Advertisement

Automatic bone segmentation in whole-body CT images

  • André KleinEmail author
  • Jan Warszawski
  • Jens Hillengaß
  • Klaus H. Maier-Hein
Original Article
  • 191 Downloads

Abstract

Purpose

Many diagnostic or treatment planning applications critically depend on the successful localization of bony structures in CT images. Manual or semiautomatic bone segmentation is tedious, however, and often not practical in clinical routine. In this paper, we present a reliable and fully automatic bone segmentation in whole-body CT scans of patients suffering from multiple myeloma.

Methods

We address this problem by using convolutional neural networks with an architecture inspired by the U-Net [17]. In this publication, we compared three training procedures: (1) training from 2D axial slices, (2) a pseudo-3D approach including axial, sagittal and coronal slices and (3) an approach where the network is pre-trained in an unsupervised manner.

Results

We evaluated the method on an in-house dataset of 18 whole-body CT scans consisting of 6800 axial slices, achieving a dice score of 0.95 and an intersection over union (IOU) of 0.91. Furthermore, we evaluated our method on the dataset used by Peréz-Carrasco et al. (Comput Methods Progr Biomed 156:85–95, 2018). The data and the ground truth have been made publicly available. The proposed method outperformed the other methods, obtaining a dice score of 0.92 and an IOU of 0.85.

Conclusion

These promising results could facilitate the evaluation of bone density and the localization of focal lesions in the future, with a potential impact on both disease staging and treatment planning.

Keywords

Bone segmentation U-Net Deep learning Computed tomography Multiple myeloma 

Notes

Acknowledgements

This research was supported by the International Myeloma Foundation.

Compliance with ethical standards

Conflict of interest

The authors declare that they have no conflict of interest.

Ethical standard

All procedures performed in studies involving human participants were in accordance with the ethical standards of the institutional and/or national research committee and with the 1964 Helsinki Declaration and its later amendments or comparable ethical standards.

Informed consent

Informed consent was obtained from all individual participants included in the study.

References

  1. 1.
    Bae E, Yuan J, Tai XC (2011) Global minimization for continuous multiphase partitioning problems using a dual approach. Int J Comput Vis 92(1):112–129CrossRefGoogle Scholar
  2. 2.
    Buie HR, Campbell GM, Klinck RJ, MacNeil JA, Boyd SK (2007) Automatic segmentation of cortical and trabecular compartments based on a dual threshold technique for in vivo micro-ct bone analysis. Bone 41(4):505–515CrossRefGoogle Scholar
  3. 3.
    Chang HH, Zhuang AH, Valentino DJ, Chu WC (2009) Performance measure characterization for evaluating neuroimage segmentation algorithms. Neuroimage 47(1):122–135CrossRefGoogle Scholar
  4. 4.
    Clarke B (2008) Normal bone anatomy and physiology. Clin J Am Soc Nephrol 3(Supplement 3):S131–S139CrossRefGoogle Scholar
  5. 5.
    Erhan D, Bengio Y, Courville A, Manzagol PA, Vincent P, Bengio S (2010) Why does unsupervised pre-training help deep learning? J Mach Learn Res 11(Feb):625–660Google Scholar
  6. 6.
    Hillengass J, Delorme S (2012) Multiples Myelom: Aktuelle Empfehlungen für die Bildgebung. Der Radiologe 52(4):360–365.  https://doi.org/10.1007/s00117-011-2257-0 CrossRefGoogle Scholar
  7. 7.
    Isensee F, Jaeger P, Full PM, Wolf I, Engelhardt S, Maier-Hein KH (2017) Automatic cardiac disease assessment on cine-mri via time-series segmentation and domain specific features. arXiv preprint arXiv:1707.00587
  8. 8.
    Isensee F, Kickingereder P, Wick W, Bendszus M, Maier-Hein KH (2017) Brain tumor segmentation and radiomics survival prediction: contribution to the brats 2017 challenge. In: 2017 International MICCAI BraTS challengeGoogle Scholar
  9. 9.
    Krčah M, Székely G, Blanc R (2011) Fully automatic and fast segmentation of the femur bone from 3d-ct images with no shape prior. In: 2011 IEEE international symposium on biomedical imaging: from nano to macro, pp 2087–2090Google Scholar
  10. 10.
    Litjens G, Kooi T, Bejnordi BE, Setio AAA, Ciompi F, Ghafoorian M, van der Laak JA, van Ginneken B, Sánchez CI (2017) A survey on deep learning in medical image analysis. arXiv preprint arXiv:1702.05747
  11. 11.
    Maas AL, Hannun AY, Ng AY (2013) Rectifier nonlinearities improve neural network acoustic models. In: Proceedings of the ICML, vol 30, p 3Google Scholar
  12. 12.
    Malladi R, Sethian JA, Vemuri BC (1995) Shape modeling with front propagation: a level set approach. IEEE Trans Pattern Anal Mach Intell 17(2):158–175CrossRefGoogle Scholar
  13. 13.
    Nolden M, Zelzer S, Seitel A, Wald D, Müller M, Franz AM, Maleike D, Fangerau M, Baumhauer M, Maier-Hein L, Maier-Hein KH, Meinzer HP, Wolf I (2013) The medical imaging interaction toolkit: challenges and advances. Int J Comput Assist Radiol Surg 8(4):607–620.  https://doi.org/10.1007/s11548-013-0840-8 CrossRefGoogle Scholar
  14. 14.
    Pérez-Carrasco JA, Acha B, Suárez-Mejías C, López-Guerra JL, Serrano C (2018) Joint segmentation of bones and muscles using an intensity and histogram-based energy minimization approach. Comput Methods Progr Biomed 156:85–95CrossRefGoogle Scholar
  15. 15.
    Pérez-Carrasco JA, Acha-Piñero B, Serrano C (2015) Segmentation of bone structures in 3d ct images based on continuous max-flow optimization. Med Imaging Image Process.  https://doi.org/10.1117/12.2082139
  16. 16.
    Pinheiro M, Alves J (2015) A new level-set-based protocol for accurate bone segmentation from ct imaging. IEEE Access 3:1894–1906CrossRefGoogle Scholar
  17. 17.
    Ronneberger O, Fischer P, Brox T (2015) U-net: Convolutional networks for biomedical image segmentation. In: International conference on medical image computing and computer-assisted intervention (MICCAI), pp 234–241Google Scholar
  18. 18.
    Wasserthal J, Neher PF, Maier-Hein KH (2018) Tractseg—fast and accurate white matter tract segmentation. arXiv preprint arXiv:1805.07103
  19. 19.
    Wiehman S, Kroon S, De Villiers H (2016) Unsupervised pre-training for fully convolutional neural networks. In: Pattern Recognition Association of South Africa and robotics and mechatronics international conference (PRASA-RobMech). IEEE, pp 1–6Google Scholar
  20. 20.
    Zhang Y, Matuszewski BJ, Shark LK, Moore CJ (2008) Medical image segmentation usingnew hybrid level-set method. In: Fifth international conference biomedical visualization: information visualization in medical and biomedical informatics. IEEE, pp 71–76Google Scholar

Copyright information

© CARS 2018

Authors and Affiliations

  1. 1.Division of Medical Image ComputingDeutsches Krebsforschungszentrum (DKFZ)HeidelbergGermany
  2. 2.Medical FacultyUniversity of HeidelbergHeidelbergGermany
  3. 3.Department of MedicineRoswell Park Comprehensive Cancer CenterBuffaloUSA

Personalised recommendations