Journal of Medical Systems

, Volume 36, Issue 5, pp 2829–2839 | Cite as

Manual Refinement System for Graph-Based Segmentation Results in the Medical Domain

  • Jan EggerEmail author
  • Rivka R. Colen
  • Bernd Freisleben
  • Christopher Nimsky


The basic principle of graph-based approaches for image segmentation is to interpret an image as a graph, where the nodes of the graph represent 2D pixels or 3D voxels of the image. The weighted edges of the graph are obtained by intensity differences in the image. Once the graph is constructed, the minimal cost closed set on the graph can be computed via a polynomial time s-t cut, dividing the graph into two parts: the object and the background. However, no segmentation method provides perfect results, so additional manual editing is required, especially in the sensitive field of medical image processing. In this study, we present a manual refinement method that takes advantage of the basic design of graph-based image segmentation algorithms. Our approach restricts a graph-cut by using additional user-defined seed points to set up fixed nodes in the graph. The advantage is that manual edits can be integrated intuitively and quickly into the segmentation result of a graph-based approach. The method can be applied to both 2D and 3D objects that have to be segmented. Experimental results for synthetic and real images are presented to demonstrate the feasibility of our approach.


Segmentation Graph-based Manual refinement 2D 3D 



The authors would like to thank the physicians Dr. Barbara Carl, Christoph Kappus, Dr. Malgorzata Kolodziej and Dr. Daniela Kuhnt for performing the manual segmentations of the medical images and therefore providing the ground truth for the evaluation. Furthermore, the authors want to thank Prof. Dr. Ron Kikinis for his thoughtful comments and Dr. Sonia Pujol for helping performing the 3D visualization of the tumor and the ventricle under Slicer (see Finally, the authors would like to thank Fraunhofer MeVis in Bremen, Germany, for their collaboration and especially Prof. Dr. Horst K. Hahn for his support.

Conflict of interest statement

All authors in this paper have no potential conflict of interests.


  1. 1.
    Shapiro, L. G., and Stockman, G. C., Computer vision. Prentice Hall, ISBN 0-13-030796-3, 608 pages, 2001.Google Scholar
  2. 2.
    Pham, D. L., Xu, C., and Prince, J. L., Current methods in medical image segmentation. Annu. Rev. Biomed. Eng. 02:315–37, 2000.CrossRefGoogle Scholar
  3. 3.
    Cufí, X., Muñoz, X., Freixenet, J., and Martí, J., A review on image segmentation techniques integrating region and boundary information. Adv. Imag. Electron. Phys. 120:1–39, 2003.CrossRefGoogle Scholar
  4. 4.
    Kass, M., Witkin, A., and Terzopolous, D., Snakes: Active contour models. International Journal of Computer Vision (IJCV) 1(4):321–331, 1988.CrossRefGoogle Scholar
  5. 5.
    Kass, M., Witkin, A., and Terzopoulos, D., Constraints on deformable models: Recovering 3D shape and nongrid motion. Artif. Intell. 36:91–123, 1988.zbMATHCrossRefGoogle Scholar
  6. 6.
    Cootes, T. F., Edwards, G. J., and Taylor, C. J., Active appearance models. Proceedings of the European Conference on Computer Vision 2:484–498, 1998.Google Scholar
  7. 7.
    Cootes, T. F., and Taylor, C. J., Statistical models of appearance for computer vision, Technical report, University of Manchester, 2004.Google Scholar
  8. 8.
    Cootes, T. F., and Taylor, C. J., Active shape models - ‘smart snakes. Proceedings of the British Machine Vision Conference 266–275, 1992.Google Scholar
  9. 9.
    Sclaroff, S., Isidoro, J., Active blobs. Proceedings of the Sixth International Conference on Computer Vision, IEEE Computer Society, pp. 1146–1153, Washington, DC, USA, 1998.Google Scholar
  10. 10.
    Li, K., Wu, X., Chen, D. Z., and Sonka, M., Efficient optimal surface detection: Theory, implementation and experimental validation. Proceedings of SPIE Int’l Symp. Medical Imaging: Image Processing 5370:620–627, 2004.Google Scholar
  11. 11.
    Li, K., Wu, X., Chen, D. Z., and Sonka, M., Globally optimal segmentation of interacting surfaces with geometric constraints. Proc. IEEE CS Conf. Computer Vision and Pattern Recognition (CVPR) 1:394–399, 2004.Google Scholar
  12. 12.
    Li, K., Wu, X., Chen, D. Z., and Sonka, M., Optimal surface segmentation in volumetric images-a graph-theoretic approach. IEEE Trans. Pattern Anal. Mach. Intell. 28(1):119–134, 2006.CrossRefGoogle Scholar
  13. 13.
    Boykov, Y., and Kolmogorov, V., An experimental comparison of min-cut/max-flow algorithms for energy minimization in vision. IEEE Trans. Pattern Anal. Mach. Intell. 26(9):1124–1137, 2004.CrossRefGoogle Scholar
  14. 14.
    Vezhnevets, V., and Konouchine, V., GrowCut - interactive multi-label N-D image segmentation. Proc. Graphicon, 150–156, 2005.Google Scholar
  15. 15.
  16. 16.
    Reese, L., Intelligent paint: region-based interactive image segmentation. Master’s thesis. Department of Computer Science, Brigham Young University, Provo, UT, 1999.Google Scholar
  17. 17.
    Mortensen, E. N., and Barrett, W. A., Interactive segmentation with intelligent scissors. Graph. Model Image Process 60(5):349–384, 1998.zbMATHCrossRefGoogle Scholar
  18. 18.
    Mortensen, E. N., and Barrett, W. A., Toboggan-based intelligent scissors with a four-parameter edge model. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2452–2458, 1999.Google Scholar
  19. 19.
    Boykov, Y., and Jolly, M.-P., Interactive graph cuts for optimal boundary and region segmentation of objects in n-d images. Proceedings of the International Conference on Computer Vision (ICCV) 1:105–112, 2001.Google Scholar
  20. 20.
    Rother, C., Kolmogorov, V., and Blake, A., Grabcut - interactive foreground extraction using iterated graph cuts. Proceedings of ACM Siggraph, 2004.Google Scholar
  21. 21.
    Moga, A., and Gabbouj, M., A parallel marker based watershed transformation. IEEE International Conference on Image Processing (ICIP), II: 137–140, 1996.Google Scholar
  22. 22.
    Grady, L., and Fumka-Lea, G., Multi-label image segmentation for medical applications based on graph-theoretic electrical potentials. ECCV Workshops CVAMIA and MMBIA, 230–245, 2004.Google Scholar
  23. 23.
    Heimann, T., Thorn, M., Kunert, T., and Meinzer, H.-P., New methods for leak detection and contour correction in seeded region growing segmentation. In 20th ISPRS Congress, Istanbul 2004. Int. Arch. Photogram. Rem. Sens. XXXV:317–322, 2004.Google Scholar
  24. 24.
    Egger, J., Bauer, M. H. A., Kuhnt, D., Freisleben, B., and Nimsky, Ch., Pituitary adenoma segmentation. Proceedings of International Biosignal Processing Conference, Charité, Berlin, Germany, July 2010.Google Scholar
  25. 25.
    Zukic, Dz., Egger, J., Bauer, M. H. A., Kuhnt, D., Carl, B., Freisleben, B., Kolb, A., and Nimsky, Ch., Preoperative volume determination for pituitary adenoma. Proceedings of SPIE Medical Imaging Conference, Orlando, Florida, USA, Feb. 2011.Google Scholar
  26. 26.
    Bauer, M. H. A., et al., A fast and robust graph-based approach for boundary estimation of fiber bundles relying on fractional anisotropy maps, 20th International Conference on Pattern Recognition (ICPR), Istanbul, Turkey, IEEE Computer Society, Aug. 2010.Google Scholar
  27. 27.
    Bauer, M. H. A. Egger, J., Kuhnt, D., Barbieri, S., Klein, J., Hahn, H. K., Freisleben, B., and Nimsky, Ch., A semi-automatic graph-based approach for determining the boundary of eloquent fiber bundles in the human brain, Proceedings of 44. Jahrestagung der DGBMT, Rostock, Germany, Oct. 2010.Google Scholar
  28. 28.
    Bauer ,M. H. A., Egger, J., Kuhnt, D., Barbieri, S., Klein, J., Hahn, H. K., Freisleben, B., and Nimsky, Ch., Ray-based and graph-based methods for fiber bundle boundary estimation. Proceedings of International Biosignal Processing Conference, Charité, Berlin, Germany, July 2010.Google Scholar
  29. 29.
    Egger, J., Freisleben, B., Setser, R., Renapuraar, R., Biermann, C., and O’Donnell, T., Aorta segmentation for stent simulation, 12th International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI), Cardiovascular Interventional Imaging and Biophysical Modelling Workshop, 10 pages, London, UK, Sep. 2009.Google Scholar
  30. 30.
    Egger, J., O’Donnell, T., Hopfgartner, C., and Freisleben, B., Graph-based tracking method for aortic thrombus segmentation. Proceedings of 4th European Congress for Medical and Biomedical Engineering, Engineering for Health, Antwerp, Belgium, Springer, pp. 584–587, 2008.Google Scholar
  31. 31.
    Renapurkar, R. D., Setser, R. M., O’Donnell, T. P., Egger, J., Lieber, M. L., Desai, M. Y., Stillman, A. E., Schoenhagen, P., and Flamm, S. D., Aortic volume as an indicator of disease progression in patients with untreated infrarenal abdominal aneurysm. Eur. J. Radiol., 7 pages, Feb. 2011.Google Scholar
  32. 32.
    Egger, J., Bauer, M. H. A., Kuhnt, D., Carl, B., Kappus, C., Freisleben, B., and Nimsky, Ch., Nugget-cut: A segmentation scheme for spherically- and elliptically-shaped 3D objects, 32nd Annual Symposium of the German Association for Pattern Recognition (DAGM), LNCS 6376, pp. 383–392, Springer Press, Darmstadt, Germany, 2010.Google Scholar
  33. 33.
    Egger, J., Bauer, M. H. A., Kuhnt, D., Kappus, C., Carl, B., Freisleben, B., and Nimsky, Ch., A flexible semi-automatic approach for glioblastoma multiforme segmentation, Proceedings of International Biosignal Processing Conference, Charité, Berlin, Germany, 4 pages, July 2010.Google Scholar
  34. 34.
    Egger, J., Zukic, Dz., Bauer ,M. H. A., Kuhnt, D., Carl, B., Freisleben, B., Kolb, A., and Nimsky, Ch., A comparison of two human brain tumor segmentation methods for MRI data, Proceedings of 6th Russian-Bavarian Conference on Bio-Medical Engineering, State Technical University, Moscow, Russia, Nov. 2010.Google Scholar
  35. 35.
    Egger, J., Kappus, C., Freisleben, B., and Nimsky, Ch., A medical software system for volumetric analysis of cerebral pathologies in magnetic resonance imaging (MRI) data. J. Med. Syst., Springer, 13 pages, Mar. 2011.Google Scholar
  36. 36.
    Egger, J., Mostarkic, Z., Großkopf, S., and Freisleben, B., A fast vessel centerline extraction algorithm for catheter simulation, 20th IEEE international symposium on computer- based medical systems, Maribor, Slovenia, pp. 177–182, IEEE Press, 2007.Google Scholar
  37. 37.
    Zou, K. H., Warfield, S. K., Bharatha, A., Tempany, C. M. C., Kaus, M. R., Haker, S. J., Wells, W. M., Jolesz, F. A., and Kikinis, R., Statistical validation of image segmentation quality based on a spatial overlap index: Scientific reports. Acad. Radiol. 11(2):178–189, 2004.CrossRefGoogle Scholar
  38. 38.
    Sampat, M. P., Wang, Z., Markey, M. K., Whitman, G. J., Stephens, T. W., and Bovik, A. C., Measuring intra- and inter-observer agreement in identifying and localizing structures in medical images. IEEE Inter. Conf. Image Processing, 2006.Google Scholar
  39. 39.
    Greiner, K., et al., Segmentation of aortic aneurysms in CTA-images with the statistic method of the active appearance models (in German), Bildverarbeitung für die Medizin (BVM), Berlin, Germany, Springer Press, pp. 51–55, 2008.Google Scholar

Copyright information

© Springer Science+Business Media, LLC 2011

Authors and Affiliations

  • Jan Egger
    • 1
    • 2
    • 3
    Email author
  • Rivka R. Colen
    • 1
  • Bernd Freisleben
    • 2
  • Christopher Nimsky
    • 3
  1. 1.Surgical Planning Laboratory, Department of Radiology, Brigham and Women’s HospitalHarvard Medical SchoolBostonUSA
  2. 2.Department of Mathematics and Computer ScienceUniversity of MarburgMarburgGermany
  3. 3.Department of NeurosurgeryUniversity of MarburgMarburgGermany

Personalised recommendations