Skip to main content

Advertisement

SpringerLink
Log in

Automatic 3D modelling of human diaphragm from lung MDCT images

  • Original Article
  • Published:
International Journal of Computer Assisted Radiology and Surgery Aims and scope Submit manuscript

Abstract

Purpose

The thoracic diaphragm separates the thorax and abdomen cavity and also performs an important function in respiration. An automatic algorithm to model the human full diaphragm from multi-detector computed tomography (MDCT) images has been developed and tested.

Method

The modelling algorithm comprises these steps: (i) diaphragm top boundary estimation (ii) diaphragm side boundary estimation and (iii) full diaphragm modelling in 3D. Diaphragm top boundary is estimated based on lungs’ diaphragmatic surfaces with three different methods including: linear interpolation and fitting fourth and fifth degree polynomial surfaces. Diaphragm side boundary is assumed as the inner surfaces of the lower ribs, spinal column and costal cartilages, estimated via interpolation. As the last step, the full diaphragm is modelled by employing 3D active contours that are initiated from a predefined mesh and expand towards the estimated boundaries of the diaphragm. The proposed algorithm was tested on MDCT datasets from 15 patients, and the result were compared to reference masks provided by an experienced radiologist.

Results

Based on quantitative evaluations, the accuracy of the algorithm highly depends on the diaphragm top surface estimation, e.g., the proposed algorithm failed on two datasets, both with enlarged pericardial fat pad that cuts off the left lung from the diaphragm. The proposed algorithm was tested on the remaining 13 datasets in which lungs’ lower surfaces have normal contact with the diaphragm. To perform quantitative evaluations, four slices per dataset including an axial, mid-coronal and one-fourth of the sagittal planes from left and right, were compared to the ground truth. Hausdorff distance and mean distance to the closest point were measured to be 11.61 and 3.46 mm respectively, when the diaphragm top surface is modelled by a fourth degree polynomial surface.

Conclusion

Human full diaphragm can be automatically modelled with 3D active contours bounded by the lower surfaces of the lungs and inner surfaces of the lower ribs, spinal column and costal cartilages.

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

References

  1. Diaphragm @ONLINE (2013). http://www.healthcentral.com/acid-reflux/19072-146.html

  2. Sharif Al S, Deriche M, Maalej N, El Ferik S (2014) A fast geodesic active contour model for medical image segmentation using prior analysis and wavelets. Arab J Sci Eng 39(2):1017–1037. doi:10.1007/s13369-013-0664-4

    Article  Google Scholar 

  3. Behr M, Thollon L, Arnoux P, Serre T, Berdah S, Baque P, Brunet C (2006) 3d reconstruction of the diaphragm for virtual traumatology. Surg Radiol Anat 28(3):235–240

    Article  PubMed  Google Scholar 

  4. Beichel R, Bischof H, Leberl F, Sonka M (2005) Robust active appearance models and their application to medical image analysis. Med Imaging IEEE Trans 24(9):1151–1169

    Article  Google Scholar 

  5. Beichel R, Gotschuli G, Sorantin E, Leberl F, Sonka M (2002) Diaphragm dome surface segmentation in ct data sets: a 3d active appearance model approach. In: SPIE proceedings of the medical imaging 2002 (4684):475–484

  6. Beichel R, Mitchell S, Sorantin E, Leberl F, Goshtasby A, Sonka M (2001) Shape and appearance based segmentation of volumetric medical images. In: Proceedings 2001 international conference on image processing, vol 2, pp 589–592

  7. Boykov Y, Funka-Lea G (2006) Graph cuts and efficient n-d image segmentation. Int J Comput Vis 70(2):109–131

    Article  Google Scholar 

  8. Caselles V, Catt F, Coll T, Dibos F (1993) A geometric model for active contours in image processing. Numer Math 66:1–31

    Article  Google Scholar 

  9. Caselles V, Kimmel R, Sapiro G (1995) Geodesic active contours. In: Proceedings of fifth international conference on computer vision, pp 694 –699

  10. Chen M, Bai J, Siochi R (2013) A new method of diaphragm apex motion detection from 2d projection images of mega-voltage cone beam ct. Phys Med Biol 58(3):715–733

    Article  PubMed  Google Scholar 

  11. Gray H, Warren Harmin L (2000) Anatomy of the human body, 20th edn. Lea and Febiger, Bartleby, Philadelphia

  12. Huttenlocher D, Klanderman G, Rucklidge W (1993) Comparing images using the hausdorff distance. Pattern Anal Mach Intell IEEE Trans 15(9):850–863

    Article  Google Scholar 

  13. Huttenlocher DP, Kedem K (1990) Computing the minimum hausdorff distance for point sets under translation. In: Proceedings of the sixth annual symposium on computational geometry, SCG ’90ACM, New York, NY, USA, pp 340–349

  14. Kang L, Xiaodong W, Chen D, Sonka M (2006) Optimal surface segmentation in volumetric images-a graph-theoretic approach. Pattern Anal Mach Intell IEEE Trans 28(1):119–134

    Article  Google Scholar 

  15. Kass M, Witkin A, Terzopoulos D (1988) Snakes: active contour models. Int J Comput Vis 1:321–331

    Article  Google Scholar 

  16. Ladjal H, Saade J, Beuve M, Azencot J, Moreau JM, Shariat B (2013) 3d biomechanical modeling of the human diaphragm based on ct scan images. In: Long M (ed) World congress on medical physics and biomedical engineering May 26–31, 2012, Beijing, China, IFMBE Proceedings, vol 39. Springer, Berlin Heidelberg, pp 2188–2191

  17. Li X, Wang X, Dai Y ((2014)) Robust global minimization of active contour model for multi-object medical image segmentation. In: Instrumentation and measurement technology conference (I2MTC) proceedings, 2014 IEEE international, pp 1443–1448 . doi:10.1109/I2MTC.2014.6860984

  18. Lrig C, Kobbelt L, Ertl T (2000) Hierarchical solutions for the deformable surface problem in visualization. Graph Models 62:1–18

    Article  Google Scholar 

  19. Martin S, Dey J, King M, Hutton B (2007) Segmenting and tracking diaphragm and heart regions in gated-ct datasets as an aid to developing a predictive model for respiratory motion-correction. In: Nuclear science symposium conference record, 2007. NSS ’07. IEEE, vol 4, pp 2680–2685

  20. McClelland J, Hawkes D, Schaeffter T, King A (2013) Respiratory motion models: a review. Med Image Anal 17(1):19–42

    Article  CAS  PubMed  Google Scholar 

  21. McQuaid S, Lambrou T, Cunningham V, Bettinardi V, Gilardi MC, Hutton B (2009) The application of a statistical shape model to diaphragm tracking in respiratory-gated cardiac pet images. In: Proceedings of the IEEE 97(12):2039–2052

  22. McQuaid S, Lambrou T, Hutton B (2011) A novel method for incorporating respiratory-matched attenuation correction in the motion correction of cardiac petct studies. Phys Med Biol 56(10):2039–2052

    Article  Google Scholar 

  23. Pato M, Santos N, Areias P, Pires E, de Carvalho M, Pinto S, Lopes D (2011) Finite element studies of the mechanical behaviour of the diaphragm in normal and pathological cases. Comput Methods Biomech Biomed Eng 14(6):505–513

    Article  CAS  Google Scholar 

  24. Pazokifard B, Sowmya A. (2013) 3-d segmentation of human sternum in lung mdct images. In: Engineering in medicine and biology society (EMBC), 2013 35th annual international conference of the IEEE, pp 3351–3354. doi:10.1109/EMBC.2013.6610259

  25. Pazokifard B, Sowmya A (2013) Efficient graph cuts based extraction of vertebral column and ribs in lung mdct images. In: 2013 20th IEEE international conference on image processing (ICIP), pp 1182–1186. doi:10.1109/ICIP.2013.6738244

  26. Pazokifard B, Sowmya A (2013) Lung segmentation with graph cuts: graph size versus performance. In: AIP conference proceedings 1559(1):315–322

  27. Pazokifard B, Sowmya A, Moses D (2014) Automatic patient-customised 3d reconstruction of human costal cartilage from lung mdct dataset. Int J Comput Assist Radiol Surg pp 1–8. doi:10.1007/s11548-014-1086-9

  28. Petkov S, Carrillo X, Radeva P, Gatta C (2014) Diaphragm border detection in coronary x-ray angiographies: new method and applications. Comput Med Imaging Graph 38(4):296–305

    Article  PubMed  Google Scholar 

  29. Rangayyan R, Banik S, Boag G (2009) Landmarking and segmentation of computed tomographic images of pediatric patients with neuroblastoma. Int J Comput Assist Radiol Surg 4(3):245–262

    Article  PubMed  Google Scholar 

  30. Rangayyan R, Vu R, Boag G (2008) Automatic delineation of the diaphragm in computed tomographic images. J Digit Imaging 21(1):134–147

    Article  PubMed Central  Google Scholar 

  31. Shuai Z, Yanjun P (2012) 3d medical image segmentation based on active contour model. In: 2012 5th international conference on biomedical engineering and informatics (BMEI), pp 98–102 . doi:10.1109/BMEI.2012.6512895

  32. Terzopoulos D, Witkin A, Kass M (1987) Symmetry-seeking models and 3d object reconstruction. Int J Comput Vis 1:211–221

    Article  Google Scholar 

  33. Vedam SS, Kini VR, Keall PJ, Ramakrishnan V, Mostafavi H, Mohan R (2003) Quantifying the predictability of diaphragm motion during respiration with a noninvasive external marker. Med Phys 30(4):505–513

    Article  CAS  PubMed  Google Scholar 

  34. Vidal F, Villard PF, Lutton E (2012) Tuning of patient-specific deformable models using an adaptive evolutionary optimization strategy. Biomed Eng IEEE Trans 59(10):2942–2949

    Article  Google Scholar 

  35. Villard P, Bourne W, Bello F (2008) Modelling organ deformation using mass-springs and tensional integrity. In: Bello F, Edwards P (eds) Biomedical Simulation. (Lecture Notes in computer science), Springer, Berlin, vol 5104, pp 221–226

  36. Vostatek P, Novak D, Rychnovskyy T, Wild J (2010) Diaphragm postural function analysis using magnetic resonance. In: 2010 10th IEEE international conference on information technology and applications in biomedicine (ITAB), pp 1–4 (2010)

  37. Wang X, Wang Q, Hao Z, Xu K, Guo P, Ren H, Jang W, Kim Jb (2014) Real-time 3d medical structure segmentation using fast evolving active contours. doi:10.1117/12.2042974

  38. Yalamanchili R, Chittajallu D, Balanca P, Tamarappoo B, Berman D, Dey D, Kakadiaris I (2010) Automatic segmentation of the diaphragm in non-contrast ct images. In: 2010 IEEE international symposium on biomedical imaging: from nano to macro, pp 900–903

  39. Zhou X, Ninomiya H, Hara T, Fujita H, Yokoyama R, Chen H, Kiryu T, Hoshi H (2008) Automated estimation of the upper surface of the diaphragm in 3-d ct images. Biomed Eng IEEE Trans 55(1):351–353

    Article  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. School of Computer Science and Engineering, University of New South Wales, Sydney, NSW, 2052, Australia

    Banafsheh Pazokifard & Arcot Sowmya

  2. Department of Medical Imaging, Prince of Wales Clinical School, University of New South Wales, Sydney, NSW, 2052, Australia

    Daniel Moses

Authors
  1. Banafsheh Pazokifard
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Arcot Sowmya
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Daniel Moses
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Banafsheh Pazokifard.

Ethics declarations

Conflict of interest

Banafsheh Pazokifard, Arcot Sowmya, and Daniel Moses declare that they have no conflict of interest.

Appendices

Appendix 1

Followings are pseudocode for merging and unifying the diaphragm top and side boundaries:

figure a

Appendix 2

Followings are pseudocode for removing diaphragmatic irrelevant voxels from unified diaphragm top and side boundaries:

figure b

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Pazokifard, B., Sowmya, A. & Moses, D. Automatic 3D modelling of human diaphragm from lung MDCT images. Int J CARS 11, 767–776 (2016). https://doi.org/10.1007/s11548-015-1298-7

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11548-015-1298-7

Keywords

Search

Navigation