medigraphic.com

2000, Number 3

<< Back Next >>

Rev Mex Ing Biomed 2000; 21 (3)

A combined algorithm for image segmentation using neural networks and 3D surface reconstruction using dynamic meshes

Reyes ACC, Algorri ME

Language: English
References: 24
Page: 73-81
PDF size: 259.29 Kb.


ABSTRACT

Reconstructing the surface from a set of unstructured points to build a 3D model is a problem that arises in many scientific and industrial fields as new 3D scanning technology is able to produce large databases of full 3D information. 3D surface reconstruction is also important after segmenting sets of 2D images to visualise the 3D surface represented by the segmentation. In this paper we propose an algorithmic methodology that obtains a series of segmentations of human head tomographies, produces a set of unstructured points in the 3D space, and then automatically produces a surface from the set of unstructured 3D points about which we have no topological knowledge. The methodology can be divided in two stages. First, tomographic images are segmented with a Neural Network algorithm based on Kohonen’s1,2 Self-Organising Maps (SOM). The output neurones that have adapted to the image, are a series of 3D points that will be fed to the second stage. Next, our method uses a spatial decomposition and surface tracking algorithm to produce a rough approximation S’ of the unknown manifold S. The produced surface S’ serves as initialisation for a dynamic mesh model that yields the details of S to improve the quality of the reconstruction.


REFERENCES

  1. Kohonen T. Self-Organisation and Associative Memory, Heidelberg: Springer-Verlag 1988.

  2. Kohonen T. Self-Organising Maps: Optimisation and Approaches, Finland: ICANN, Espoo 1991.

  3. Hall EL. Computer Image Processing and Recognition, New York: Academic Press 1979.

  4. Scudder HJ. Introduction to Computed Aided Tomography, Proc. IEEE 1978; 66: 628-637.

  5. Mueller RK, Kaveh M and Wade G. Reconstructive Tomography and Applications to Ultrasonic, Proc IEEE 1979; 67: 567-587.

  6. Hinshaw W and Lent AH. An Introduction to NMR Imaging: From the Bloch Equation to the Imaging Equation, Proc IEEE 1983; 71: 338-350.

  7. Warfield SK, Jolesz FA and Kikinis R. Real-time Image Segmentation for Image-Guided Surgery, Surgical Planning Laboratory, Department of Radiology, Harvard Medical School and Brigham and Women’s Hospital: SPL Technical Report 1998; 106.

  8. Kapur T. Model based three dimensional Medical Image Segmentation, Artificial Intelligence Laboratory, Massachusetts Institute of Technology: Ph.D. Thesis 1999.

  9. Saiviroonporn P, Robatino A, Zahajszky J, Kikinis R and Jolesz FA. Real-time Interactive 3D-Segmentation. Acad. Radiol 1998; 5: 49-56

  10. Rueckert D, Burger P, Forbat SM, Mohiaddin RD and Yang GZ. Automatic Tracking of the Aorta in Cardiovascular MR images Using Deformable Models, IEEE Transactions on Medical Imaging 1997; 16(5): 581-590.

  11. González RC and Woods RE. Digital Image Processing, Addison Wesley, Reading 1992.

  12. Felzenszwalb PF and Huttenlocher DP. Image Segmentation Using Local Variation, Santa Barbara, California: CVPR98 1998.

  13. Ramón-Cajal S. Histology, Baltimore: William Wood & Co 1933).

  14. Reyes-Aldasoro CC. A Non-linear Decrease Rate to Optimise the Convergence of the Kohonen Neural Network Self-Organising Algorithm, ROCC99 Acapulco, Mexico, 1998: 11-16.

  15. Lorensen WE, Cline HE. Marching Cubes: A High Resolution 3D Surface Construction Algorithm, SIGGRAPH ’87 1987; 21(4): 163-169.

  16. Szeliski R, Tonnesen D, Terzopoulos D. Modelling Surfaces of Arbitrary Topology with dynamic particles, Proc CVPR ‘93 1993: 82-87.

  17. Miller JV, Breen DE, Lorensen WE, O’Bara RM, Wozny MJ. Geometrically Deformed Models: A Method for Extract. Closed Geom. Models from Vol. Data, SIGGRAPH ‘91 1991; 25(4): 217-225.

  18. Vasilescu M, Terzopoulos D. Adaptive Meshes and Shells: Irregular Triangulation, Discontinuities, and Hierarchical Subdivision, Proc CVPR’92 1992: 829-832.

  19. Hoppe H. Surface Reconstruction from Unorganised Points, Univ. of Washington, Seattle WA: Ph.D. Dissertation 1994.

  20. Huang W-C, Goldgof DB. Sampling and Surface Reconstruction with Adaptive-Size Meshes, Proc SPIE Appl of Art. Intell. X 1992; 1798: 760-770.

  21. Delinguette H. Modelisation, Déformation et Reconnaissance d’Objets Tridimensionnels à l’aide de Maillages Simplexes, Ecole Centrale Paris: Ph.D. thesis 1994.

  22. Leitner F. Segmentation Dynamique d’Images Tridimensionelles, Institut National Polytechnique de Grenoble: Ph.D. thesis 1993.

  23. Gordon D, Udupa J. Fast Surface Tracking in 3-D Binary Images, Computer Vision, Graphics, and Image Processing 1989; 45: 196-214.

  24. Algorri MR, Schmitt F. Surface Reconstruction from Unstructured 3D Data, Computer Graphics Forum 1996; 15(1): 47-60.




2020     |     www.medigraphic.com