Advertisement

Convolutional Neural Network Based COPD and Emphysema Classifications Are Predictive of Lung Cancer Diagnosis

  • Charles HattEmail author
  • Craig Galban
  • Wassim Labaki
  • Ella Kazerooni
  • David Lynch
  • Meilan Han
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11040)

Abstract

Lung cancer is a leading cause of mortality and morbidity for patients suffering from Chronic Obstructive Pulmonary Disease (COPD). Both the presence of visually assessed emphysema on CT scans and abnormal pulmonary function tests are associated with the development of lung cancer. Based on recent results showing that convolutional neural networks (CNNs) applied to CT scans can predict spirometrically-defined COPD (\(\frac{FEV_{1}}{FVC}<0.7\)), we hypothesized that CNN-based classification of COPD and emphysema is predictive of lung cancer development in the National Lung Cancer Screening (NLST) cohort. We trained spirometric COPD and visual emphysema CNN classifiers using data from the COPDGene study. The classifiers were then used to generate COPD and emphysema scores (\(CS_{CNN}\) and \(ES_{CNN}\), respectively) on 7347 CT scans from the NLST study. Cox proportional hazards regression was used to model the effects of \(CS_{CNN}\), \(ES_{CNN}\), age, body mass index, education, gender, smoking pack-years, and years since smoking cessation on lung cancer diagnosis. It was found that, individually, both \(CS_{CNN}\) and \(ES_{CNN}\) were statistically significant predictors (p < 0.000 and p < 0.000, respectively) of lung cancer diagnosis hazard.

Keywords

CNN COPD Lung cancer screening Survival analysis 

Notes

Acknowledgements

The authors thank the National Cancer Institute for access to NCI’s data collected by the National Lung Screening Trial. The statements contained herein are solely those of the authors and do not represent or imply concurrence or endorsement by NCI. This work was supported by NIH grant 2R44CA203050-02. The COPDGene study is supported by NIH Grant Numbers R01 HL089897 and R01 HL089856, and is also supported by the COPD Foundation through contributions made to an Industry Advisory Board comprised of AstraZeneca, Boehringer Ingelheim, Novartis, Pfizer, Siemens, Sunovion and GlaxoSmithKline.

References

  1. 1.
    Cruz, A.A.: Global surveillance, prevention and control of chronic respiratory diseases: a comprehensive approach. World Health Organization (2007)Google Scholar
  2. 2.
    Young, R.P., et al.: Airflow limitation and histology shift in the national lung screening trial. The NLST-ACRIN cohort substudy. Am. J. Respir. Criti. Care Med. 192(9), 1060–1067 (2015)CrossRefGoogle Scholar
  3. 3.
    Smith, B.M., Pinto, L., Ezer, N., Sverzellati, N., Muro, S., Schwartzman, K.: Emphysema detected on computed tomography and risk of lung cancer: a systematic review and meta-analysis. Lung Cancer 77(1), 58–63 (2012)CrossRefGoogle Scholar
  4. 4.
    National Lung Screening Trial Research Team: Reduced lung-cancer mortality with low-dose computed tomographic screening. New Engl. J. Med. 365(5), 395–409 (2011)Google Scholar
  5. 5.
    McClure, J.B.: Are biomarkers a useful aid in smoking cessation? A review and analysis of the literature. Behav. Med. 27(1), 37–47 (2001)CrossRefGoogle Scholar
  6. 6.
    Bankier, A.A., De Maertelaer, V., Keyzer, C., Gevenois, P.A.: Pulmonary emphysema: subjective visual grading versus objective quantification with macroscopic morphometry and thin-section CT densitometry. Radiology 211(3), 851–858 (1999)CrossRefGoogle Scholar
  7. 7.
    González, G., et al.: Disease staging and prognosis in smokers using deep learning in chest computed tomography. Am. J. Respir. Crit. Care Med. 197(2), 193–203 (2018)CrossRefGoogle Scholar
  8. 8.
    Regan, E.A., et al.: Genetic epidemiology of COPD (COPDGene) study design. COPD J. Chronic Obstr. Pulm. Dis. 7(1), 32–43 (2011)CrossRefGoogle Scholar
  9. 9.
    Gierada, D.S., et al.: Quantitative CT assessment of emphysema and airways in relation to lung cancer risk. Radiology 261(3), 950–959 (2011)CrossRefGoogle Scholar
  10. 10.
    Wilson, D.O., et al.: Association of radiographic emphysema and airflow obstruction with lung cancer. Am. J. Respir. Crit. Care Med. 178(7), 738–744 (2008)CrossRefGoogle Scholar
  11. 11.
    Maldonado, F., Bartholmai, B.J., Swensen, S.J., Midthun, D.E., Decker, P.A., Jett, J.R.: Are airflow obstruction and radiographic evidence of emphysema risk factors for lung cancer?: a nested case-control study using quantitative emphysema analysis. Chest 138(6), 1295–1302 (2010)CrossRefGoogle Scholar

Copyright information

© Springer Nature Switzerland AG 2018

Authors and Affiliations

  • Charles Hatt
    • 1
    • 2
    Email author
  • Craig Galban
    • 2
  • Wassim Labaki
    • 3
  • Ella Kazerooni
    • 2
    • 3
  • David Lynch
    • 4
  • Meilan Han
    • 3
  1. 1.Imbio LLCAnn ArborUSA
  2. 2.Department of RadiologyUniversity of MichiganAnn ArborUSA
  3. 3.Department of Internal Medicine, Division of Pulmonary and Critical CareUniversity of MichiganAnn ArborUSA
  4. 4.Department of Medicine, Division of RadiologyNational Jewish HealthDenverUSA

Personalised recommendations