Advertisement

Deep Learning Approaches for Gynaecological Ultrasound Image Segmentation: A Radio-Frequency vs B-mode Comparison

  • Catarina CarvalhoEmail author
  • Sónia Marques
  • Carla Peixoto
  • Duarte Pignatelli
  • Jorge Beires
  • Jorge Silva
  • Aurélio Campilho
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11663)

Abstract

Ovarian cancer is one of the pathologies with the worst prognostic in adult women and it has a very difficult early diagnosis. Clinical evaluation of gynaecological ultrasound images is performed visually, and it is dependent on the experience of the medical doctor. Besides the dependency on the specialists, the malignancy of specific types of ovarian tumors cannot be asserted until their surgical removal. This work explores the use of ultrasound data for the segmentation of the ovary and the ovarian follicles, using two different convolutional neural networks, a fully connected residual network and a U-Net, with a binary and multi-class approach. Five different types of ultrasound data (from beam-formed radio-frequency to brightness mode) were used as input. The best performance was obtained using B-mode, for both ovary and follicles segmentation. No significant differences were found between the two convolutional neural networks. The use of the multi-class approach was beneficial as it provided the model information on the spatial relation between follicles and the ovary. This study demonstrates the suitability of combining convolutional neural networks with beam-formed radio-frequency data and with brightness mode data for segmentation of ovarian structures. Future steps involve the processing of pathological data and investigation of biomarkers of pathological ovaries.

Keywords

B-mode ultrasound data Beam-formed ultrasound data Image segmentation Neuronal networks Ovarian cancer 

Notes

Acknowledgments

This work is financed by National Funds through the Portuguese funding agency, FCT - Fundação para a Ciência e a Tecnologia as part of project “UID/EEA/50014/2019”.

References

  1. 1.
    Al-Kadi, O.S., Chung, D.Y., Carlisle, R.C., Coussios, C.C., Noble, J.A.: Quantification of ultrasonic texture intra-heterogeneity via volumetric stochastic modeling for tissue characterization. Med. Image Anal. 21(1), 59–71 (2015)CrossRefGoogle Scholar
  2. 2.
    Ali, M., Magee, D., Dasgupta, U.: Signal processing overview of ultrasound systems for medical imaging. In: SPRAB12, Texas, pp. 1–27 (2008)Google Scholar
  3. 3.
    Brand, S., Weiss, E.C., Lemor, R.M., Kolios, M.C.: High frequency ultrasound tissue characterization and acoustic microscopy of intracellular changes. Ultrasound Med. Biol. 34(9), 1396–1407 (2008)CrossRefGoogle Scholar
  4. 4.
    Cigale, B., Zazula, D.: Directional 3D wavelet transform based on gaussian mixtures for the analysis of 3D ultrasound ovarian volumes. IEEE Trans. Pattern Anal. Mach. Intell. 41(1), 64–77 (2019)CrossRefGoogle Scholar
  5. 5.
    Dhanya, S., Kumari Roshni, V.S.: Comparison of various texture classification methods using multiresolution analysis and linear regression modeling. SpringerPlus 5(1), 54 (2016)CrossRefGoogle Scholar
  6. 6.
    Dice, L.R.: Measures of the amount of ecologic association between species. Ecology 26(3), 297–302 (1945)CrossRefGoogle Scholar
  7. 7.
    Wanderley, D.S., et al.: End-to-end ovarian structures segmentation. In: Vera-Rodriguez, R., Fierrez, J., Morales, A. (eds.) CIARP 2018. LNCS, vol. 11401, pp. 681–689. Springer, Cham (2019).  https://doi.org/10.1007/978-3-030-13469-3_79CrossRefGoogle Scholar
  8. 8.
    Furuya, M.: Ovarian cancer stroma: pathophysiology and the roles in cancer development. Cancers 4(3), 701–724 (2012)CrossRefGoogle Scholar
  9. 9.
    He, K., Zhang, X., Ren, S., Sun, J.: Deep Residual Learning for Image Recognition. zrXiv (2015)Google Scholar
  10. 10.
    Hiremath, P.S., Tegnoor, J.R.: automatic detection of follicles in ultrasound images of ovaries by optimal threshoding method. Int. J. Comput. Sci. Inf. Technol. 3(2), 217-2 (2010)Google Scholar
  11. 11.
    Isah, O.R., Usman, A.D., Tekanyi, A.M.: A hybrid model of PSO algorithm and artificial neural network for automatic follicle classification. Int. J. Bioautomation 21(1), 43–58 (2017)Google Scholar
  12. 12.
    Kingma, D., Ba, J.: Adam: a method for stochastic optimization. In: International Conference on Learning Representations (2014)Google Scholar
  13. 13.
    Lenic, M., Zazula, D., Cigale, B.: Segmentation of ovarian ultrasound images using single template cellular neural networks trained with support vector machines. In: Twentieth IEEE International Symposium on Computer-Based Medical Systems (CBMS 2007), pp. 205–212 (2007)Google Scholar
  14. 14.
    Milletari, F., Navan, N., Ahmadi, S.A.: V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentation. arXiv (2016)Google Scholar
  15. 15.
    Olsen, L.O., Takiwaki, H., Serup, J.: High-frequency ultrasound characterization of normal skin. Skin thickness and echographic density of 22 anatomical sites. Skin Res. Technol. 1(2), 74–80 (1995)CrossRefGoogle Scholar
  16. 16.
    Potočnik, B., Cigale, B., Zazula, D.: Computerized detection and recognition of follicles in ovarian ultrasound images: a review. Med. Biol. Eng. Comput. 50(12), 1201–1212 (2012)CrossRefGoogle Scholar
  17. 17.
    Rauh-Hain, J.A., Krivak, T.C., Del Carmen, M.G., Olawaiye, A.B.: Ovarian cancer screening and early detection in the general population. Rev. Obstet. Gynecol. 4(1), 15–21 (2011)Google Scholar
  18. 18.
    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
  19. 19.
    Usman, A.D., Isah, O.R., Tekanyi, A.M.S.: Application of artificial neural network and texture features for follicle detection. Afr. J. Comput. ICT 8(4), 2–9 (2015)Google Scholar
  20. 20.
    Veit, A., Wilber, M., Belongie, S.: Residual Networks Behave Like Ensembles of Relatively Shallow Networks, pp. 550–558 (2016)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  • Catarina Carvalho
    • 1
    Email author
  • Sónia Marques
    • 2
  • Carla Peixoto
    • 3
    • 4
  • Duarte Pignatelli
    • 3
    • 4
  • Jorge Beires
    • 3
  • Jorge Silva
    • 1
    • 2
  • Aurélio Campilho
    • 1
    • 2
  1. 1.INESC TECPortoPortugal
  2. 2.Faculdade de Engenharia da Universidade do PortoPortoPortugal
  3. 3.Centro Hospitalar de São JoãoPortoPortugal
  4. 4.Faculdade de Medicina da Universidade do PortoPortoPortugal

Personalised recommendations