Abstract
Over the past decade, automated 3D reconstruction and segmentation has been widely applied to processing and analysis of fetal MRI. While the majority of reported methods primarily focus on structural brain imaging, additional quantitative T2* information could improve characterisation of changes in functional tissue properties. In this work, we propose a first solution for automated combined tissue-specific analysis of 3D quantitative T2* map and structural T2-weighted (T2w) fetal brain MRI. We build upon the existing 3D structural brain analysis pipeline from SVRTK by adding fully automated 3D T2* reconstructions globally aligned to 3D segmented T2w images (already reconstructed in the standard radiological space) followed by deep learning T2* tissue parcellation. In addition, we assess the general applicability the proposed pipeline by analysing brain growth trajectories in 26 control T2w+T2* fetal MRI datasets from 20–28 weeks GA range.
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
Notes
- 1.
SVRTK automated fetal MRI reconstruction and segmentation docker: https://hub.docker.com/r/fetalsvrtk/svrtk auto-2.20 tag.
- 2.
MIRTK library: https://github.com/BioMedIA/MIRTK.
- 3.
SVRTK toolbox: https://github.com/SVRTK/SVRTK.
- 4.
SVRTK docker: https://hub.docker.com/r/fetalsvrtk/svrtk.
References
Svrtk fetal MRI docker (2023). https://hub.docker.com/r/fetalsvrtk/svrtk
Arun, K.S., et al.: Least-squares fitting of two 3-d point sets. IEEE Trans. Pattern Anal. Mach. Intell. PAMI 9(5), 698–700 (1987)
Baadsgaard, K., et al.: T2* weighted fetal MRI and the correlation with placental dysfunction. Placenta 131, 90–97 (2023)
Cardoso, M.J., et al.: Monai: an open-source framework for deep learning in healthcare. arXiv preprint arXiv:2211.02701 (2022)
Ebner, M., et al.: An automated framework for localization, segmentation and super-resolution reconstruction of fetal brain MRI. NeuroImage 206, 116324 (2020)
Hall, M., et al.: Characterisation of placental, fetal brain and maternal cardiac structure and function in pre-eclampsia using MRI. medRxiv (2023)
Hutter, J., et al.: Multi-modal functional MRI to explore placental function over gestation. Magn. Reson. Med. 81, 1191–1204 (2019)
Karimi, D., et al.: Learning to segment fetal brain tissue from noisy annotations. Med. Image Anal., 102731 (2023)
Kuklisova-Murgasova, M., et al.: Reconstruction of fetal brain MRI with intensity matching and complete outlier removal. MediAN 16(8), 1550–1564 (2012)
Oktay, O., et al.: Attention u-net: learning where to look for the pancreas. In: MIDDL 2016 (2018)
Payette, K., et al.: An automatic multi-tissue human fetal brain segmentation benchmark using the fetal tissue annotation dataset. Sci. Data 8, 1–14 (2021)
Prayer, D., et al.: Isuog practice guidelines (updated): performance of fetal magnetic resonance imaging. Ultrasound Obstet. Gynecol. 61, 278–287 (2023)
Salehi, S.S., Khan, S., Erdogmus, D., Gholipour, A.: Real-time deep pose estimation with geodesic loss for image-to-template rigid registration. IEEE TMI 38(2), 470–481 (2019)
Story, L., Rutherford, M.: Advances and applications in fetal magnetic resonance imaging. Obstet. Gynaecol. 17, 189–199 (2015)
Story, L., et al.: Brain volumetry in fetuses that deliver very preterm: an MRI pilot study. NeuroImage: Clin. 30, 102650 (2021)
Uus, A., et al.: Deformable slice-to-volume registration for motion correction of fetal body and placenta MRI. IEEE TMI 39, 2750–2759 (2020)
Uus, A., et al.: Deformable slice-to-volume registration for reconstruction of quantitative t2* placental and fetal MRI, pp. 222–232 (2020)
Uus, A.U., et al.: Automated 3d reconstruction of the fetal thorax in the standard atlas space from motion-corrupted MRI stacks for 21–36 weeks GA range. MedIAn 80 (2022)
Uus, A.U., et al.: Retrospective motion correction in foetal MRI for clinical applications: existing methods, applications and integration into clinical practice. Brit. J. Radiol. 96, 20220071 (2022)
Uus, A.U., et al.: Bounti: brain volumetry and automated parcellation for 3D fetal MRI. bioRxiv (2023)
Vasylechko, S., et al.: T2 relaxometry of fetal brain at 1.5 tesla using a motion tolerant method. Magn. Reson. Med. 73, 1795–1802 (2015)
Xu, J., et al.: Nesvor: implicit neural representation for slice-to-volume reconstruction in MRI. IEEE Trans. Med. Imaging 42, 1707–1719 (2023)
Acknowledgments
We thank everyone who was involved in acquisition and analysis of the datasets and all participating mothers and families.
This work was supported by NIHR Advanced Fellowship awarded to Lisa Story [NIHR30166], MRC Confidence in concept [MC_PC_19041], the NIH Human Placenta Project grant [1U01HD087202-01], the Wellcome/ EPSRC Centre for Medical Engineering at King’s College London [WT 203148/Z/16/Z], the NIHR Clinical Research Facility (CRF) at Guy’s and St Thomas’ and by the National Institute for Health Research Biomedical Research Centre based at Guy’s and St Thomas’ NHS Foundation Trust and King’s College London.
The views expressed are those of the authors and not necessarily those of the NHS, the NIHR or the Department of Health.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Uus, A.U. et al. (2023). Combined Quantitative T2* Map and Structural T2-Weighted Tissue-Specific Analysis for Fetal Brain MRI: Pilot Automated Pipeline. In: Link-Sourani, D., Abaci Turk, E., Macgowan, C., Hutter, J., Melbourne, A., Licandro, R. (eds) Perinatal, Preterm and Paediatric Image Analysis. PIPPI 2023. Lecture Notes in Computer Science, vol 14246. Springer, Cham. https://doi.org/10.1007/978-3-031-45544-5_3
Download citation
DOI: https://doi.org/10.1007/978-3-031-45544-5_3
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-45543-8
Online ISBN: 978-3-031-45544-5
eBook Packages: Computer ScienceComputer Science (R0)
