Skip to main content

Advertisement

SpringerLink
Log in

Vascular decomposition using weighted approximate convex decomposition

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

Abstract

Objective

Stroke treatment often requires analysis of vascular pathology evaluated using computed tomography (CT) angiography. Due to vascular variability and complexity, finding precise relationships between vessel geometries and arterial pathology is difficult. A new convex shape decomposition strategy was developed to understand complex vascular structures and synthesize a weighted approximate convex decomposition (WACD) method for vascular decomposition in computer-aided diagnosis.

Materials and methods

The vascular tree is decomposed into optimal number of components (determined by an expert). The decomposition is based on two primary features of vascular structures: (i) the branching factor that allows structural decomposition and (ii) the concavity over the vessel surface seen primarily at the site of an aneurysm. Such surfaces are decomposed into subcomponents. Vascular sections are reconstructed using CT angiograms. Next the dual graph is constructed, and edge weights for the graph are computed from shape indices. Graph vertices are iteratively clustered by a mesh decimation operator, while minimizing a cost function related to concavity.

Results

The method was validated by first comparing results with an approximate convex decomposition (ACD) method and next on vessel sections (n = 177) whose number of clusters (ground truth) was predetermined by an expert. In both cases, WACD produced promising results with 84.7 % of the vessel sections correctly clustered and when compared with ACD produced a more effective decomposition. Next, the algorithm was validated in a longitudinal study data of 4 subjects where volumetric and surface area comparisons were made between expert segmented sections and WACD decomposed sections that contained aneurysms. The results showed a mean error rate of 7.8 % for volumetric comparisons and 10.4 % for surface area comparisons.

Conclusion

Decomposition of the cerebral vasculature from CT angiograms into a geometrically optimal set of convex regions may be useful for computer-assisted diagnosis. A new WACD method capable of decomposing complex vessel structures, including bifurcations and aneurysms, was developed and tested with promising results.

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.

Similar content being viewed by others

References

  1. AHA Statistical Update (2012) Heart disease and stroke statistics-2012 update. A Report From the American Heart Association

  2. Welter P, Hocken C, Deserno T, Grouls C, Gunther R (2010) Workflow management of content-based image retrieval for CAD support in PACS environments based on IHE. Int J Comput Assist Radiol Surgery 5(4): 393–400

    Article  Google Scholar 

  3. Radaelli AG, Peiró J (2010) On the segmentation of vascular geometries from medical images. Int J Numer Methods Biomed Eng 26(1): 3–34

    Article  Google Scholar 

  4. Tizon X (2004) Algorithms for the analysis of 3D magnetic resonance angiography images. Acta Universitatis Agriculturae Sueciae, Uppsala, ISBN 91-576-670-4

  5. Thompson P (2004) Mapping cortical change in alzheimer’s disease, brain development and schizophrenia. Neuroimage 23(Suppl 1): S2–S18

    Article  PubMed  Google Scholar 

  6. Christian SW, Lorenzo P (2007) Comparative morphology of the hemolymph vascular system in scorpions-A survey using corrosion casting, MicroCT and 3D reconstruction. J Morphol 268(5): 401–413

    Article  Google Scholar 

  7. Camarlinghi N, Gori I, Retico A, Bellotti R, Bosco P, Cerello P, Gargano G, Lopez Torres E, Megna R, Peccarisi M, Fantacci ME (2012) Combination of computer-aided detection algorithms for automatic lung nodule identification. Int J Comput Assist Radiol Surg 7(3):455–464

    Google Scholar 

  8. Francesco C, Roberto F, Christian D, Laurent M, Francesco M, Alfonso M, Antonio M, Sergio C (2010) Hepatic vessel segmentation for 3D planning of liver surgery: experimental evaluation of a new fully automatic algorithm. Acad Radiol 18(4): 461–470

    Google Scholar 

  9. Funkhouser T, Kazhdan M, Shilane P, Min P, Kiefer W, Tal A, Rusinkiewicz S, Dobkin D (2004) Modeling by example. ACM Trans Graph (TOG)—Proceedings of ACM SIGGRAPH 23(3): 652–663

    Article  Google Scholar 

  10. Tung T, Schmitt F (2004) Augmented reeb graphs for content-based retrieval of 3d mesh models. Proceedings In Shape Modeling and Applications, pp. 157–166

  11. David L, Elsa DA, Isabelle B, Gareth F-L (2009) A review of 3D vessel lumen segmentation techniques: models, features and extraction schemes. Med Image Anal 13(6): 819–845

    Article  Google Scholar 

  12. Xiaopeng Z, Jianfei L, Zili L, Marc J (2008) Volume Decomposition and Hierarchical Skeletonization. In: Proceedings of The 7th ACM SIGGRAPH international conference on virtual-reality continuum and its applications in industry, Article No. 17

  13. Lien JM, Keyser J, Amato NM (2006) Simultaneous shape decomposition and skeletonization. In: Proceedings of ACM symposium on solid and physical modeling, pp 219–228

  14. Weimin H, Jiayin Z, Jiang L, Jing Z, Tao Y, Yi S, Gim HL, Chee KC, Stephen C (2011) 3D shape decomposition and comparison for gallbladder modeling. In: Proceedings of the SPIE 7964, 79642K

  15. Dekanic K, Loncari S (2007) 3D vascular tree segmentation using level set deformable model. In Proceeding of the 5th international symposium on image and signal processing and analysis

  16. Cohen LD, Deschamps T (2007) Segmentation of 3D tubular objects with adaptive front propagation and minimal tree extraction for 3D medical imaging. Comput Methods in Biomech Biomed Eng 10(4): 289–305

    Article  Google Scholar 

  17. Gooya A, Liao H (2008) A variational method for geometric regularization of vascular segmentation in medical images. IEEE Trans Image Process 17(8): 1295–1312

    Article  PubMed  Google Scholar 

  18. Chen B, Kitasaka T, Honma H, Takabatake H, Mori M, Natori H, Mori K (2012) Automatic segmentation of pulmonary blood vessels and nodules based on local intensity structure analysis and surface propagation in 3D chest CT images. Int J Comput Assist Radiol Surg 7(3): 465–482

    Article  PubMed  Google Scholar 

  19. Bing-yin R, Yong-bo Z, Daniel XBC (2010) A novel method for 3D-segmentation of vascular images. The 3rd international conference of bionic engineering, Advances in Natural Science 3(2)

  20. Kirbas C, Quek FKH (2004) A review of vessel extraction techniques and algorithms. ACM Comput Surv (CSUR) 36(2): 81–121

    Article  Google Scholar 

  21. Attene M, Biasotti S, Mortara M, Patane G, Spagnuolo M, Falcidieno B (2006) Computational methods for understanding 3d shapes. Comput Graph Special Issue Comput Graph 30(3): 323–333

    Google Scholar 

  22. Carrillo J, Orkisz M, Hoyos M (2005) Extraction of 3D vascular tree skeletons based on the analysis of connected components evolution. Lect Notes Comput Sci 3691: 604–611

    Article  Google Scholar 

  23. Florez-Valencia L, Azencot J, Vincent F, Orkisz M, Magnin IE (2006) Segmentation and quantification of blood vessels in 3D images using a right generalized cylinder state model. IEEE international conference on image processing, pp 2441–2444

  24. Piccinelli M, Veneziani A, Steinman DA, Remuzzi A, Antiga L (2009) A framework for geometric analysis of vascular structures: application to cerebral aneurysms. IEEE Trans Med Imaging 28(8): 1141–1155

    Article  PubMed  Google Scholar 

  25. Marcela HH, Maciej O, Philippe CD, Isabelle EM (2006) Assessment of carotid artery stenoses in 3D contrast-enhanced magnetic resonance angiography, based on improved generation of the centerline. Mach Graph Vis 14(4): 349–378

    Google Scholar 

  26. Antiga L (2004) Robust and objective decomposition and mapping of bifurcating vessels. IEEE Trans Med Imaging 23(6): 704–713

    Article  PubMed  Google Scholar 

  27. Franchini E, Morigi S, Sgallari F (2010) Segmentation of 3D tubular structures by a PDE-based anisotropic diffusion model. MMCS, volume 5862 of lecture notes in computer science, pp 224–241

  28. McIntosh C, Hamarneh G (2006) Vessel Crawlers: 3D physically-based deformable organisms for vasculature segmentation and analysis. IEEE computer society conference on computer vision and pattern recognition (CVPR’06), vol. 1, pp 1084–1091

  29. Xiaopeng Z, Bo X, Wujun C, Marc J (2009) Volume decomposition and hierarchical skeletonization for shape analysis. Pattern Recognit D: 47–72

    Google Scholar 

  30. Wei Ma, Bo X, Xiaopeng Z, Hongbin Z (2008) Decomposition of branching volume data by tip detection. IEEE international conference on image processing, pp 1948–1951

  31. Lien JM, Amato NM (2006) Approximate convex decomposition. Comput Geom 35(1–2): 100–123

    Article  Google Scholar 

  32. Lien JM, Amato NM (2004) Approximate convex decomposition of polygons. In: Proceedings of the 20th annual ACM symposium computational geometry (SoCG), pp 17–26

  33. Katz S, Tal A (2003) Hierarchical mesh decomposition using fuzzy clustering and cuts. ACM Trans Graph (TOG)—Proceedings of ACM SIGGRAPH 22(3): 954–961

    Article  Google Scholar 

  34. Lien JM, Amato NM (2008) Approximate convex decomposition of polyhedra and its applications. Comput Aided Geom Des (CAGD) 25(7): 503–522

    Article  Google Scholar 

  35. Newman T, Hong Y (2006) A survey on marching cubes algorithm. Comput Graph 30(5): 854–879

    Article  Google Scholar 

  36. Kawata Y, Niki N, Ohmatsu H, Kakinuma R, Eguchi K, Kaneko M, Moriyama N (1998) Quantitative surface characterization of pulmonary nodules based on thin-section CT images. IEEE Trans Nucl Sci 45(4): 2132–2138

    Article  Google Scholar 

  37. Cees W, Vincent FR, Frans MV, Lucas JV (2010) Detection and segmentation of colonic polyps on implicit isosurfaces by second principal curvature flow. IEEE Trans Med Imaging 29(3): 688–689

    Article  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Department of Computer Science and Engineering, The State University of New York, Buffalo, NY, USA

    Ashirwad Chowriappa & Peter D. Scott

  2. Department of Mechanical and Aerospace Engineering, The State University of New York, Buffalo, NY, USA

    T. Kesavadas & Sarthak Salunke

  3. Department of Neuroscience, Millard Fillmore Gates Hospital, Buffalo, NY, USA

    Maxim Mokin, Peter Kan & Sabareesh K. Natarajan

Authors
  1. Ashirwad Chowriappa
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. T. Kesavadas
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Maxim Mokin
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Peter Kan
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Sarthak Salunke
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Sabareesh K. Natarajan
    View author publications

    You can also search for this author in PubMed Google Scholar

  7. Peter D. Scott
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Ashirwad Chowriappa.

Rights and permissions

Reprints and permissions

About this article

Cite this article

Chowriappa, A., Kesavadas, T., Mokin, M. et al. Vascular decomposition using weighted approximate convex decomposition. Int J CARS 8, 207–219 (2013). https://doi.org/10.1007/s11548-012-0766-6

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11548-012-0766-6

Keywords

Search

Navigation