Skip to main content

Advertisement

Log in

3D statistical shape models for automatic segmentation of the fetal cerebellum in ultrasound images

  • Original Paper
  • Published:
Signal, Image and Video Processing Aims and scope Submit manuscript

Abstract

The cerebellum is an important structure to determine fetal development because its volume has a high correlation with gestational age. Manual annotation of the cerebellum in 3D ultrasound images (to measure the cerebellar volume) requires highly trained experts to perform a time-consuming task. To assist in this task, we developed a totally automatic system for the 3D segmentation of the cerebellum in ultrasound images of the fetal brain, using a 3D Point Distribution Model (PDM) obtained from another statistical shape model based on a spherical harmonics (SPHARMs) representation, which provides a very efficient basis for the construction of statistical shape models of 3D organs with a spherical topology. Our PDM of the fetal cerebellum was automatically adjusted with the optimization of an objective function based on gray level voxel profiles, using a genetic algorithm. An automatic initialization and plane selection scheme was also developed, based on the detection of the cerebellum on each plane by a convolutional neural network (YOLO v2). Our results of the 3D segmentation of 18 ultrasound volumes of the fetal brain are: Dice coefficient of 0.83 ± 0.10 and Hausdorff distance of 3.61 ± 0.83 mm. The methods reported show potential to successfully assist the experts in the assessment of fetal growth in ultrasound volumes.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Subscribe and save

Springer+ Basic
$34.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7

Similar content being viewed by others

Data availability

Data available on request to the corresponding author.

References

  1. Ahmadi, S.A., Baust, M., Karamalis, A., Plate, A., Boetzel, K., Klein, T., Navab, N.: Midbrain segmentation in tran-scranial 3D ultrasound for Parkinson diagnosis. In International Conference on Medical Image Computing and Computer-Assisted Intervention (pp. 362–369). Springer, Berlin, Heidelberg. (2011). https://doi.org/10.1007/978-3-642-23626-6_45

  2. Ahmed, A., Alghareb, S., F: A hybrid ROI extraction Approach for Mask and Unmask Facial Recognition System using Light-CNN. Int. J. Comput. Digit. Syst. 16(1), 1223–1232 (2024). https://doi.org/10.12785/ijcds/160190

    Article  MATH  Google Scholar 

  3. de Priscille, D., Clément, M., Lucia, C., Antonio, R., Marilia, Y., Marcos, I., Nina, T.R., Loic, M., Liliane, G., Chao, H., Hongtu, Z.: Muniz Luciana, Shoukri Brandon, Paniagua Beatriz, Styner Martin, Pieper Steve, Budin Francois, Vimort Jean-Baptiste, Pascal Laura, and Prieto Juan Carlos, (2018). A web-based system for neural network based classification in temporomandibular joint osteoarthritis. Comput. Med. Imaging Graph. 67, 45–54. https://doi.org/10.1016/j.compmedimag.2018.04.009

  4. Dice, L.R.: Measures of the amount of ecologic association between species. Ecology. 26(3), 297–302 (1945). https://doi.org/10.2307/1932409

    Article  MATH  Google Scholar 

  5. Edwards, D.A.: The structure of superspace. Studies in topology (pp. 121–133). Academic Press. (1975). https://doi.org/10.1016/B978-0-12-663450-1.50017-7

  6. Fei Liu, Z., Zhang, X., Lin, G., Teng, H., Meng, T., Yu, F., Fang, F., Zang, Z., Li, Shuwei, Liu: Development of the human fetal cerebellum in the second trimester: A postmortem magnetic resonance imaging evaluation. J. Anat. 219(5), 582–588 (2011). https://doi.org/10.1111/j.1469-7580.2011.01418.x

    Article  Google Scholar 

  7. Goldberg, D.E.: Genetic algorithms, Pearson Education, USA. ISBN-10 0201157675. (1989)

  8. Gutiérrez-Becker, B., Arámbula Cosío, F., Huerta, M.E.G., Benavides-Serralde, J.A., Camargo-Marín, L., Bañuelos, V.M.: Automatic segmentation of the fetal cerebellum on ultrasound volumes, using a 3D statistical shape model. Medical Biological Engineering Computing. 51(9), 1021–1030 (2013). https://doi.org/10.1007/s11517-013-1082-1

    Article  MATH  Google Scholar 

  9. Haq, I., Mazhar, T., Asif, R.N., Ghadi, Y.Y., Ullah, N., Khan, M.A., Al-Rasheed, A.: YOLO and residual network for colorectal cancer cell detection and counting. Heliyon. 10(2) (2024). https://doi.org/10.1016/j.heliyon.2024.e24403

  10. Hatab, M.R., Kamourieh, S.W., Twickler, D.M.: MR volume of the fetal cerebellum in relation to growth. Journal of magnetic resonance imaging. Official J. Int. Soc. Magn. Reson. Med. 27(4), 840–845 (2008). https://doi.org/10.1002/jmri.21290

    Article  Google Scholar 

  11. Jordina, T.-B., Gemma, P., Narcís, M., Eduard, G., Elisenda, E., Mario, C.: Segmentation and classification in MRI and US fetal imaging: Recent trends and future prospects. Med. Image. Anal. 51, 61–88 (2019). https://doi.org/10.1016/j.media.2018.10.003 González Ballester Miguel Ángel

  12. Khalili, N., Lessmann, N., Turk, E., Claessens, N., de Heus, R., Kolk, T., Išgum, I.: Automatic brain tissue segmentation in fetal MRI using convolutional neural networks. Magn. Reson. Imaging. 64, 77–89 (2019). https://doi.org/10.1016/j.mri.2019.05.020

    Article  Google Scholar 

  13. Nelder, J.A., Mead, R.: A simplex method for function minimization. Comput. J. 7(4), 308–313 (1965). https://doi.org/10.1093/comjnl/7.4.308

    Article  MathSciNet  MATH  Google Scholar 

  14. Nirmala, S., Palanisamy, V.: Clinical decision support system for early prediction of Down syndrome fetus using sonogram images. Signal. Image Video Process. 245–255 (2011). 5https://doi.org/10.1007/s11760-010-0158-8

  15. Paniagua Beatriz, C., Lucia, W.D., Hongtu, Z., Ruixin, G., Martin, S.: Clinical application of SPHARM-PDM to quantify temporomandibular joint osteoarthritis. Comput. Med. Imaging Graph. 35, 345–352 (2011). https://doi.org/10.1016/j.compmedimag.2010.11.012

    Article  Google Scholar 

  16. Redmon, J., Farhadi, A.: YOLO9000: better, faster, stronger. Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 6517–6525), Honolulu, HI, USA. (2017)

  17. Shakeri Mahsa, L., Herve, Datta Alexandre, N., Oser Nadine, Laurent, Létourneau-Guillon, L.L., Vincent, M., Florence, M., Domitille, T., Alan: Statistical shape analysis of subcortical structures using spectral matching. Comput. Med. Imaging Graph. 52, 58–71 (2016). https://doi.org/10.1016/j.compmedimag.2016.03.001 Lippé Sarah, Kadoury Samuel; Alzheimer’s Disease Neuroimaging Initiative

  18. Shen, L.: SPHARM-MAT Documentation, Release 1.0.0., (2010). http://lishenlab.com/spharm/SPHARM-MAT.pdf

  19. Shen, L., Huang, H., Makedon, F., Saykin, A.J.: May. Efficient registration of 3D SPHARM surfaces. Fourth Canadian Conference on Computer and Robot Vision (CRV07) (pp. 81–88). IEEE. (2007). https://doi.org/10.1109/CRV.2007.26

  20. Shen, L., Farid, H., McPeek, M.A.: Modeling three-dimensional morphological structures using spherical harmonics. Evolution. 63(4), 1003–1016 (2009). https://doi.org/10.1111/j.1558-5646.2008.00557.x

    Article  MATH  Google Scholar 

  21. Styner, M., Oguz, I., Xu, S., Brechbühler, C., Pantazis, D., Levitt, J.J., Gerig, G.: Framework for the statistical shape analysis of brain structures using SPHARM-PDM. Insight J. 1071, 242 (2006)

    MATH  Google Scholar 

  22. Velásquez-Rodríguez, G., Arámbula Cosío, F., Escalante Ramírez, B.: Automatic segmentation of the fetal cerebellum using spherical harmonics and gray level profiles. 11th International Symposium on Medical Image Processing and Analysis (Vol. 9681, p. 968114). International Society for Optics and Photonics. (2015). https://doi.org/10.1117/12.2207833

  23. Velásquez-Rodríguez, G., Arámbula Cosío, F., Huerta, M.G., Marín, L.C., Olivares, H.B., Ramírez, E., B: Automatic segmentation of the cerebellum in ultrasound volumes of the fetal brain. Revista Mexicana De Ingeniería Biomédica. 36(2), 121–129 (2015a)

    Article  Google Scholar 

  24. Venturini, L., Papageorghiou, A.T., Noble, J.A., Namburete, A.I.: Multi-task CNN for Structural Semantic Segmentation in 3D Fetal Brain Ultrasound. Annual Conference on Medical Image Understanding and Analysis (pp. 164–173). Springer, Cham. (2019). https://doi.org/10.1007/978-3-030-39343-4_14

  25. Yaqub, M., Cuingnet, R., Napolitano, R., Roundhill, D., Papageorghiou, A., Ardon, R., Noble, J.A.: Volumetric segmentation of key fetal brain structures in 3D ultrasound. International Workshop on Machine Learning in Medical Imaging, 8184, pp. 25–32. (2013). https://doi.org/10.1007/978-3-319-02267-3_4

  26. Yu, Y., Molloy, J.A., Acton, S.T.: Three-dimensional speckle reducing anisotropic diffusion. In Signals, Systems and Computers, 2004. Conference Record of the Thirty Seventh Asilomar Conference on (Vol. 2, pp. 1987–1991). IEEE. (2003)., November https://doi.org/10.1109/ACSSC.2003.1292329

Download references

Acknowledgements

The financial support of UNAM (grants PAPIIT IV100420 and PAPIIT IA104622), CONAHCYT and “Programa de Becas Posdoctorales de DGAPA” is gratefully acknowledged. Fabian Torres acknowledges the support of the Postdoctoral Fellowship granted by CONAHCYT (CVU 298645). Zian Fanti and Gustavo Velásquez, gratefully acknowledge the support of CONACYT with their doctoral scholarships.

Author information

Authors and Affiliations

Authors

Contributions

GVR: Designed and implemented the algorithms, performed the tests and analysis of results. Collaborated in the preparation of the manuscript. ZFG and FTR: Collaborated in the design and implementation of the algorithms, provided feedback on the manuscript. VMB and BER: Provided feedback on the design of the algorithms, collaborated in the analysis of results and the writing of the manuscript. LCM and MGH: Cured and annotated all the ultrasound data, provided clinical guidance on the segmentation of the cerebellum, collaborated in the analysis of results and the writing of the manuscript. FAC: Collaborated in the design and implementation of the algorithms, test design and analysis of results. He also collaborated in the writing of the manuscript.

Corresponding author

Correspondence to Fernando Arámbula Cosío.

Ethics declarations

Competing interests

The authors declare no competing interests.

Additional information

Publisher’s note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Velásquez-Rodríguez, G.A., Fanti-Gutiérrez, Z., Torres, F. et al. 3D statistical shape models for automatic segmentation of the fetal cerebellum in ultrasound images. SIViP 19, 81 (2025). https://doi.org/10.1007/s11760-024-03615-1

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • DOI: https://doi.org/10.1007/s11760-024-03615-1

Keywords

Navigation