Advertisement

Automatic Image Annotation and Deep Learning for Tooth CT Image Segmentation

  • Miao Gou
  • Yunbo RaoEmail author
  • Minglu Zhang
  • Jianxun Sun
  • Keyang Cheng
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11902)

Abstract

Recently, convolutional networks show great ability dealing with the problem of biomedical imaging, such as tooth image segmentation. In this paper, we propose a novel tooth-based computer tomography (CT) image segmentation approach that integrates U-Net with a level set model. Compared with a single U-Net, our method uses the level set method to build the mask for CT images. This allows automatic annotation in our model, improving the efficiency on image segmentation. Furthermore, we make some changes to the origin U-Net structure for the feasibility to images of any sizes. Using the combination of these two models, our integrated method shows its superiority dealing with problems on tooth image segmentation, outperforming the U-Net or the level set model alone.

Keywords

Image segmentation Automation image annotation Level set U-Net Convolutional networks 

Notes

Acknowledgments

This work was supported in part by the Science and Technology Service Industry project of Sichuan under 2019GFW126, Key R&D project of Sichuan under 2019ZDYF2790.

References

  1. 1.
    Lin, D., Dai, J.F., Jia, J.Y.: ScribbleSup: scribble-supervised convolutional networks for semantic segmentation. In: the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, pp. 3159–3167 (2016)Google Scholar
  2. 2.
    Pathak, D., Krahenbuhl, P., Darrell, T.: Constrained convolutional neural networks for weakly supervised segmentation. In: The IEEE International Conference on Computer Vision (ICCV), Centro Parque Convention Center in Santiago, Chile, pp. 1796–1804 (2015)Google Scholar
  3. 3.
    Papandreou, G., Chen, L.C., Murphy, K.P., Yuille, A.L.: Weakly-and semi-supervised learning of a deep convolutional network for semantic image segmentation. In: The IEEE International Conference on Computer Vision (ICCV), Centro Parque Convention Center in Santiago, Chile, pp. 1742–1750 (2015)Google Scholar
  4. 4.
    Haslhofer, R.: Singularities of mean convex level set flow in general ambient manifolds. Adv. Math. 329, 1137–1155 (2018)MathSciNetCrossRefGoogle Scholar
  5. 5.
    Gibouab, F., Fedkiwc, R., Osher, S.: A review of level-set methods and some recent applications. J. Comput. Phys. 353, 82–109 (2018)MathSciNetCrossRefGoogle Scholar
  6. 6.
    Li, C.M., Xu, C.Y.: Distance regularized level set evolution and its application to image segmentation. IEEE Trans. Image Process. 19(12), 3243–3254 (2010)MathSciNetCrossRefGoogle Scholar
  7. 7.
    Allaire, G., Jouve, F., Michailidis, G.: Thickness control in structural optimization via a level set method. Struct. Multidisc. Optim. 53, 1349–1382 (2016)MathSciNetCrossRefGoogle Scholar
  8. 8.
    Yang, X., Gao, X.B., Tao, D.C., Li, X.L., Li, J.: An efficient MRF embedded level set method for image segmentation. IEEE Trans. Image Process. 24, 9–21 (2014)MathSciNetCrossRefGoogle Scholar
  9. 9.
    Morar, A., Moldoveanu, F., Gröller, E.: Image segmentation based on active contours without edges. In: IEEE 8th International Conference on Intelligent Computer Communication and Processing, Cluj-Napoca, pp. 213–220 (2012)Google Scholar
  10. 10.
    Gan, Y., Xia, Z., Xiong, J., Zhao, Q., Hu, Y., Zhang, J.: Toward accurate tooth segmentation from computed tomography images using a hybrid level set model. Med. Phys. 42(1), 14–27 (2015)CrossRefGoogle Scholar
  11. 11.
    Wang, L., Li, S., Chen, R., Liu, S.Y., Chen, J.C.: A segmentation and classification scheme for single tooth in micro CT images based on 3D level set and K-means++. Comput. Med. Imaging Graph. 57, 19–28 (2017)CrossRefGoogle Scholar
  12. 12.
    Ronneberger, O., Fischer, P., Brox, T.: U-net: convolutional networks for biomedical image segmentation. In: Navab, N., Hornegger, J., Wells, W.M., Frangi, A.F. (eds.) MICCAI 2015. LNCS, vol. 9351, pp. 234–241. Springer, Cham (2015).  https://doi.org/10.1007/978-3-319-24574-4_28CrossRefGoogle Scholar
  13. 13.
    Lu, S., Wang, S., Zhang, Y.: A note on the marker-based watershed method for X-ray image segmentation. Comput. Methods Program. Biomed. 141, 1–2 (2017)CrossRefGoogle Scholar
  14. 14.
    Li, H.W., Andrii, Z.G., Bjoern, M.: Automatic brain structures segmentation using deep residual dilated U-net. arXiv preprint arXiv:1811.04312 (2018)
  15. 15.
    Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)
  16. 16.
    Jung, M.Y., Chan, T.F., Vese, L.A.: Nonlocal Mumford-Shah regularizes for color image restoration. IEEE Trans. Image Process. 20, 1583–1598 (2011)MathSciNetCrossRefGoogle Scholar
  17. 17.
    Ju, W., Xiang, D., Zhang, B.: Random walk and graph cut for co-segmentation of lung tumor on PET-CT Images. IEEE Trans. Image Process. 24, 5854–5867 (2015)MathSciNetCrossRefGoogle Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  • Miao Gou
    • 1
  • Yunbo Rao
    • 1
    Email author
  • Minglu Zhang
    • 1
  • Jianxun Sun
    • 2
  • Keyang Cheng
    • 3
  1. 1.School of Information and Software EngineeringUniversity of Electronic Science and Technology of ChinaChengduPeople’s Republic of China
  2. 2.West China School of StomatologySichuan UniversityChengduPeople’s Republic of China
  3. 3.School of Computer Science and Telecommunications EngineeringJiangsu UniversityZhenjiangPeople’s Republic of China

Personalised recommendations