Advertisement

Statistical Shape Models: Understanding and Mastering Variation in Anatomy

  • Felix Ambellan
  • Hans Lamecker
  • Christoph von Tycowicz
  • Stefan ZachowEmail author
Chapter
Part of the Advances in Experimental Medicine and Biology book series (AEMB, volume 1156)

Abstract

In our chapter we are describing how to reconstruct three-dimensional anatomy from medical image data and how to build Statistical 3D Shape Models out of many such reconstructions yielding a new kind of anatomy that not only allows quantitative analysis of anatomical variation but also a visual exploration and educational visualization. Future digital anatomy atlases will not only show a static (average) anatomy but also its normal or pathological variation in three or even four dimensions, hence, illustrating growth and/or disease progression.

Statistical Shape Models (SSMs) are geometric models that describe a collection of semantically similar objects in a very compact way. SSMs represent an average shape of many three-dimensional objects as well as their variation in shape. The creation of SSMs requires a correspondence mapping, which can be achieved e.g. by parameterization with a respective sampling. If a corresponding parameterization over all shapes can be established, variation between individual shape characteristics can be mathematically investigated.

We will explain what Statistical Shape Models are and how they are constructed. Extensions of Statistical Shape Models will be motivated for articulated coupled structures. In addition to shape also the appearance of objects will be integrated into the concept. Appearance is a visual feature independent of shape that depends on observers or imaging techniques. Typical appearances are for instance the color and intensity of a visual surface of an object under particular lighting conditions, or measurements of material properties with computed tomography (CT) or magnetic resonance imaging (MRI). A combination of (articulated) Statistical Shape Models with statistical models of appearance lead to articulated Statistical Shape and Appearance Models (a-SSAMs).

After giving various examples of SSMs for human organs, skeletal structures, faces, and bodies, we will shortly describe clinical applications where such models have been successfully employed. Statistical Shape Models are the foundation for the analysis of anatomical cohort data, where characteristic shapes are correlated to demographic or epidemiologic data. SSMs consisting of several thousands of objects offer, in combination with statistical methods or machine learning techniques, the possibility to identify characteristic clusters, thus being the foundation for advanced diagnostic disease scoring.

Keywords

Statistical shape analysis Medical image segmentation Data reconstruction Therapy planning Automated diagnosis support 

Notes

Acknowledgements

The authors gratefully acknowledge the financial support by the German research foundation (DFG) within the research center MATHEON (Germany´s Excellence Strategy – MATH+ : The Berlin Mathematics Research Center, EXC-2046/1 – project ID: 390685689), the German federal ministry of education and research (BMBF) within the research network on musculoskeletal diseases, grant no. 01EC1408B (Overload/PrevOP) and grant no. 01EC1406E (TOKMIS), the research program “Medical technology solutions for digital health care”, grant no. 13GW0208C (ArtiCardio), as well as the BMBF research campus MODAL.

References

  1. Agostini V, Balestra G, Knaflitz M (2014) Segmentation and classification of gait cycles. IEEE Trans Neural Syst Rehabil Eng 22(5):946–952CrossRefGoogle Scholar
  2. Akbari Shandiz M (2015) Component placement in hip and knee replacement surgery: device development, imaging and biomechanics. Doctoral dissertation, University of CalgaryGoogle Scholar
  3. Akbari Shandiz M, Boulos P, Saevarsson SK, Ramm H, Fu CK, Miller S, Zachow S, Anglin C (2018) Changes in knee shape and geometry resulting from total knee arthroplasty. Proc Inst of Mech Eng H J Eng Med 232(1):67–79CrossRefGoogle Scholar
  4. Ambellan F, Tack A, Ehlke M, Zachow S (2019) Automated segmentation of knee bone and cartilage combining statistical shape knowledge and convolutional neural networks: Data from the Osteoarthritis Initiative. Med Image Anal 52:109–118CrossRefGoogle Scholar
  5. Bergmann RA, Thompson SA, Afifi AK, Saadeh FA (1988) Compendium of human anatomic variation. Urban & Schwarzenberg. https://www.anatomyatlases.org
  6. Bernard F, Salamanca L, Thunberg J, Tack A, Jentsch D, Lamecker H, Zachow S, Hertel F, Goncalves J, Gemmar P (2017) Shape-aware surface reconstruction from sparse 3D point-clouds. Med Image Anal 38:77–89CrossRefGoogle Scholar
  7. Bindernagel M, Kainmüller D, Seim H, Lamecker H, Zachow S, Hege HC (2011) An articulated statistical shape model of the human knee. In: Bildverarbeitung für die Medizin, pp 59–63Google Scholar
  8. Boisvert J, Cheriet F, Pennec X, Labelle H, Ayache N (2008) Geometric variability of the scoliotic spine using statistics on articulated shape models. IEEE Trans Med Imaging 27(4):557–568CrossRefGoogle Scholar
  9. Bookstein FL (1986) Size and shape spaces for landmark data in two dimensions. Stat Sci 1(2):181–222CrossRefGoogle Scholar
  10. Bruse JL, Zuluaga MA, Khushnood A, McLeod K, Ntsinjana HN, Hsia TY, Taylor AM, Schievano S (2017) Detecting clinically meaningful shape clusters in medical image data: metrics analysis for hierarchical clustering applied to healthy and pathological aortic arches. IEEE Trans Biomed Eng 64(10):2373–2383CrossRefGoogle Scholar
  11. Davis RH, Twining CJ, Cootes TF, Waterton JC, Taylor CJ (2002) A minimum description length approach to statistical shape modelling. IEEE Trans Med Imaging 21:525–537CrossRefGoogle Scholar
  12. Dworzak J, Lamecker H, von Berg J, Klinder T, Lorenz C, Kainmüller D, Hege HC, Zachow S (2010) 3D reconstruction of the human rib cage from 2D projection images using a statistical shape model. Int J Comput Assist Radiol Surg 5(2):111–124CrossRefGoogle Scholar
  13. Ehlke M, Ramm H, Lamecker H, Hege HC, Zachow S (2013) Fast generation of virtual X-ray images for reconstruction of 3D anatomy. IEEE Trans Visual Comput Graph 19(12):2673–2682CrossRefGoogle Scholar
  14. Galloway F, Kahnt M, Ramm H, Worsley P, Zachow S, Nair P, Taylor M (2013) A large scale finite element study of a cementless osseointegrated tibial tray. J Biomech 46(11):1900–1906CrossRefGoogle Scholar
  15. Gerig G, Fishbaugh J, Sadeghi N (2016) Longitudinal modeling of appearance and shape and its potential for clinical use. Med Image Anal 33:114–121CrossRefGoogle Scholar
  16. German National Cohort. German federal and local state governments and the Helmholtz Association. https://nako.de/informationen-auf-englisch
  17. Gomes J, Darsa L, Costa B, Velho L (1999) Warping and morphing of graphical objects. Morgan Kaufmann Publishers, San FranciscoGoogle Scholar
  18. Grewe CM, Zachow S (2016) Fully automated and highly accurate dense correspondence for facial surfaces. In: European conference on computer vision, pp 552–568Google Scholar
  19. Griffiths I (2012) Choosing running shoes: the evidence behind the recommendations. http://www.sportspodiatryinfo.co.uk/choosing-running-shoes-the-evidence-behind-the-recommendations
  20. Gundelwein L, Ramm H, Goubergrits L, Kelm M, Lamecker H (2018) 3D Shape analysis for coarctation of the Aorta. In: International workshop on shape in medical imaging, pp 73–77Google Scholar
  21. Hochfeld M, Lamecker H, Thomale UW, Schulz M, Zachow S, Haberl H (2014) Frame-based cranial reconstruction. J Neurosurg Pediatr 13(3):319–323CrossRefGoogle Scholar
  22. The Osteoarthritis Initiative, National Institute of Health, USA. https://oai.nih.gov/
  23. Ingraham L (2018) You might just be weird: the clinical significance of normal – and not so normal – anatomical variations. https://www.painscience.com/articles/anatomical-variation.php
  24. Jones KL, Jones MC, Del Campo M (2013) Smith’s recognizable patterns of human malformation, 7th edn. Elsevier/Saunders, LondonGoogle Scholar
  25. Kainmüller D, Lange T, Lamecker H (2007) Shape constrained automatic segmentation of the liver based on a heuristic intensity model. In: MICCAI workshop 3D segmentation in the clinic: a grand challenge, pp 109–116Google Scholar
  26. Kainmüller D, Lamecker H, Zachow S, Hege HC (2009) An articulated statistical shape model for accurate hip joint segmentation. In: IEEE Engineering in medicine and biology society annual conference, pp 6345–6351Google Scholar
  27. Kamer L, Noser H, Lamecker H, Zachow S, Wittmers A, Kaup T, Schramm A, Hammer B (2006) Three-dimensional statistical shape analysis – a useful tool for developing a new type of orbital implant? AO Development Institute, New Products Brochure 2/06, pp 20–21Google Scholar
  28. Kendall DG, Barden D, Carne TK, Le H (2009) Shape and shape theory. Wiley, New YorkGoogle Scholar
  29. Klinder T, Wolz R, Lorenz C, Franz A, Ostermann J (2008) Spine segmentation using articulated shape models. In: International conference on medical image computing and computer-assisted intervention, pp 227–234Google Scholar
  30. Lamecker H (2008) Variational and statistical shape modeling for 3D geometry reconstruction. Doctoral dissertation, Freie Universität BerlinGoogle Scholar
  31. Lamecker H, Zachow S (2016) Statistical shape modeling of musculoskeletal structures and its applications. In: Computational radiology for orthopaedic interventions. Springer, pp 1–23Google Scholar
  32. Lamecker H, Lange T, Seebaß M (2002) A statistical shape model for the liver. In: International conference on medical image computing and computer-assisted intervention, pp 421–427Google Scholar
  33. Lamecker H, Seebaß M, Hege HC, Deuflhard P (2004) A 3D statistical shape model of the pelvic bone for segmentation. In: Medical imaging 2004: image processing, vol. 5370, pp 1341–1352Google Scholar
  34. Lamecker H, Zachow S, Haberl H, Stiller M (2005) Medical applications for statistical shape models. Computer Aided Surgery around the Head, Fortschritt-Berichte VDI – Biotechnik/Medizintechnik 17(258):1–61Google Scholar
  35. Lamecker H, Wenckebach TH, Hege HC (2006a) Atlas-based 3D-shape reconstruction from X-ray images. In: IEEE 18th International conference on pattern recognition, pp 371–374Google Scholar
  36. Lamecker H, Zachow S, Hege HC, Zockler M, Haberl H (2006b) Surgical treatment of craniosynostosis based on a statistical 3D-shape model: first clinical application. Int J Comput Assist Radiol Surg 1(Suppl 7):253–254Google Scholar
  37. Moore KL (1989) Meaning of “normal”. Clin Anat 2(4):235–239CrossRefGoogle Scholar
  38. Mukhopadhyay A, Victoria OSM, Zachow S, Lamecker H (2016) Robust and accurate appearance models based on joint dictionary learning data from the osteoarthritis initiative. In: International workshop on patch-based techniques in medical imaging, pp 25–33Google Scholar
  39. Nava-Yazdani E, Hege H-C, von Tycowicz C, Sullivan T (2018) A shape trajectories approach to longitudinal statistical analysis. Technical report, ZIB-report 18-42Google Scholar
  40. Rybak J, Kuß A, Hans L, Zachow S, Hege HC, Lienhard M, Singer J, Neubert K, Menzel R (2010) The digital bee brain: integrating and managing neurons in a common 3D reference system. Front Syst Neurosci 4:1–30Google Scholar
  41. Sañudo JR, Vázquez R, Puerta J (2003) Meaning and clinical interest of the anatomical variations in the 21st century. Eur J Anat 7(1):1–3Google Scholar
  42. Seim H, Kainmüller D, Lamecker H, Bindernagel M, Malinowski J, Zachow S (2010) Model-based auto-segmentation of knee bones and cartilage in MRI data. In: MICCAI workshop medical image analysis for the clinic, pp 215–223Google Scholar
  43. Study of Health in Pomerania. Forschungsverbund Community Medicine at Greifswald Medical School. http://www2.medizin.uni-greifswald.de/cm/fv/ship
  44. Tack A, Zachow S (2019) Accurate automated volumetry of cartilage of the knee using convolutional neural networks: data from the osteoarthritis initiative. In: IEEE 16th International Symposium on Biomedical Imaging (ISBI 2019), (accepted for publication)Google Scholar
  45. Tack A, Mukhopadhyay A, Zachow S (2018) Knee menisci segmentation using convolutional neural networks: data from the Osteoarthritis Initiative. Osteoarthr Cartil 26(5):680–688CrossRefGoogle Scholar
  46. Thompson DAW (1917) On growth and form. Cambridge University Press, CambridgeGoogle Scholar
  47. Toga AW (1998) Brain warping. Elsevier, AmsterdamGoogle Scholar
  48. van Kaick O, Zhang H, Hamarneh G, CohenOr D (2011) A survey on shape correspondence. Comput Graphics Forum 30(6):1681–1707CrossRefGoogle Scholar
  49. Vidal-Migallon I, Ramm H, Lamecker H (2015) Reconstruction of partial liver shapes based on a statistical 3D shape model. In: Shape symposium Delemont Switzerland, p 22Google Scholar
  50. von Berg J, Dworzak J, Klinder T, Manke D Kreth A, Lamecker H, Zachow S, Lorenz C (2011) Temporal subtraction of chest radiographs compensating pose differences. In: Medical imaging 2011: image processing, 79620UGoogle Scholar
  51. von Tycowicz C, Ambellan F, Mukhopadhyay A, Zachow S (2018) An efficient Riemannian statistical shape model using differential coordinates: with application to the classification of data from the osteoarthritis initiative. Med Image Anal 43:1–9CrossRefGoogle Scholar
  52. Wilson DAJ, Anglin C, Ambellan F, Grewe CM, Tack A, Lamecker H, Dunbar M, Zachow S (2017) Validation of three-dimensional models of the distal femur created from surgical navigation point cloud data for intraoperative and postoperative analysis of total knee arthroplasty. Int J Comput Assist Radiol Surg 12(12):2097–2105CrossRefGoogle Scholar
  53. Yao J (2002) A statistical bone density atlas and deformable medical image registration. Doctoral dissertation, Johns Hopkins UniversityGoogle Scholar
  54. Zachow S, Lamecker H, Elsholtz B, Stiller M (2005) Reconstruction of mandibular dysplasia using a statistical 3D shape model. In: Computer Assisted Radiology and Surgery (CARS), pp 1238–1243Google Scholar
  55. Zachow S, Zilske M, Hege HC (2007) 3D reconstruction of individual anatomy from medical image data: Segmentation and geometry processing. In: Proceedings of the 25. ANSYS conference and CADFEM users’ meeting, ZIB Preprint 07-41 available at opus4.kobv.de/opus4-zib/files/1044/ZR_07_41.pdf
  56. Zachow S, Kubiack K, Malinowski J, Lamecker H, Essig H, Gellrich NC (2010) Modellgestützte chirurgische Rekonstruktion komplexer Mittelgesichtsfrakturen. In: Proceedings of Biomedical Technology Conference (BMT), pp 107–108Google Scholar
  57. SHIP (2019) Study of Health in Pomerania. Forschungsverbund Community Medicine at Greifswald Medical School. http://www2.medizin.uni-greifswald.de/cm/fv/shipGoogle Scholar
  58. OAI (2019) The Osteoarthritis Initiative, National Institute of Health, USA. https://oai.nih.gov/Google Scholar
  59. GNC (2019) German National Cohort. German federal and local state governments and the Helmholtz Association. https://nako.de/informationen-auf-englischGoogle Scholar
  60. https://opus4.kobv.de/opus4-zib/files/1044/ZR_07_41.pdfGoogle Scholar
  61. Zachow S, Zilske M, Hege HC (2007) 3D reconstruction of individual anatomy from medical image data: Segmentation and geometry processing. In: Proceedings of the 25. ANSYS conference and CADFEM users’ meeting, ZIB Preprint 07-41 available at https://opus4.kobv.de/opus4-zib/files/1044/ZR_07_41.pdfGoogle Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  • Felix Ambellan
    • 1
  • Hans Lamecker
    • 2
    • 1
  • Christoph von Tycowicz
    • 1
  • Stefan Zachow
    • 2
    • 1
    Email author
  1. 1.Zuse Institute BerlinBerlinGermany
  2. 2.1000 Shapes GmbHBerlinGermany

Personalised recommendations