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.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
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)
Ali, M., Magee, D., Dasgupta, U.: Signal processing overview of ultrasound systems for medical imaging. In: SPRAB12, Texas, pp. 1–27 (2008)
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)
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)
Dhanya, S., Kumari Roshni, V.S.: Comparison of various texture classification methods using multiresolution analysis and linear regression modeling. SpringerPlus 5(1), 54 (2016)
Dice, L.R.: Measures of the amount of ecologic association between species. Ecology 26(3), 297–302 (1945)
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_79
Furuya, M.: Ovarian cancer stroma: pathophysiology and the roles in cancer development. Cancers 4(3), 701–724 (2012)
He, K., Zhang, X., Ren, S., Sun, J.: Deep Residual Learning for Image Recognition. zrXiv (2015)
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)
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)
Kingma, D., Ba, J.: Adam: a method for stochastic optimization. In: International Conference on Learning Representations (2014)
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)
Milletari, F., Navan, N., Ahmadi, S.A.: V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentation. arXiv (2016)
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)
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)
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)
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_28
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)
Veit, A., Wilber, M., Belongie, S.: Residual Networks Behave Like Ensembles of Relatively Shallow Networks, pp. 550–558 (2016)
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”.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2019 Springer Nature Switzerland AG
About this paper
Cite this paper
Carvalho, C. et al. (2019). Deep Learning Approaches for Gynaecological Ultrasound Image Segmentation: A Radio-Frequency vs B-mode Comparison. In: Karray, F., Campilho, A., Yu, A. (eds) Image Analysis and Recognition. ICIAR 2019. Lecture Notes in Computer Science(), vol 11663. Springer, Cham. https://doi.org/10.1007/978-3-030-27272-2_25
Download citation
DOI: https://doi.org/10.1007/978-3-030-27272-2_25
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-27271-5
Online ISBN: 978-3-030-27272-2
eBook Packages: Computer ScienceComputer Science (R0)