Combining rules using local statistics and uncertainty estimates for improved ensemble segmentation
- 29 Downloads
Segmentation using an ensemble of classifiers (or committee machine) combines multiple classifiers’ results to increase the performance when compared to single classifiers. In this paper, we propose new concepts for combining rules. They are based (1) on uncertainties of the individual classifiers, (2) on combining the result of existing combining rules, (3) on combining local class probabilities with the existing segmentation probabilities at each individual segmentation, and (4) on using uncertainty-based weights for the weighted majority rule. The results show that the proposed local-statistics-aware combining rules can reduce the effect of noise in the individual segmentation result and consequently improve the performance of the final (combined) segmentation. Also, combining existing combining rules and using the proposed uncertainty- based weights can further improve the performance.
Keywordsensemble of classifiers combining rules image segmentation modified Fuzzy c-means
Unable to display preview. Download preview PDF.
- 8.T. G. Dietterich, “Ensemble methods in machine learning,” in Proc. 1st Int. Workshop on Multiple Classifier Systems (Springer-Verlag, London, 2000), pp. 1–15.Google Scholar
- 12.R. Langerak, U. A. van der Heide, A. N. T. J. Kotte, M. A. Viergever, M. van Vulpen, and J. P. W. Pluim, “Label fusion in atlas-based segmentation using a selective and iterative method for performance level estimation (simple),” IEEE Trans. Med. Imag. 29 (12), 2000–2008 (2010).CrossRefGoogle Scholar
- 13.C. Li, C. Xu, A. Anderson, and J. Gore, “Mri tissue classification and bias field estimation based on coherent local intensity clustering: a unified energy minimization framework,” in Information Processing in Medical Imaging, Lecture Notes in Computer Science (Springer, Berlin, Heidelberg, 2009), Vol. 5636, pp. 288–299.CrossRefGoogle Scholar
- 15.MNI. Brainweb, simulated brain database (1997). http://www.bic.mni.mcgill.ca/brainweb/Accessed Nov. 2012.Google Scholar
- 16.N. Mohamed, M. Ahmed, and A. Farag, “Modified fuzzy c-mean in medical image segmentation,” in Proc. IEEE Int. Conf. on Acoustics, Speeeh, and Signal Processing (Piscataway, NI, 1999), Vol. 6, pp. 3429–3432.Google Scholar
- 23.W. Wang, Y. Zhu, X. Huang, D. P. Lopresti, Z. Xue, L. R. Long, S. Antani, and G. R. Thoma, “A classifier ensemble based on performance level estimation,” in Proc. IEEE ISBI (Boston, MA, 2009), pp. 342–345.Google Scholar