Automatic segmentation and analysis of the main pulmonary artery on standard post-contrast CT studies using iterative erosion and dilation

Original Article

Abstract

Purpose

To describe an algorithm for the accurate segmentation of the main pulmonary artery (MPA) and determining its length, mid-cross-sectional area and mid-circumferential perimeter. This will help with accurate, rapid and reproducible MPA measurements which can be used to detect diseases that cause raised pulmonary arterial pressure, and allow standardized serial measurements to assess progression or response to treatment.

Method

We perform MPA segmentation using a novel approach based on erosion and dilation. A centerline is then determined by skeletonization, graph construction and spline fitting. MPA cross sections perpendicular to the centerline are analyzed in order to determine MPA length, and mid-cross-sectional area and perimeter. The technique was developed using four normal chest CT data sets and then tested on twenty normal post-contrast chest CT studies. Results are compared to manual segmentation and measurement by a thoracic radiologist.

Results

The mean MPA length, mid-cross-sectional area and mid-circumferential perimeter of the twenty test data sets, calculated by our algorithm, are 43.6 \(\pm \) 9.2 mm, 552.9 \(\pm \) 132.4\(\hbox { mm}^{2}\) and \(86.0 \pm 10.5\hbox { mm}\), respectively, compared with \(41.3 \pm 5.9\hbox { mm}, 574.1 \pm 124.2\hbox { mm}^{2}\) and \(99.7 \pm 12.1\hbox { mm}\) obtained manually by the radiologist. Our technique shows high correlation with the manually determined parameters for both mid- cross-sectional area (\(R = 0.96\)) and length (\(R = 0.93\)), and good correlation for mid-circumferential perimeter (\(R = 0.87\)).

Conclusion

Our algorithm is a robust accurate automated method for obtaining measurements of the MPA. This allows a more standardized method for determining length, and mid- cross-sectional area/perimeter and therefore allows more accurate comparison of MPA measurements.

Keywords

Pulmonary artery Segmentation Measurement Computed tomography 

Notes

Acknowledgments

We would like to thank the Prince of Wales Hospital Radiology Department for providing the anonymized CT data.

Compliance with ethical standards

Conflict of interest

Daniel Moses, Tatjana Zrimec, and Claude Sammut declare that they have no conflict of interest.

References

  1. 1.
    Pawade T, Holloway B, Bradlow W, Steeds RP (2014) Noninvasive imaging for the diagnosis and prognosis of pulmonary hypertension. Expert Rev Cardiovasc Ther 12(1):71–86. doi: 10.1586/14779072.2014.867806 CrossRefPubMedGoogle Scholar
  2. 2.
    Shen Y, Wan C, Tian P, Wu Y, Li X, Yang T, An J, Wang T, Chen L, Wen F (2014) CT-base pulmonary artery measurement in the detection of pulmonary hypertension: a meta-analysis and systematic review. Medicine (Baltimore) 93(27):e256. doi: 10.1097/md.0000000000000256 CrossRefGoogle Scholar
  3. 3.
    Edwards PD, Bull RK, Coulden R (1998) CT measurement of main pulmonary artery diameter. Br J Radiol 71(850):1018–1020. doi: 10.1259/bjr.71.850.10211060 CrossRefPubMedGoogle Scholar
  4. 4.
    Raymond TE, Khabbaza JE, Yadav R, Tonelli AR (2014) Significance of main pulmonary artery dilation on imaging studies. Ann Am Thorac Soc 11(10):1623–1632. doi: 10.1513/AnnalsATS.201406-253PP PubMedCentralCrossRefPubMedGoogle Scholar
  5. 5.
    McLaughlin VV, Gaine SP, Howard LS, Leuchte HH, Mathier MA, Mehta S, Palazzini M, Park MH, Tapson VF, Sitbon O (2013) Treatment goals of pulmonary hypertension. J Am Coll Cardiol 62(25 Suppl):D73–D81. doi: 10.1016/j.jacc.2013.10.034 CrossRefPubMedGoogle Scholar
  6. 6.
    Corson N, Armato SG 3rd, Labby ZE, Straus C, Starkey A, Gomberg-Maitland M (2014) CT-based pulmonary artery measurements for the assessment of pulmonary hypertension. Acad Radiol 21(4):523–530. doi: 10.1016/j.acra.2013.12.015 PubMedCentralCrossRefPubMedGoogle Scholar
  7. 7.
    Park CY, Yoo SM, Rho JY, Ji YG, Lee HY (2012) The ratio of descending aortic enhancement to main pulmonary artery enhancement measured on pulmonary CT angiography as a finding to predict poor outcome in patients with massive or submassive pulmonary embolism. Tuberc Respir Dis (Seoul) 72(4):352–359. doi: 10.4046/trd.2012.72.4.352 CrossRefGoogle Scholar
  8. 8.
    Matsushita S, Matsuoka S, Yamashiro T, Fujikawa A, Yagihashi K, Kurihara Y, Nakajima Y (2014) Pulmonary arterial enlargement in patients with acute exacerbation of interstitial pneumonia. Clin Imaging 38(4):454–457. doi: 10.1016/j.clinimag.2014.02.004 CrossRefPubMedGoogle Scholar
  9. 9.
    Sheikhzadeh S, De Backer J, Gorgan N, Rybczynski M, Hillebrand M, Schuler H, Bernhardt AM, Koschyk D, Bannas P, Keyser B, Mortensen K, Radke RM, Mir TS, Kolbel T, Robinson PN, Schmidtke J, Berger J, Blankenberg S, von Kodolitsch Y (2014) The main pulmonary artery in adults: a controlled multicenter study with assessment of echocardiographic reference values, and the frequency of dilatation and aneurysm in Marfan syndrome. Orphanet J Rare Dis 9(1):203. doi: 10.1186/s13023-014-0203-8 PubMedCentralCrossRefPubMedGoogle Scholar
  10. 10.
    Kawano Y, Tamura A, Watanabe T, Kadota J (2013) Severe obstructive sleep apnoea is independently associated with pulmonary artery dilatation. Respirology 18(7):1148–1151. doi: 10.1111/resp.12123 PubMedGoogle Scholar
  11. 11.
    Linguraru MG, Pura JA, Gladwin MT, Koroulakis AI, Minniti C, Machado RF, Kato GJ, Wood BJ (2014) Computed tomography correlates with cardiopulmonary hemodynamics in pulmonary hypertension in adults with sickle cell disease. Pulm Circ 4(2):319–329. doi: 10.1086/675997 PubMedCentralCrossRefPubMedGoogle Scholar
  12. 12.
    Gupta V, Tonelli AR, Krasuski RA (2012) Congenital heart disease and pulmonary hypertension. Heart Fail Clin 8(3):427–445. doi: 10.1016/j.hfc.2012.04.002 CrossRefPubMedGoogle Scholar
  13. 13.
    Morjaria S, Grinnan D, Voelkel N (2012) Massive dilatation of the pulmonary artery in association with pulmonic stenosis and pulmonary hypertension. Pulm Circ 2(2):256–257. doi: 10.4103/2045-8932.97640 PubMedCentralCrossRefPubMedGoogle Scholar
  14. 14.
    Linguraru MG, Mukherjee N, Van Uitert RL, Summers RM, Gladwin MT, Machado RF, Wood BJ (2008) Pulmonary artery segmentation and quantification in sickle cell associated pulmonary hypertension. In: Medical imaging 2008: physiology, function, and structure from medical images, 17 Feb. 2008, USA. Proceedings of SPIE—international society optical engineering (USA). SPIE—The International Society for Optical Engineering, pp 691611–691612. doi: 10.1117/12.770485
  15. 15.
    Linguraru MG, Pura JA, Van Uitert RL, Mukherjee N, Summers RM, Minniti C, Gladwin MT, Kato G, MacHado RF, Wood BJ (2010) Segmentation and quantification of pulmonary artery for noninvasive CT assessment of sickle cell secondary pulmonary hypertension. Med Phys 37(4):1522–1532. doi: 10.1118/1.3355892 PubMedCentralCrossRefPubMedGoogle Scholar
  16. 16.
    Zhang J, He Z, Huang X (2011) Automatic 3D anatomy-based mediastinum segmentation method in CT images. Int J Digit Content Technol Appl 5(7):266–274CrossRefGoogle Scholar
  17. 17.
    Feuerstein M, Kitasaka T, Mori K (2010) Adaptive model based pulmonary artery segmentation in 3D chest CT. In: Medical imaging 2010: image processing, february 14, 2010–february 16, 2010, San Diego, CA, USA. Progress in biomedical optics and imaging—proceedings of SPIE. SPIE, The Society of Photo-Optical Instrumentation Engineers (SPIE); Medtronic, Inc.; Aeroflex, Inc.; Hamamatsu Photonics K.K.; OpenXi; Tungsten Heavy Powder, Inc. doi: 10.1117/12.843750
  18. 18.
    Ebrahimdoost Y, Qanadli SD, Nikravanshalmani A, Ellis TJ, Falah Shojaee Z, Dehmeshki J Automatic segmentation of pulmonary artery (PA) in 3D pulmonary CTA images. In: 17th international conference on digital signal processing, DSP 2011, July 6, 2011–July 8, 2011, Corfu, Greece, 2011. 17th DSP 2011 international conference on digital signal processing, proceedings. IEEE Computer Society. doi: 10.1109/icdsp.2011.6004964
  19. 19.
    Ebrahimdoost Y, Qanadli SD, Nikravanshalmani A, Ellis TJ, Shojaee ZF, Dehmeshki J (2011) Automatic segmentation of pulmonary artery (PA) using customized level set method in 3D (CTA) images. In: 2011 international conference on image processing, computer vision, and pattern recognition, IPCV 2011, July 18, 2011–July 21, Las Vegas, NV, USA, 2011. Proceedings of the 2011 international conference on image processing, computer vision, and pattern recognition, IPCV 2011. CSREA Press, pp 288–292Google Scholar
  20. 20.
    Saremi F, Gera A, Ho SY, Hijazi ZM, Sanchez-Quintana D (2014) CT and MR imaging of the pulmonary valve. Radiographics 34(1):51–71. doi: 10.1148/rg.341135026 CrossRefPubMedGoogle Scholar
  21. 21.
    Moses DA, Dawes L, Sammut C, Zimrec T (2015) Main pulmonary artery detection from CT data using machine learning. In: Press CARS 2015 proceedingsGoogle Scholar
  22. 22.
    Zrimec T, Mander T, Lambert T, Parker G (1995) 3D visualization of the human cerebral vasculature. In: Medical imaging 1995: image display, February 26, 1995–February 28, 1995, San Diego, CA, USA. Proceedings of SPIE—the international society for optical engineering. Society of Photo-Optical Instrumentation Engineers, pp 86–96Google Scholar
  23. 23.
    Truong QA, Massaro JM, Rogers IS, Mahabadi AA, Kriegel MF, Fox CS, O’Donnell CJ, Hoffmann U (2012) Reference values for normal pulmonary artery dimensions by noncontrast cardiac computed tomography: the Framingham Heart Study. Circ Cardiovasc Imaging 5(1):147–154. doi: 10.1161/circimaging.111.968610 PubMedCentralCrossRefPubMedGoogle Scholar
  24. 24.
    Ussavarungsi K, Whitlock J, Lundy T, Carabenciov I, Burger C, Lee A (2014) The Significance of Pulmonary Artery Size in Pulmonary Hypertension. Diseases 2(3):243–259Google Scholar
  25. 25.
    Kuriyama K, Gamsu G, Stern RG, Cann CE, Herfkens RJ, Brundage BH (1984) CT-determined pulmonary artery diameters in predicting pulmonary hypertension. Invest Radiol 19(1):16–22Google Scholar
  26. 26.
    Ebrahimdoost Y, Dehmeshki J, Ellis TS, Firoozbakht M, Youannic A, Qanadli SD (2010) Medical image segmentation using active contours and a level set model: application to pulmonary embolism (PE) segmentation. In: 2010 fourth international conference on the digital society (ICDS 2010), 10–16 Feb. 2010, Los Alamitos, CA, USA. 2010 fourth international conference on the digital society (ICDS 2010). IEEE Computer Society, pp 269–273. doi: 10.1109/icds.2010.64

Copyright information

© CARS 2015

Authors and Affiliations

  1. 1.School of Computer Science and EngineeringUniversity of New South WalesSydneyAustralia
  2. 2.Department of RadiologyPrince of Wales HospitalSydneyAustralia
  3. 3.Faculty of Mathematics, Natural Sciences and Information TechnologiesUniversity of PrimorskaKoperSlovenia

Personalised recommendations