An Automated Localization, Segmentation and Reconstruction Framework for Fetal Brain MRI

  • Michael EbnerEmail author
  • Guotai WangEmail author
  • Wenqi Li
  • Michael Aertsen
  • Premal A. Patel
  • Rosalind Aughwane
  • Andrew Melbourne
  • Tom Doel
  • Anna L. David
  • Jan Deprest
  • Sébastien Ourselin
  • Tom Vercauteren
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11070)


Reconstructing a high-resolution (HR) volume from motion-corrupted and sparsely acquired stacks plays an increasing role in fetal brain Magnetic Resonance Imaging (MRI) studies. Existing reconstruction methods are time-consuming and often require user interaction to localize and extract the brain from several stacks of 2D slices. In this paper, we propose a fully automatic framework for fetal brain reconstruction that consists of three stages: (1) brain localization based on a coarse segmentation of a down-sampled input image by a Convolutional Neural Network (CNN), (2) fine segmentation by a second CNN trained with a multi-scale loss function, and (3) novel, single-parameter outlier-robust super-resolution reconstruction (SRR) for HR visualization in the standard anatomical space. We validate our framework with images from fetuses with variable degrees of ventriculomegaly associated with spina bifida. Experiments show that each step of our proposed pipeline outperforms state-of-the-art methods in both segmentation and reconstruction comparisons. Overall, we report automatic SRR reconstructions that compare favorably with those obtained by manual, labor-intensive brain segmentations. This potentially unlocks the use of automatic fetal brain reconstruction studies in clinical practice.



This work is supported by Wellcome Trust [WT101957; 203145Z/16/Z], EPSRC [EP/L016478/1; NS/A000027/1; NS/A000050/1], and the NIHR UCLH BRC.


  1. 1.
    Alansary, A., et al.: PVR: patch-to-volume reconstruction for large area motion correction of fetal MRI. IEEE Trans. Med. Imaging 36(10), 2031–2044 (2017)CrossRefGoogle Scholar
  2. 2.
    Ebner, M., et al.: Point-spread-function-aware slice-to-volume registration: application to upper abdominal MRI super-resolution. In: Zuluaga, M.A., Bhatia, K., Kainz, B., Moghari, M.H., Pace, D.F. (eds.) RAMBO/HVSMR -2016. LNCS, vol. 10129, pp. 3–13. Springer, Cham (2017). Scholar
  3. 3.
    Gholipour, A., Estroff, J.A., Warfield, S.K.: Robust super-resolution volume reconstruction from slice acquisitions: application to fetal brain MRI. IEEE Trans. Med. Imaging 29(10), 1739–1758 (2010)CrossRefGoogle Scholar
  4. 4.
    Gholipour, A., et al.: A normative spatiotemporal MRI atlas of the fetal brain for automatic segmentation and analysis of early brain growth. Sci. Rep. 7(1), 476 (2017)CrossRefGoogle Scholar
  5. 5.
    Gibson, E., et al.: NiftyNet: a deep-learning platform for medical imaging. Comput. Methods Programs Biomed. 158, 113–122 (2018)CrossRefGoogle Scholar
  6. 6.
    Kainz, B., et al.: Fast volume reconstruction from motion corrupted stacks of 2D slices. IEEE Trans. Med. Imaging 34(9), 1901–1913 (2015)CrossRefGoogle Scholar
  7. 7.
    Keraudren, K., et al.: Automated fetal brain segmentation from 2D MRI slices for motion correction. Neuroimage 101, 633–643 (2014)CrossRefGoogle Scholar
  8. 8.
    Ovaere, C., et al.: Prenatal diagnosis and patient preferences in patients with neural tube defects around the advent of fetal surgery in Belgium and Holland. Fetal Diagn. Ther. 37(3), 226–234 (2015)CrossRefGoogle Scholar
  9. 9.
    Rousseau, F., et al.: Registration-based approach for reconstruction of high-resolution in Utero Fetal MR Brain images. Acad. Radiol. 13(9), 1072–1081 (2006)CrossRefGoogle Scholar
  10. 10.
    Salehi, S.S.M., et al.: Real-time automatic fetal brain extraction in fetal MRI by deep learning. arXiv Preprint. arXiv1710.09338 (2017)Google Scholar
  11. 11.
    Tourbier, S., et al.: Automated template-based brain localization and extraction for fetal brain MRI reconstruction. Neuroimage 155, 460–472 (2017)CrossRefGoogle Scholar
  12. 12.
    Wang, G., et al.: Interactive medical image segmentation using deep learning with image-specific fine-tuning. IEEE Trans. Med. Imaging 37(7), 1562–1573 (2018)CrossRefGoogle Scholar

Copyright information

© Springer Nature Switzerland AG 2018

Authors and Affiliations

  1. 1.Translational Imaging Group, WEISSUniversity College LondonLondonUK
  2. 2.Department of RadiologyUniversity Hospitals KU LeuvenLeuvenBelgium
  3. 3.Institute for Women’s Health, University College LondonLondonUK
  4. 4.Department of Obstetrics and GynaecologyUniversity Hospitals KU LeuvenLeuvenBelgium
  5. 5.School of Biomedical Engineering and Imaging Sciences, King’s College LondonLondonUK

Personalised recommendations