Abstract
The evaluation of 3D medical image segmentation quality requires a reliable detailed comparison of a reference segmentation with an automatic segmentation. It should be able to measure the quality accurately and, thus, to reveal problematic regions. While several (global) measures, providing a single quality value, are available, the only widely used local measure is the Surface Distance (i.e., point-to-surface distance). This measure, however, has significant drawbacks such as asymmetry and underestimation in distant and differently formed regions. Other available measures have limited suitability for 3D medical segmentation evaluation. We present a more reliable distance measure for assessing and analyzing local differences between automatic and reference (i.e., ground truth) 3D segmentations. We identify and overcome Surface Distance drawbacks, esp. in regions with larger dissimilarities. We evaluated our approach on four real medical image datasets. The results indicate that our measure provides more accurate local distance values.
Similar content being viewed by others
References
Aspert, N., Santa-Cruz, D., Ebrahimi, T.: Mesh: measuring errors between surfaces using the hausdorff distance. In: Proceedings of Multimedia and Expo, ICME, vol. 1, pp. 705–708. IEEE, New York (2002)
Becker, M., Kirschner, M., Sakas, G.: Segmentation of risk structures for otologic surgery using the probabilistic active shape model (pasm). In: Proceedings of SPIE Medical Imaging, pp. 90,360O–90,360O. International Society for Optics and Photonics (2014)
Belongie, S., Malik, J., Puzicha, J.: Matching shapes. In: Proceedings of Computer Vision, ICCV, vol. 1, pp. 454–461. IEEE, New York (2001)
Brown, B.J., Rusinkiewicz, S.: Global non-rigid alignment of 3-d scans. In: Proceedings of ACM T. Graphics (TOG), vol. 26, p. 21. ACM, New York (2007)
Cates, J., Meyer, M., Fletcher, T., Whitaker, R., et al.: Entropy-based particle systems for shape correspondence. In: Proceedings of 1st MICCAI Workshop on Mathematical Foundations of Computational Anatomy: Geometrical, Statistical and Registration Methods for Modeling Biological Shape Variability, pp. 90–99 (2006)
Chalana, V., Kim, Y.: A methodology for evaluation of boundary detection algorithms on medical images. IEEE T. Med. Imaging 16(5), 642–652 (1997)
Cohen-Steiner, D., Alliez, P., Desbrun, M.: Variational shape approximation. ACM T. Gr. 23(3), 905–914 (2004)
Gerig, G., Jomier, M., Chakos, M.: Valmet: a new validation tool for assessing and improving 3D object segmentation. In: Proceedings of Medical Image Computing and Computer-Assisted Intervention, MICCAI, pp. 516–523. Springer, Berlin, Germany (2001)
Gueziec, A.: Meshsweeper: dynamic point-to-polygonal mesh distance and applications. IEEE T. Vis. Comput. Gr. 7(1), 47–61 (2001)
Haehnel, D., Thrun, S., Burgard, W.: An extension of the icp algorithm for modeling nonrigid objects with mobile robots. In: Proceedings of IJCAI, pp. 915–920 (2003)
Heimann, T., van Ginneken, B., Styner, M.A., Arzhaeva, Y., Aurich, V., Bauer, C., Beck, A., Becker, C., Beichel, R., Bekes, G., et al.: Comparison and evaluation of methods for liver segmentation from ct datasets. IEEE T. Med. Imaging 28(8), 1251–1265 (2009)
Heimann, T., Meinzer, H.P.: Statistical shape models for 3d medical image segmentation: a review. Med. Image Anal. 13(4), 543–563 (2009)
Hoppe, H.: Progressive meshes. In: Proceedings of Computer Graphics and Interactive Techniques, pp. 99–108. ACM, New York (1996)
Johnson, A.E.: Spin-images: a representation for 3-D surface matching. Ph.D. thesis, Carnegie Mellon University (1997)
Kirschner, M., Becker, M., Wesarg, S.: 3D active shape model segmentation with nonlinear shape priors. In: Proceedings of Medical Image Computing and Computer-Assisted Intervention, MICCAI, LNCS, vol. 6892, pp. 492–499 (2011)
Kraevoy, V., Sheffer, A.: Cross-parameterization and compatible remeshing of 3d models. In: Proceedings of ACM T. Graphics (TOG), vol. 23, pp. 861–869. ACM, New York (2004)
Landesberger, T.V., Andrienko, G., Andrienko, N., Bremm, S., Kirschner, M., Wesarg, S., Kuijper, A.: Opening up the “black box” of medical image segmentation with statistical shape models. Vis. Comput. 29(9), 893–905 (2013)
Li, H., Hartley, R.: The 3D–3D registration problem revisited. In: Proceedings of Computer Vision, ICCV, pp. 1–8. IEEE, New York (2007)
Li, H., Sumner, R.W., Pauly, M.: Global correspondence optimization for non-rigid registration of depth scans. In: Proceedings of Computer Graphics Forum, vol. 27, pp. 1421–1430. Wiley, New Jersey (2008)
Lipman, Y., Rustamov, R.M., Funkhouser, T.A.: Biharmonic distance. ACM T. Gr. 29(3), 27 (2010)
Lorenz, C., Krahnstover, N.: 3D statistical shape models for medical image segmentation. In: Proceedings of 3-D Digital Imaging and Modeling, pp. 414–423. IEEE, New York (1999)
Martinek, M., Grosso, R., Greiner, G.: Interactive partial 3d shape matching with geometric distance optimization. Vis. Comput. 31(2), 223–233 (2015)
Pizer, S.M., Fletcher, P.T., Joshi, S., Thall, A., Chen, J.Z., Fridman, Y., Fritsch, D.S., Gash, A.G., Glotzer, J.M., Jiroutek, M.R., et al.: Deformable m-reps for 3d medical image segmentation. Int. J. Comput. Vis. 55(2–3), 85–106 (2003)
Sahillioglu, Y., Yemez, Y.: Coarse-to-fine combinatorial matching for dense isometric shape correspondence. In: Proceedings of Computer Graphics Forum, vol. 30, pp. 1461–1470. Wiley, New Jersey (2011)
Strecha, C., von Hansen, W., Van Gool, L., Fua, P., Thoennessen, U.: On benchmarking camera calibration and multi-view stereo for high resolution imagery. In: Proceedings of Computer Vision and Pattern Recognition, CVPR, pp. 1–8. IEEE, New York (2008)
Udupa, J.K., Leblanc, V.R., Zhuge, Y., Imielinska, C., Schmidt, H., Currie, L.M., Hirsch, B.E., Woodburn, J.: A framework for evaluating image segmentation algorithms. Comput. Med. Imaging Gr. 30(2), 75–87 (2006)
Van Ginneken, B., Heimann, T., Styner, M.: 3D segmentation in the clinic: a grand challenge. 3D segmentation in the clinic: a grand challenge, pp. 7–15 (2007)
Van Kaick, O., Zhang, H., Hamarneh, G., Cohen-Or, D.: A survey on shape correspondence. In: Proceedings of Computer Graphics Forum, vol. 30, pp. 1681–1707. Wiley, New Jersey (2011)
Veltkamp, R.C., Hagedoorn, M.: State-of-the-art in shape matching. In: Proceedings of Technical Report, Principles of Visual Information Retrieval (1999)
Wu, H., Miao, Z., Wang, Y., Lin, M.: Optimized recognition with few instances based on semantic distance. Vis. Comput. 31(4), 367–375 (2015)
Zhang, H., Sheffer, A., Cohen-Or, D., Zhou, Q., Van Kaick, O., Tagliasacchi, A.: Deformation-driven shape correspondence. In: Proceedings of Computer Graphics Forum, vol. 27, pp. 1431–1439. Wiley, New York (2008)
Zou, K.H., Warfield, S.K., Bharatha, A., Tempany, C.M., Kaus, M.R., Haker, S.J., Wells, W.M., Jolesz, F.A., Kikinis, R.: Statistical validation of image segmentation quality based on a spatial overlap index 1: scientific reports. Acad. Radiol. 11(2), 178–189 (2004)
Acknowledgments
The work has been partially supported by DFG within an SPP 1335 project. The authors are grateful to Prof. Georg Sakas and Dr. Meike Becker for the data provision, support with the project and helpful comments on the paper draft.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Getto, R., Kuijper, A. & von Landesberger, T. Extended surface distance for local evaluation of 3D medical image segmentations. Vis Comput 31, 989–999 (2015). https://doi.org/10.1007/s00371-015-1113-z
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00371-015-1113-z