Interactive Medical Image Segmentation Method with only Positive Label Examples

Abstract:

In this paper, a novel interactive medical image segmentation method called SMOPL is proposed. This method only needs marking some pixels on foreground region for segmentation. To do this, SMOPL characterize the inherent correlations among foreground and background pixels as Hilbert-Schmidt independence. By maximizing the independence and minimizing the smoothness of labels on instance neighbor graph simultaneously, SMOPL gets the sufficiently smooth confidences of both positive and negative classes in absence of negative training examples. Then a image segmentation can be obtained by assigning each pixel to the label for which the greatest confidence is calculated. Experiments on real-world medical images show that SMOPL is robust to get a high-quality segmentation with only positive label examples.

• Periodical: Advanced Materials Research (Volumes 989-994)
• Pages: 1088-1092
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.989-994.1088
• Online since: July 2014
• Authors: Chen Guang Zhang, Yan Zhang*, Xia Huan Zhang
• Keywords: Graph Based Learning, Interactive Image Segmentation, Smoothness Constraint

References

[1] B.N. Li, et al. Computers in Biology and Medicine. Vol. 41(2011), pp.1-10.

[2] C. MCINTOSH, et al. Medical Imaging, IEEE Transactions on. Vol. 31(2012), pp.33-50.

[3] A.A. Qazi, V. Pekar, et al. Medical physics. Vol. 38(11)(2011), pp.6160-6170.

[4] H. W. Kang, S.Y. Shin. Graphical Models. Vol. 64(5)(2002), pp.282-303.

[5] F. Zhao, X. H Xie. Annals of the BMVA. Vol. 7(2013), pp.1-22.

[6] L. Grady. IEEE Transactions on Pattern Analysis and Machine Intelligence. Vol. 28(11)(2006), pp.1768-1783.

[7] S. Andrews, G. Hamarneh，A. Saad, in: Proceedings of the 13th International Conference on Medical Image Computing and Computer assisted Intervention: Part III, edited by T.Z. Jiang, et al. Publications/ Springer Verlag, Berlin, German(2010).

[8] Y. Li, J. Sun，et al. ACM Transactions on Graphics. Vol. 23(3)(2004)，pp.303-308.

[9] A. Gretton, B. Bousquet, et al, In: 16th International Conference on Algorithmic Learning Theory. Edited by S. Jian Publications/Springer Verlag, Berlin (2005), pp.63-77.

[10] L. Song, A. Smola, et al. In: Proceedings of the 24th international conference on Machine learning, edited by Zoubin Publication/ACM, USA(2007), pp.815-822.

[11] B. Schölkopf, R. C. Williamson, et al, in: Advances in Neural Information Processing Systems 12, Edited by S.A. Solla, T.K. Leen and K.R. MüllerDenver, Publication/Cambridge MA, USA(1999), pp.582-588.

[12] W.K. Li, Q.H. Guo. Geoscience and Remote Sensing, IEEE Transactions on. Vol. 49(2)(2011), pp.717-725.