Advertisement

Deep Learning-Based Landmark Localisation in the Liver for Couinaud Segmentation

Conference paper
  • 158 Downloads
Part of the Lecture Notes in Computer Science book series (LNCS, volume 12722)

Abstract

Couinaud segmenation, which divides the liver into functional regions, is the most widely used functional anatomy of the liver and is important for surgical planning and lesion monitoring. Couinaud segmentation can be a time-consuming task, thereby necessitating automated methods. In this study, we propose a deep learning approach for automatically defining Couinaud segments 2 to 8, based on a novel application of automatic landmark localisation. We utilise a heatmap regression CNN to predict landmark locations in the liver, which can subsequently be used to derive the planes that divide the liver into Couinaud segments. A novel postprocessing step for reducing false-positive peaks in heatmaps and/or aiding quality control is also presented. We apply our approach to non-contrast T1-weighted MRI data and compare the accuracy of the derived segments to those obtained directly from a semantic segmentation network. We show that the approach we propose can match and potentially outperform the direct segmentation approach, and thus can be a good alternative option for automatic Couinaud segmentation.

Keywords

Deep learning Landmark localisation Heatmap regression Couinaud segmentation Liver segmenation CNN 

References

  1. 1.
    Couinaud, C.: Le foie; études anatomiques et chirurgicales. Masson, Paris, France (1957)Google Scholar
  2. 2.
    Germain, T., Favelier, S., Cercueil, J.P., Denys, A., Krausé, D., Guiu, B.: Liver segmentation: practical tips. Diagn. Interv. Imaging 95(11), 1003–1016 (2014)CrossRefGoogle Scholar
  3. 3.
    Huang, S., Wang, B., Cheng, M., Wu, W., Huang, X., Ju, Y.: A fast method to segment the liver according to Couinaud’s classification. In: Gao, X., Müller, H., Loomes, M.J., Comley, R., Luo, S. (eds.) MIMI 2007. LNCS, vol. 4987, pp. 270–276. Springer, Heidelberg (2008).  https://doi.org/10.1007/978-3-540-79490-5_33CrossRefGoogle Scholar
  4. 4.
    Liao, H., Mesfin, A., Luo, J.: Joint vertebrae identification and localization in spinal CT images by combining short- and long-range contextual information. IEEE Trans. Med. Imaging 37(5), 1266–1275 (2018)CrossRefGoogle Scholar
  5. 5.
    Mole, D.J., et al.: Study protocol: HepaT1ca - an observational clinical cohort study to quantify liver health in surgical candidates for liver malignancies. BMC Cancer 18(1), 890 (2018)CrossRefGoogle Scholar
  6. 6.
    Oliveira, D.A., Feitosa, R.Q., Correia, M.M.: Segmentation of liver, its vessels and lesions from CT images for surgical planning. BioMed. Eng. Online 10, 30 (2011)CrossRefGoogle Scholar
  7. 7.
    Owler, J., Irving, B., Ridgeway, G., Wojciechowska, M., McGonigle, J., Brady, S.M.: Comparison of multi-atlas segmentation and U-Net approaches for automated 3D liver delineation in MRI. In: Zheng, Y., Williams, B.M., Chen, K. (eds.) MIUA 2019. CCIS, vol. 1065, pp. 478–488. Springer, Cham (2020).  https://doi.org/10.1007/978-3-030-39343-4_41CrossRefGoogle Scholar
  8. 8.
    Payer, C., Štern, D., Bischof, H., Urschler, M.: Integrating spatial configuration into heatmap regression based CNNs for landmark localization. Med. Image Anal. 54, 207–219 (2019)CrossRefGoogle Scholar
  9. 9.
    Tian, J., Liu, L., Shi, Z., Xu, F.: Automatic couinaud segmentation from CT volumes on liver using GLC-UNet. In: Suk, H.-I., Liu, M., Yan, P., Lian, C. (eds.) MLMI 2019. LNCS, vol. 11861, pp. 274–282. Springer, Cham (2019).  https://doi.org/10.1007/978-3-030-32692-0_32CrossRefGoogle Scholar
  10. 10.
    Yang, D., et al.: Automatic vertebra labeling in large-scale 3D CT using deep Image-to-Image network with message passing and sparsity regularization. In: Niethammer, M., et al. (eds.) IPMI 2017. LNCS, vol. 10265, pp. 633–644. Springer, Cham (2017).  https://doi.org/10.1007/978-3-319-59050-9_50CrossRefGoogle Scholar
  11. 11.
    Zhang, J., Liu, M., Shen, D.: Detecting anatomical landmarks from limited medical imaging data using two-stage task-oriented deep neural networks. IEEE Trans. Image Process. 26(10), 4753–4764 (2017)MathSciNetCrossRefGoogle Scholar

Copyright information

© Springer Nature Switzerland AG 2021

Authors and Affiliations

  1. 1.Perspectum Ltd.OxfordUK

Personalised recommendations