
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Yingjian Yang
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Shicong Wang
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Nanrong Zeng
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Jiaxuan Xu
    View author publications

    You can also search for this author in PubMed Google Scholar

  7. Haseeb Hassan
    View author publications

    You can also search for this author in PubMed Google Scholar

  8. Ziran Chen
    View author publications

    You can also search for this author in PubMed Google Scholar

  9. Yang Liu
    View author publications

    You can also search for this author in PubMed Google Scholar

  10. Xiaoqiang Miao
    View author publications

    You can also search for this author in PubMed Google Scholar

  11. Yingwei Guo
    View author publications

    You can also search for this author in PubMed Google Scholar

  12. Rongchang Chen
    View author publications

    You can also search for this author in PubMed Google Scholar

  13. Yan Kang
    View author publications

    You can also search for this author in PubMed Google Scholar

Contributions

XD: methodolog, software, data analysis. WL: methodology, conceptualization. YY: methodology. SW: data analysis. NZ: data analysis. JX: medical guidance. HH: language polishing. ZC: data analysis. XM: investigation. YG: investigation. RC: conceptualization. YK: conceptualization.

Corresponding authors

Correspondence to Rongchang Chen or Yan Kang.

Ethics declarations

Conflict of interest

The authors declare no competing interests.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Deng, X., Li, W., Yang, Y. et al. COPD stage detection: leveraging the auto-metric graph neural network with inspiratory and expiratory chest CT images. Med Biol Eng Comput (2024). https://doi.org/10.1007/s11517-024-03016-z

Download citation

  • Received:

  • Accepted:

  • Published:

  • DOI: https://doi.org/10.1007/s11517-024-03016-z

Keywords

Search

Navigation