Advertisement

Automatic Liver Lesion Segmentation in CT Combining Fully Convolutional Networks and Non-negative Matrix Factorization

  • Shenhai Zheng
  • Bin FangEmail author
  • Laquan Li
  • Mingqi Gao
  • Yi Wang
  • Kaiyi Peng
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 10549)

Abstract

Automatic liver tumor segmentation is an important step towards digital medical research, clinical diagnosis and therapy planning. However, the existence of noise, low contrast and heterogeneity make the automatic liver tumor segmentation remaining an open challenge. In this work, we focus on a novel automatic method to segment liver tumor in abdomen images from CT scans by using fully convolutional networks (FCN) and non-negative matrix factorization (NMF). We train the FCN for semantic liver and tumor segmentation. The segmented liver and tumor regions of FCN are used as ROI and initialization for the NMF based tumor refinement, respectively. We refine the surfaces of tumors using a 3D deformable model which derived from NMF and driven by local cumulative spectral histograms (LCSH). The refinement is designed to obtain a smoother, more accurate and natural liver tumor surface. Experiments demonstrated that the proposed segmentation method achieves satisfactory results. Likewise, it has been notably observed that the computing time of the segmentation method is no more than one minute for each CT volume.

Keywords

Liver lesion FCN Non-negative matrix factorization Local cumulative spectral histograms Segmentation 

Notes

Acknowledgments

This research is sponsored by the National Natural Science Foundation of China (61472053, 91420102), Major Program of National Natural Science Foundation of China (No. 61190122), National Key Technology R&D Program of China (No. 2012BAI06B01).

References

  1. 1.
    Becker, M., Magnenat-Thalmann, N.: Deformable models in medical image segmentation. In: Magnenat-Thalmann, N., Ratib, O., Choi, H.F. (eds.) 3D Multiscale Physiological Human, pp. 81–106. Springer, London (2014). doi: 10.1007/978-1-4471-6275-9_4 CrossRefGoogle Scholar
  2. 2.
    Chan, T.F., Esedoglu, S., Nikolova, M.: Algorithms for finding global minimizers of image segmentation and denoising models. SIAM J. Appl. Math. 66(5), 1632–1648 (2006)MathSciNetCrossRefzbMATHGoogle Scholar
  3. 3.
    Chen, B., Chen, Y., Yang, G., Meng, J., Zeng, R., Luo, L.: Segmentation of liver tumor via nonlocal active contours. In: 2015 IEEE International Conference on Image Processing (ICIP), pp. 3745–3748. IEEE (2015)Google Scholar
  4. 4.
    Christ, P.F., et al.: Automatic liver and lesion segmentation in CT using cascaded fully convolutional neural networks and 3D conditional random fields. In: Ourselin, S., Joskowicz, L., Sabuncu, M.R., Unal, G., Wells, W. (eds.) MICCAI 2016. LNCS, vol. 9901, pp. 415–423. Springer, Cham (2016). doi: 10.1007/978-3-319-46723-8_48 CrossRefGoogle Scholar
  5. 5.
    Gao, M., Chen, H., Zheng, S., Fang, B.: A factorization based active contour model for texture segmentation. In: 2016 IEEE International Conference on Image Processing (ICIP), pp. 4309–4313. IEEE (2016)Google Scholar
  6. 6.
    Göçeri, E.: Fully automated liver segmentation using sobolev gradient-based level set evolution. Int. J. Numeri. Methods Biomed. Eng. 32(11) (2016)Google Scholar
  7. 7.
    Goldstein, T., Osher, S.: The split bregman method for l1-regularized problems. SIAM J. Imaging Sci. 2(2), 323–343 (2009)MathSciNetCrossRefzbMATHGoogle Scholar
  8. 8.
    Götz, M., Heim, E., März, K., Norajitra, T., Hafezi, M., Fard, N., Mehrabi, A., Knoll, M., Weber, C., Maier-Hein, L., Maier-Hein, K.H.: A learning-based, fully automatic liver tumor segmentation pipeline based on sparsely annotated training data. In: Medical Imaging 2016: Image Processing (2016)Google Scholar
  9. 9.
    Heimann, T., Van Ginneken, B., Styner, M.A., Arzhaeva, Y., Aurich, V., Bauer, C., Beck, A., Becker, C., Beichel, R., Bekes, G.: Comparison and evaluation of methods for liver segmentation from CT datasets. IEEE Trans. Med. Imaging 28(8), 1251–1265 (2009)CrossRefGoogle Scholar
  10. 10.
    Krinidis, S., Chatzis, V.: A robust fuzzy local information C-means clustering algorithm. IEEE Trans. Image Process. 19(5), 1328–1337 (2010)MathSciNetCrossRefzbMATHGoogle Scholar
  11. 11.
    Li, B.N., Chui, C.K., Chang, S., Ong, S.H.: A new unified level set method for semi-automatic liver tumor segmentation on contrast-enhanced CT images. Expert Syst. Appl. 39(10), 9661–9668 (2012)CrossRefGoogle Scholar
  12. 12.
    Patil, D.D., Deore, S.G.: Medical image segmentation: a review. Int. J. Comput. Sci. Mob. Comput. 2(1), 22–27 (2013)Google Scholar
  13. 13.
    Shelhamer, E., Long, J., Darrell, T.: Fully convolutional networks for semantic segmentation. IEEE Trans. Pattern Anal. Mach. Intell. 39(4), 640–651 (2017)CrossRefGoogle Scholar
  14. 14.
    Shen, D., Wu, G., Suk, H.I.: Deep learning in medical image analysis. Ann. Rev. Biomed. Eng. 19, 221–248 (2017)CrossRefGoogle Scholar
  15. 15.
    Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. CoRR abs/1409.1556 (2014)Google Scholar
  16. 16.
    Yuan, J., Wang, D., Cheriyadat, A.M.: Factorization-based texture segmentation. IEEE Trans. Image Process. 24(11), 3488–3497 (2015)MathSciNetCrossRefGoogle Scholar
  17. 17.
    Zhang, K., Zhang, L., Lam, K.M., Zhang, D.: A level set approach to image segmentation with intensity inhomogeneity. IEEE Trans. Cybernet. 46(2), 546–557 (2016)CrossRefGoogle Scholar

Copyright information

© Springer International Publishing AG 2017

Authors and Affiliations

  • Shenhai Zheng
    • 1
  • Bin Fang
    • 1
    Email author
  • Laquan Li
    • 2
  • Mingqi Gao
    • 1
  • Yi Wang
    • 1
  • Kaiyi Peng
    • 1
  1. 1.College of Computer ScienceChongqing UniversityChongqingChina
  2. 2.School of AutomationHuazhong University of Science and TechnologyWuhanChina

Personalised recommendations