Advertisement

Deep Small Bowel Segmentation with Cylindrical Topological Constraints

Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 12264)

Abstract

We present a novel method for small bowel segmentation where a cylindrical topological constraint based on persistent homology is applied. To address the touching issue which could break the applied constraint, we propose to augment a network with an additional branch to predict an inner cylinder of the small bowel. Since the inner cylinder is free of the touching issue, a cylindrical shape constraint applied on this augmented branch guides the network to generate a topologically correct segmentation. For strict evaluation, we achieved an abdominal computed tomography dataset with dense segmentation ground-truths. The proposed method showed clear improvements in terms of four different metrics compared to the baseline method, and also showed the statistical significance from a paired t-test.

Keywords

Small bowel segmentation Topological constraint Persistent homology Inner cylinder Abdominal computed tomography 

Notes

Acknowledgments

This research was supported by the National Institutes of Health, Clinical Center and National Cancer Institute.

References

  1. 1.
  2. 2.
    Adcock, A., Rubin, D., Carlsson, G.: Classification of hepatic lesions using the matching metric. Comput. Vis. Image Understand. 121, 36–42 (2014).  https://doi.org/10.1016/j.cviu.2013.10.014CrossRefGoogle Scholar
  3. 3.
    Belchi, F., Pirashvili, M., Conway, J., Bennett, M., Djukanovic, R., Brodzki, J.: Lung topology characteristics in patients with chronic obstructive pulmonary disease. Sci. Rep. 8, 5341 (2018).  https://doi.org/10.1038/s41598-018-23424-0CrossRefGoogle Scholar
  4. 4.
    Çiçek, Ö., Abdulkadir, A., Lienkamp, S.S., Brox, T., Ronneberger, O.: 3D U-Net: learning dense volumetric segmentation from sparse annotation. In: Ourselin, S., Joskowicz, L., Sabuncu, M.R., Unal, G., Wells, W. (eds.) MICCAI 2016. LNCS, vol. 9901, pp. 424–432. Springer, Cham (2016).  https://doi.org/10.1007/978-3-319-46723-8_49CrossRefGoogle Scholar
  5. 5.
    Clough, J.R., Oksuz, I., Byrne, N., Zimmer, V.A., Schnabel, J.A., King, A.P.: A topological loss function for deep-learning based image segmentation using persistent homology. arXiv preprint arXiv:1910.01877 (2019)
  6. 6.
    Fedorov, A., et al.: 3D slicer as an image computing platform for the quantitative imaging network. Magn. Reson. Imaging 30(9), 1323–1341 (2012).  https://doi.org/10.1016/j.mri.2012.05.001CrossRefGoogle Scholar
  7. 7.
    Gabrielsson, R.B., Nelson, B.J., Dwaraknath, A., Skraba, P., Guibas, L.J., Carlsson, G.E.: A topology layer for machine learning. arXiv preprint arXiv:1905.12200 (2019)
  8. 8.
    Hu, X., Li, F., Samaras, D., Chen, C.: Topology-preserving deep image segmentation. Adv. Neural Inf. Process. Syst. 32, 5657–5668 (2019)Google Scholar
  9. 9.
    Loshchilov, I., Hutter, F.: Decoupled weight decay regularization. In: International Conference on Learning Representations (2019)Google Scholar
  10. 10.
    Murphy, K.P., McLaughlin, P.D., O’Connor, O.J., Maher, M.M.: Imaging the small bowel. Curr. Opinion Gastroenterol. 30(2), 134–140 (2014)CrossRefGoogle Scholar
  11. 11.
    Oda, H., et al.: Visualizing intestines for diagnostic assistance of ileus based on intestinal region segmentation from 3D CT images. arXiv preprint arXiv:2003.01290 (2020)
  12. 12.
    Otter, N., Porter, M.A., Tillmann, U., Grindrod, P., Harrington, H.A.: A roadmap for the computation of persistent homology. EPJ Data Sci. 6, 17 (2017).  https://doi.org/10.1140/epjds/s13688-017-0109-5CrossRefGoogle Scholar
  13. 13.
    Ségonne, F., Fischl, B.: Integration of topological constraints in medical image segmentation. In: Paragios, N., Duncan, J., Ayache, N. (eds.) Handbook of Biomedical Imaging, pp. 245–262. Springer, Boston, MA (2015).  https://doi.org/10.1007/978-0-387-09749-7_13CrossRefGoogle Scholar
  14. 14.
    Sudre, C.H., Li, W., Vercauteren, T., Ourselin, S., Jorge Cardoso, M.: Generalised dice overlap as a deep learning loss function for highly unbalanced segmentations. In: Cardoso, M.J., et al. (eds.) DLMIA/ML-CDS -2017. LNCS, vol. 10553, pp. 240–248. Springer, Cham (2017).  https://doi.org/10.1007/978-3-319-67558-9_28CrossRefGoogle Scholar
  15. 15.
    Wu, Y., He, K.: Group normalization. arXiv preprint arXiv:1803.08494 (2018)
  16. 16.
    Zhang, W., et al.: Mesenteric vasculature-guided small bowel segmentation on 3-D CT. IEEE Trans. Med. Imaging 32(11), 2006–2021 (2013).  https://doi.org/10.1109/TMI.2013.2271487

Copyright information

© Springer Nature Switzerland AG 2020

Authors and Affiliations

  1. 1.Imaging Biomarkers and Computer-Aided Diagnosis Laboratory, Radiology and Imaging Sciences, Clinical CenterNational Institutes of HealthBethesdaUSA
  2. 2.Center for Cancer Research, National Cancer InstituteNational Institutes of HealthBethesdaUSA

Personalised recommendations