Medical & Biological Engineering & Computing

, Volume 55, Issue 1, pp 127–139 | Cite as

Metastatic liver tumour segmentation with a neural network-guided 3D deformable model

  • Eugene Vorontsov
  • An Tang
  • David Roy
  • Christopher J. Pal
  • Samuel Kadoury
Original Article

Abstract

The segmentation of liver tumours in CT images is useful for the diagnosis and treatment of liver cancer. Furthermore, an accurate assessment of tumour volume aids in the diagnosis and evaluation of treatment response. Currently, segmentation is performed manually by an expert, and because of the time required, a rough estimate of tumour volume is often done instead. We propose a semi-automatic segmentation method that makes use of machine learning within a deformable surface model. Specifically, we propose a deformable model that uses a voxel classifier based on a multilayer perceptron (MLP) to interpret the CT image. The new deformable model considers vertex displacement towards apparent tumour boundaries and regularization that promotes surface smoothness. During operation, a user identifies the target tumour and the mesh then automatically delineates the tumour from the MLP processed image. The method was tested on a dataset of 40 abdominal CT scans with a total of 95 colorectal metastases collected from a variety of scanners with variable spatial resolution. The segmentation results are encouraging with a Dice similarity metric of \(0.80 \pm 0.11\) and demonstrates that the proposed method can deal with highly variable data. This work motivates further research into tumour segmentation using machine learning with more data and deeper neural networks.

Keywords

Liver cancer Tumour segmentation CT imaging Multilayer perceptron Deformable surface model 

References

  1. 1.
    Achanta R, Shaji A, Smith K, Lucchi A, Fua P, Ssstrunk S (2010) Slic superpixels. Technical reportGoogle Scholar
  2. 2.
    Baladhandapani A, Nachimuthu DS (2014) Evolutionary learning of spiking neural networks towards quantification of 3D MRI brain tumor tissues. Soft Comput 19(7):1803–1816CrossRefGoogle Scholar
  3. 3.
    Chapiro J, Duran R, Lin M, Schernthaner RE, Wang Z, Gorodetski B, Geschwind JF (2015) Identifying staging markers for hepatocellular carcinoma before transarterial chemoembolization: comparison of three-dimensional quantitative versus nonthree-dimensional imaging markers. Radiology 275(2):438–447CrossRefPubMedGoogle Scholar
  4. 4.
    Cohen AB, Diamant I, Klang E, Amitai M, Greenspan H (2014) Automatic detection and segmentation of liver metastatic lesions on serial CT examinations. In: SPIE Medical Imaging, International Society for Optics and Photonics 903519–903519Google Scholar
  5. 5.
    Cybenko G (1989) Approximation by superpositions of a sigmoidal function. Math Control Signals Syst 2(4):303–314CrossRefGoogle Scholar
  6. 6.
    Dahl G, Sainath T, Hinton G (2013) Improving deep neural networks for LVCSR using rectified linear units and dropout. In: 2013 IEEE international conference on acoustics, speech and signal processing (ICASSP), pp 8609–8613Google Scholar
  7. 7.
    Durst C, Tustison N, Wintermark M, Avants B (2013) Ants and Rboles. In: Proceedings of BRATS Challenge—MICCAIGoogle Scholar
  8. 8.
    Eisenhauer EA, Therasse P, Bogaerts J, Schwartz LH, Sargent D, Ford R, Dancey J, Arbuck S, Gwyther S, Mooney M (2009) New response evaluation criteria in solid tumours: revised RECIST guideline (version 1.1). Eur J Cancer 45(2):228–247CrossRefPubMedGoogle Scholar
  9. 9.
    Hame Y (2008) Liver tumor segmentation using implicit surface evolution. Midas J. http://hdl.handle.net/10380/1440
  10. 10.
    Havaei M, Davy A, Warde-Farley D, Biard A, Courville A, Bengio Y, Pal C, Jodoin PM, Larochelle H (2015) Brain tumor segmentation with deep neural networks. arXiv preprint arXiv:1505.03540
  11. 11.
    Heimann T, Van Ginneken B, Styner M, Arzhaeva Y, Aurich V, Bauer C, Beck A, Becker C, Beichel R, Bekes G et al (2009) Comparison and evaluation of methods for liver segmentation from ct datasets. IEEE Trans Med Imaging 28(8):1251–1265CrossRefPubMedGoogle Scholar
  12. 12.
    Hochreiter S (1998) The vanishing gradient problem during learning recurrent neural nets and problem solutions. Int J Uncertain Fuzziness Knowl Based Syst 6(02):107–116CrossRefGoogle Scholar
  13. 13.
    Huang M, Yang W, Wu Y, Jiang J, Chen W, Feng Q (2014) Brain tumor segmentation based on local independent projection-based classification. IEEE Trans Biomed Eng 61(10):2633–2645CrossRefPubMedGoogle Scholar
  14. 14.
    Kadoury S, Vorontsov E, Tang A (2015) Metastatic liver tumour segmentation from discriminant grassmannian manifolds. Phys Med Biol 60(16):6459CrossRefPubMedGoogle Scholar
  15. 15.
    Kainmueller D, Lamecker H, Heller MO, Weber B, Hege HC, Zachow S (2013) Omnidirectional displacements for deformable surfaces. Med Image Anal 17(4):429–441CrossRefPubMedGoogle Scholar
  16. 16.
    Khotanlou H, Colliot O, Atif J, Bloch I (2009) 3D brain tumor segmentation in MRI using fuzzy classification, symmetry analysis and spatially constrained deformable models. Fuzzy Sets Syst 160(10):1457–1473CrossRefGoogle Scholar
  17. 17.
    Krizhevsky A, Sutskever I, Hinton GE (2012) ImageNet classification with deep convolutional neural networks. In: Pereira F, Burges CJC, Bottou L, Weinberger KQ (eds) Advances in neural information processing systems 25. Curran Associates Inc, Red Hook, pp 1097–1105Google Scholar
  18. 18.
    Nair V, Hinton GE (2010) Rectified linear units improve restricted boltzmann machines. In: Proceedings of the 27th international conference on machine learning (ICML-10), pp 807–814Google Scholar
  19. 19.
    Plaut DC, Hinton GE (1987) Learning sets of filters using back-propagation. Comput Speech Lang 2(1):35–61CrossRefGoogle Scholar
  20. 20.
    Qi Y, Xiong W, Leow WK, Tian Q, Zhou J, Liu J, Han T, Venkatesh SK, Wang SC (2008) Semi-automatic segmentation of liver tumors from CT scans using Bayesian rule-based 3d region growing. In: MICCAI Workshop, vol 41, pp 201Google Scholar
  21. 21.
    Rajendran A, Dhanasekaran R (2012) Fuzzy clustering and deformable model for tumor segmentation on MRI brain image: a combined approach. Procedia Eng 30:327–333CrossRefGoogle Scholar
  22. 22.
    Stawiaski J, Decenciere E, Bidault F (2008) Interactive liver tumor segmentation using graph-cuts and watershed. In: Workshop on 3D segmentation in the clinic: a grand challenge II. Liver tumor segmentation challenge. MICCAI, New York, USAGoogle Scholar
  23. 23.
    Vorontsov E, Abi-Jaoudeh N, Kadoury S (2014) Metastatic liver tumor segmentation using texture-based omni-directional deformable surface models. In: Yoshida H, Nppi JJ, Saini S (ed) Abdominal imaging. Computational and clinical applications. Number 8676 in Lecture Notes in Computer Science. Springer International Publishing, pp 74–83Google Scholar

Copyright information

© International Federation for Medical and Biological Engineering 2016

Authors and Affiliations

  • Eugene Vorontsov
    • 1
  • An Tang
    • 2
    • 3
  • David Roy
    • 1
  • Christopher J. Pal
    • 1
  • Samuel Kadoury
    • 1
    • 4
  1. 1.École Polytechnique de MontréalMontrealCanada
  2. 2.Centre de recherche du Centre hospitalier de l’Université de Montréal (CRCHUM)MontrealCanada
  3. 3.Department of Radiology, Radio-oncology and Nuclear MedicineCentre hospitalier de l’Université de Montréal (CHUM)MontrealCanada
  4. 4.CHU Sainte-Justine Research CenterMontrealCanada

Personalised recommendations