![](bg8.png)
images with thin structures. However, without the
use of discriminative classifiers and texture descrip-
tors, it could not distinguish liver tissues from muscle
tissues, as shown in Fig. 7(b).
6 CONCLUSIONS
We have presented a robust and accurate method for
biomedical image segmentation using level sets of
probabilities. Our method integrates a probabilis-
tic classifier with the level set method, making the
level set method less vulnerable to local minima. Our
method obtains a posterior probabilistic mask of an
object of interest as the segmentation result. We
further alternate classifier training and the level set
method to improve the performance of both. We have
successfully applied our method to the segmentation
of various organs and tissues in the Visible Human
dataset. Level sets of probabilities can be applied
in segmentation of three dimensional MR images as
shown in Fig. 6. Experiments and comparisons have
demonstrated the effectiveness of our method.
ACKNOWLEDGMENTS
This work was partially supported by National Natu-
ral Science Foundation of China (NSFC) (61202255).
REFERENCES
Aboitiz, F., Scheibel, A. B., Fisher, R. S., and Zaidel, E.
(1992). Fiber composition of the human corpus callo-
sum. Brain Research, 598(1-2):143–153.
Basser, P. J., Pajevic, S., Pierpaoli, C., Duda, J., and Al-
droubi, A. (2000). In vivo fiber tractography using dt-
mri data. Magnetic Resonance in Medicine, 44:354–
363.
Boykov, Y. and Jolly, M. (2001). Interactive graph cuts for
optimal boundary and region segmentation of objects
in n-d images. In Intl. Conf. Computer Vision, vol-
ume I, pages 105–112.
Cobzas, D., Birkbeck, N., Schmidt, M., and Jagersand, M.
(2007). 3d variational brain tumor segmentation using
a high dimensional feature set. In Proceedings of the
International Conference on Computer Vision, pages
1–8. IEEE.
Friedman, J., Hastie, T., and Tibshirani, R. (2000). Additive
logistic regression: a statistical view of boosting. The
Annals of Statistics, 28(2):337–407.
Hadwiger, M., Kniss, J. M., Rezk-salama, C., Weiskopf, D.,
and Engel, K. (2006). Real-time Volume Graphics. A.
K. Peters, first edition.
Holtzman-Gazit, M., Kimmel, R., Peled, N., and Goldsher,
D. (2006). Segmentation of thin structures in volu-
metric medical images. IEEE Transaction on Image
Processing, 15(2):354–363.
Liu, Y. and Yu, Y. (2012). Interactive image segmentation
based on level sets of probabilities. IEEE Transaction
on Visualization and Computer Graphics, 18(2):202–
213.
Manjunath, B. and Ma, W. (1996). Texture features for
browsing and retrieval of image data. IEEE Trans-
actions on Pattern Analysis and Machine Intelligence,
18(8):837–842.
Mori, S. and van Zijl, P. C. M. (2002). Fiber tracking: prin-
ciples and strategies - a technical review. NMR IN
BIOMEDICINE, 15:468–480.
Osher, S. J. and Fedkiw, R. P. (2003). Level Set Methods
and Dynamic Implicit Surfaces. Springer-Verlag, first
edition.
Paragios, N. and Deriche, R. (1999). Geodesic active re-
gions for supervised texture segmentation. In Pro-
ceedings of the International Conference on Computer
Vision, volume 2, pages 926–932. IEEE.
Peng, D., Merriman, B., Osher, S., Zhao, H., and Kang,
M. (1999). A pde-based fast local level set method.
Journal of Computational Physics, 155(2):410–438.
Pham, D. L., Xu, C., and Prince, J. L. (2000). Current meth-
ods in medical image segmentation. Annual Review of
Biomedical Engineering, 2:315–337.
Press, W. H., Saul A. Teukolsky, W. T. V., and Flannery,
B. P. (2002). Numerical recipes in C++: the art of sci-
entific computing. Cambridge University Press,New
York, second edition.
Schroeder, W., Martin, K., and Lorensen, B. (2004). The
Visualization Toolkit. Kitware Inc., third edition.
Sethian, J. (1999). Level Set Methods and Fast Marching
Methods. Cambridge University Press.
Tu, Z., Narr, K. L., Dollar, P., Dinov, I., Thompson, P. M.,
and Toga, A. W. (2008). Brain anatomical struc-
ture segmentation by hybrid discriminative/generative
models. IEEE Transactions on Medical Imaging,
27(4):495–508.
VISAPP2013-InternationalConferenceonComputerVisionTheoryandApplications
394