Advertisement

Deep Learning Based Rib Centerline Extraction and Labeling

  • Matthias Lenga
  • Tobias Klinder
  • Christian Bürger
  • Jens von Berg
  • Astrid Franz
  • Cristian Lorenz
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11404)

Abstract

Automated extraction and labeling of rib centerlines is a typically needed prerequisite for more advanced assisted reading tools that help the radiologist to efficiently inspect all 24 ribs in a computed tomography (CT) volume. In this paper, we combine a deep learning-based rib detection with a dedicated centerline extraction algorithm applied to the detection result for the purpose of fast, robust and accurate rib centerline extraction and labeling from CT volumes. More specifically, we first apply a fully convolutional neural network to generate a probability map for detecting the first rib pair, the twelfth rib pair, and the collection of all intermediate ribs. In a second stage, a newly designed centerline extraction algorithm is applied to this multi-label probability map. Finally, the distinct detection of first and twelfth rib separately, allows to derive individual rib labels by simple sorting and counting the detected centerlines. We applied our method to CT volumes with an isotropic voxel spacing of 1.5 mm from 113 patients which included a variety of different challenges and achieved a mean centerline accuracy of 0.723 mm with respect to manual centerline annotations. The presented approach can be applied to similar tracing problems, such as detecting the spinal column centerline.

Keywords

Rib segmentation Centerline tracing Deep learning Fully convolutional neural networks Whole-body CT scans Trauma 

References

  1. 1.
    Tobon-Gomez, C., et al.: Unfolded cylindrical projection for rib fracture diagnosis. In: Glocker, B., Yao, J., Vrtovec, T., Frangi, A., Zheng, G. (eds.) MSKI 2017. LNCS, vol. 10734, pp. 36–47. Springer, Cham (2018).  https://doi.org/10.1007/978-3-319-74113-0_4CrossRefGoogle Scholar
  2. 2.
    Wu, D., et al.: A learning based deformable template matching method for automatic rib centerline extraction and labeling in CT images. In: Proceedings of 2012 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2012, pp. 980–987. IEEE (2012).  https://doi.org/10.1109/CVPR.2012.6247774
  3. 3.
    Shen, H., Liang, L., Shao, M., Qing, S.: Tracing based segmentation for the labeling of individual rib structures in chest CT volume data. In: Barillot, C., Haynor, D.R., Hellier, P. (eds.) MICCAI 2004. LNCS, vol. 3217, pp. 967–974. Springer, Heidelberg (2004).  https://doi.org/10.1007/978-3-540-30136-3_117CrossRefGoogle Scholar
  4. 4.
    Lee, J., Reeves, A.: Segmentation of individual ribs from low-dose chest CT. In: Karssemeijer, N., Summers, R. (eds.) Proceedings of SPIE Medical Imaging 2010: Computer Aided Diagnosis, vol. 7624, p. 76243J. SPIE (2010).  https://doi.org/10.1117/12.844565
  5. 5.
    Staal, J., van Ginneken, B., Viergever, M.: Automatic ribsegmentation and labeling in computed tomography scans using ageneral framework for detection, recognition and segmentation ofobjects in volumetric data. Med. Image Anal. 11(1), 35–46 (2006).  https://doi.org/10.1016/j.media.2006.10.001CrossRefGoogle Scholar
  6. 6.
    Klinder, T., Lorenz, C., von Berg, J., Dries, S.P.M., Bülow, T., Ostermann, J.: Automated model-based rib cage segmentation and labeling in CT images. In: Ayache, N., Ourselin, S., Maeder, A. (eds.) MICCAI 2007. LNCS, vol. 4792, pp. 195–202. Springer, Heidelberg (2007).  https://doi.org/10.1007/978-3-540-75759-7_24CrossRefGoogle Scholar
  7. 7.
    Brosch, T., Saalbach, A.: Foveal fully convolutional nets for multi-organ segmentation. In: Angelini, E., Landman, B. (eds.) Proceedings of SPIE Medical Imaging 2018: Image Processing, vol. 10574, p. 105740U. SPIE (2018).  https://doi.org/10.1117/12.2293528
  8. 8.
    Zeiler, M.: ADADELTA: an adaptive learning rate method. arXiv:1212.5701 (2012)

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  • Matthias Lenga
    • 1
  • Tobias Klinder
    • 1
  • Christian Bürger
    • 1
  • Jens von Berg
    • 1
  • Astrid Franz
    • 1
  • Cristian Lorenz
    • 1
  1. 1.Philips Research EuropeHamburgGermany

Personalised recommendations