Advertisement

Pelvis Segmentation Using Multi-pass U-Net and Iterative Shape Estimation

  • Chunliang WangEmail author
  • Bryan Connolly
  • Pedro Filipe de Oliveira Lopes
  • Alejandro F. Frangi
  • Örjan Smedby
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11404)

Abstract

In this report, an automatic method for segmentation of the pelvis in three-dimensional (3D) computed tomography (CT) images is proposed. The method is based on a 3D U-net which has as input the 3D CT image and estimated volumetric shape models of the targeted structures and which returns the probability maps of each structure. During training, the 3D U-net is initially trained using blank shape context inputs to generate the segmentation masks, i.e. relying only on the image channel of the input. The preliminary segmentation results are used to estimate a new shape model, which is then fed to the same network again, with the input images. With the additional shape context information, the U-net is trained again to generate better segmentation results. During the testing phase, the input image is fed through the same 3D U-net multiple times, first with blank shape context channels and then with iteratively re-estimated shape models. Preliminary results show that the proposed multi-pass U-net with iterative shape estimation outperforms both 2D and 3D conventional U-nets without the shape model.

Keywords

Deep learning Multi-pass U-net Pelvis segmentation Shape context Statistic shape model 

Notes

Acknowledgements

This study was supported by the Swedish Heart-lung foundation (grant no. 20160609), Swedish Medtech4Health AIDA research grant, and the Swedish Childhood Cancer Foundation (grant no. MT2016-00166).

References

  1. 1.
    Seim, H., Kainmüller, D., Heller, M., Lamecker, H., Zachow, S., Hege, H.C.: Automatic segmentation of the pelvic bones from CT data based on a statistical shape model. In: Proceedings 1st Eurographics Conference on Visual Computing for Biomedicine - EG VCBM 2008, pp. 93–100 (2008).  https://doi.org/10.2312/VCBM/VCBM08/093-100
  2. 2.
    Kang, Y., Engelke, K., Kalender, W.: A new accurate and precise 3-D segmentation method for skeletal structures in volumetric CT data. IEEE Trans. Med. Imaging 22(5), 586–598 (2003).  https://doi.org/10.1109/TMI.2003.812265CrossRefGoogle Scholar
  3. 3.
    Chu, C., Chen, C., Liu, L., Zheng, G.: FACTS: fully automatic CT segmentation of a hip joint. Ann. Biomed. Eng. 43(5), 1247–1259 (2015).  https://doi.org/10.1007/s10439-014-1176-4CrossRefGoogle Scholar
  4. 4.
    Chu, C., Bai, J., Wu, X., Zheng, G.: MASCG: multi-atlas segmentation constrained graph method for accurate segmentation of hip CT images. Med. Image Anal. 26(1), 173–184 (2015).  https://doi.org/10.1016/j.media.2015.08.011CrossRefGoogle Scholar
  5. 5.
    Long, J., Shelhamer, E., Darrell, T.: Fully convolutional networks for semantic segmentation. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition - CVPR 2015, pp. 3431–3440. IEEE (2015).  https://doi.org/10.1109/CVPR.2015.7298965
  6. 6.
    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
  7. 7.
    Yokota, F., Okada, T., Takao, M., Sugano, N., Tada, Y., Sato, Y.: Automated segmentation of the femur and pelvis from 3D CT data of diseased hip using hierarchical statistical shape model of joint structure. In: Yang, G.-Z., Hawkes, D., Rueckert, D., Noble, A., Taylor, C. (eds.) MICCAI 2009. LNCS, vol. 5762, pp. 811–818. Springer, Heidelberg (2009).  https://doi.org/10.1007/978-3-642-04271-3_98CrossRefGoogle Scholar
  8. 8.
    Wang, C., Smedby, Ö.: Automatic whole heart segmentation using deep learning and shape context. In: Pop, M., et al. (eds.) STACOM 2017. LNCS, vol. 10663, pp. 242–249. Springer, Cham (2018).  https://doi.org/10.1007/978-3-319-75541-0_26CrossRefGoogle Scholar
  9. 9.
    Johnson, C., et al.: Accuracy of CT colonography for detection of large adenomas and cancers. N. Engl. J. Med. 359(12), 1207–1217 (2008).  https://doi.org/10.1056/NEJMoa0800996CrossRefGoogle Scholar
  10. 10.
    Roth, H.R., et al.: A new 2.5D representation for lymph node detection using random sets of deep convolutional neural network observations. In: Golland, P., Hata, N., Barillot, C., Hornegger, J., Howe, R. (eds.) MICCAI 2014. LNCS, vol. 8673, pp. 520–527. Springer, Cham (2014).  https://doi.org/10.1007/978-3-319-10404-1_65CrossRefGoogle Scholar
  11. 11.
    Yushkevich, P., et al.: User-guided 3D active contour segmentation of anatomical structures: significantly improved efficiency and reliability. Neuroimage 31(3), 1116–1128 (2006).  https://doi.org/10.1016/j.neuroimage.2006.01.015CrossRefGoogle Scholar
  12. 12.
    Leventon, M., Grimson, W., Faugeras, O.: Statistical shape influence in geodesic active contours. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition - CVPR 2000, pp. 316–323. IEEE (2000).  https://doi.org/10.1109/CVPR.2000.855835
  13. 13.
    Wang, C., Smedby, Ö.: Automatic multi-organ segmentation in non-enhanced CT datasets using hierarchical shape priors. In: Proceedings of 22nd International Conference on Pattern Recognition - ICPR 2014, pp. 3327–3332. IEEE (2014).  https://doi.org/10.1109/ICPR.2014.574

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  • Chunliang Wang
    • 1
    Email author
  • Bryan Connolly
    • 2
  • Pedro Filipe de Oliveira Lopes
    • 3
  • Alejandro F. Frangi
    • 3
  • Örjan Smedby
    • 1
  1. 1.Department of Biomedical Engineering and Health SystemsKTH Royal Institute of TechnologyStockholmSweden
  2. 2.Radiology DepartmentKarolinska InstituteSolnaSweden
  3. 3.Center for Computational Imaging and Simulation Technologies in BiomedicineThe University of SheffieldSheffieldUK

Personalised recommendations