Abstract
Background
Accurate segmentation of neonatal brain tissues and structures is crucial for studying normal development and diagnosing early neurodevelopmental disorders. However, there is a lack of an end-to-end pipeline for automated segmentation and imaging analysis of the normal and abnormal neonatal brain.
Objective
To develop and validate a deep learning-based pipeline for neonatal brain segmentation and analysis of structural magnetic resonance images (MRI).
Materials and methods
Two cohorts were enrolled in the study, including cohort 1 (582 neonates from the developing Human Connectome Project) and cohort 2 (37 neonates imaged using a 3.0-tesla MRI scanner in our hospital).We developed a deep leaning-based architecture capable of brain segmentation into 9 tissues and 87 structures. Then, extensive validations were performed for accuracy, effectiveness, robustness and generality of the pipeline. Furthermore, regional volume and cortical surface estimation were measured through in-house bash script implemented in FSL (Oxford Centre for Functional MRI of the Brain Software Library) to ensure reliability of the pipeline. Dice similarity score (DSC), the 95th percentile Hausdorff distance (H95) and intraclass correlation coefficient (ICC) were calculated to assess the quality of our pipeline. Finally, we finetuned and validated our pipeline on 2-dimensional thick-slice MRI in cohorts 1 and 2.
Results
The deep learning-based model showed excellent performance for neonatal brain tissue and structural segmentation, with the best DSC and the 95th percentile Hausdorff distance (H95) of 0.96 and 0.99 mm, respectively. In terms of regional volume and cortical surface analysis, our model showed good agreement with ground truth. The ICC values for the regional volume were all above 0.80. Considering the thick-slice image pipeline, the same trend was observed for brain segmentation and analysis. The best DSC and H95 were 0.92 and 3.00 mm, respectively. The regional volumes and surface curvature had ICC values just below 0.80.
Conclusions
We propose an automatic, accurate, stable and reliable pipeline for neonatal brain segmentation and analysis from thin and thick structural MRI. The external validation showed very good reproducibility of the pipeline.
Similar content being viewed by others
Explore related subjects
Discover the latest articles, news and stories from top researchers in related subjects.Data availability
All data and code used in this study are available from the corresponding author without any restrictions.
References
Antonios M, Paul et al (2016) Regional growth and atlasing of the developing human brain. Neuroimage 125:456–478. https://doi.org/10.1016/j.neuroimage.2015.10.047
Dubois J, Germanaud D, Angleys H et al (2016) Exploring the successive waves of cortical folding in the developing brain using MRI and spectral analysis of gyrification. 2016 IEEE 13th Int Symp Biomed Imaging (ISBI). IEEE, pp 261–264
Pappas A, Adams-Chapman I, Shankaran S et al (2018) Neurodevelopmental and behavioral outcomes in extremely premature neonates with ventriculomegaly in the absence of periventricular-intraventricular hemorrhage. JAMA Pediatr 172:32–42. https://doi.org/10.1001/jamapediatrics.2017.3545
Hintz SR, Barnes PD, Bulas D et al (2015) Neuroimaging and neurodevelopmental outcome in extremely preterm infants. Pediatrics 135:e32–e42. https://doi.org/10.1542/peds.2014-0898
Lyall AE, Shi F, Geng X et al (2015) Dynamic development of regional cortical thickness and surface area in early childhood. Cereb Cortex 25:2204–2212. https://doi.org/10.1093/cercor/bhu027
Makropoulos A, Counsell SJ, Rueckert D (2018) A review on automatic fetal and neonatal brain MRI segmentation. Neuroimage 170:231–248. https://doi.org/10.1016/j.neuroimage.2017.06.074
Khalili N, Lessmann N, Turk E et al (2019) Automatic brain tissue segmentation in fetal MRI using convolutional neural networks. Magn Reson Imaging 64:77–89. https://doi.org/10.1016/j.mri.2019.05.020
Dolz J, Gopinath K, Yuan J et al (2019) HyperDense-Net: a hyper-densely connected CNN for multi-modal image segmentation. IEEE Trans Med Imaging 38:1116–1126. https://doi.org/10.1109/TMI.2018.2878669
Moeskops P, Viergever MA, Mendrik AM et al (2016) Automatic segmentation of MR brain images with a convolutional neural network. IEEE Trans Med Imaging 35:1252–1261. https://doi.org/10.1109/TMI.2016.2548501
Urru A, Nakaki et al (2022) An automatic pipeline for atlas-based fetal and neonatal brain.arXiv preprint. https://doi.org/10.48550/arXiv.2205.07575
Makropoulos A, Robinson EC, Schuh A et al (2018) The developing human connectome project: a minimal processing pipeline for neonatal cortical surface reconstruction. Neuroimage 173:88–112. https://doi.org/10.1016/j.neuroimage.2018.01.054
Hughes EJ, Winchman T, Padormo F et al (2017) A dedicated neonatal brain imaging system. Magn Reson Med 78:794–804. https://doi.org/10.1002/mrm.26462
Cordero-Grande L, Rui P, Hughes EJ et al (2016) Sensitivity encoding for aligned multishot magnetic resonance reconstruction. IEEE Trans Comput Imaging 2:266–280
Tustison NJ, Avants BB, Cook PA et al (2010) N4ITK: improved N3 bias correction. IEEE Trans Med Imaging 29:1310–1320. https://doi.org/10.1109/tmi.2010.2046908
Smith SM (2002) Fast robust automated brain extraction. Hum Brain Mapp 17:143–155. https://doi.org/10.1002/hbm.10062
Makropoulos A, Gousias IS, Ledig C et al (2014) Automatic whole brain MRI segmentation of the developing neonatal brain. IEEE Trans Med Imaging 33:1818–1831. https://doi.org/10.1109/TMI.2014.2322280
Siciarz P, McCurdy B (2022) U-net architecture with embedded Inception-ResNet-v2 image encoding modules for automatic segmentation of organs-at-risk in head and neck cancer radiation therapy based on computed tomography scans. Phys Med Biol 67. https://doi.org/10.1088/1361-6560/ac530e
Cheng J, Liu J, Kuang H et al (2022) A fully automated multimodal MRI-based multi-task learning for glioma segmentation and IDH genotyping. IEEE Trans Med Imaging 41:1520–1532. https://doi.org/10.1109/TMI.2022.3142321
Cipolla R, Gal Y, Kendall A (2018) Multi-task learning using uncertainty to weigh losses for scene geometry and semantics. 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. IEEE, pp 7482–7491
Beare RJ, Chen J, Kelly CE et al (2016) Neonatal brain tissue classification with morphological adaptation and unified segmentation. Front Neuroinform 10:12. https://doi.org/10.3389/fninf.2016.00012
Guha Roy A, Conjeti S, Navab N et al (2019) QuickNAT: a fully convolutional network for quick and accurate segmentation of neuroanatomy. Neuroimage 186:713–727. https://doi.org/10.1016/j.neuroimage.2018.11.042
Dolz J, Desrosiers C, Wang L et al (2020) Deep CNN ensembles and suggestive annotations for infant brain MRI segmentation. Comput Med Imaging Graph 79:101660. https://doi.org/10.1016/j.compmedimag.2019.101660
Hatamizadeh A, Yang D, Roth H et al (2021) UNETR: transformers for 3D medical image segmentation.arXiv preprint. https://doi.org/10.48550/arXiv.2103.10504
Cao H, Wang Y, Chen J et al (2021) Swin-Unet: Unet-like pure transformer for medical image segmentation.arXiv preprint. https://doi.org/10.48550/arXiv.2105.05537
Gao Y, Zhou M, Metaxas D (2021) UTNet: a hybrid transformer architecture for medical image segmentation.arXiv preprint. https://doi.org/10.48550/arXiv.2107.00781
Henschel L, Conjeti S, Estrada S et al (2020) FastSurfer - a fast and accurate deep learning based neuroimaging pipeline. Neuroimage 219:117012. https://doi.org/10.1016/j.neuroimage.2020.117012
Chen J, YL, QY et al (2021) TransUNet: transformers make strong encoders for medical image segmentation.arXiv preprint. https://doi.org/10.48550/arXiv.2102.04306
Zeng N, Li H, Peng Y (2021) A new deep belief network-based multi-task learning for diagnosis of Alzheimer’s disease. Neural Comput Appl. https://doi.org/10.1007/s00521-021-06149-6
Song Z, Awate SP, Licht DJ et al (2007) Clinical neonatal brain MRI segmentation using adaptive nonparametric data models and intensity-based Markov priors. Med Image Comput Comput Assist Interv 10:883–890. https://doi.org/10.1007/978-3-540-75757-3_107
Schmahmann JD (2019) The cerebellum and cognition. Neurosci Lett 688:62–75. https://doi.org/10.1016/j.neulet.2018.07.005
Kamnitsas K, Ledig C, Newcombe V et al (2016) Efficient multi-scale 3D CNN with fully connected CRF for accurate brain lesion segmentation. Med Image Anal 36:61. https://doi.org/10.1016/j.media.2016.10.004
Dolz J, Desrosiers C, Ben Ayed I (2018) 3D fully convolutional networks for subcortical segmentation in MRI: a large-scale study. Neuroimage 170:456–470. https://doi.org/10.1016/j.neuroimage.2017.04.039
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Ethics approval and consent to participate
The study was approved by the research ethics committee of the Affiliated Hospital and Medical School of Nantong University (No.2021-K027-01).
Conflict of interest
None
Additional information
Publisher's note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Supplementary Information
Below are the links to the supplementary materials.
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.
About this article
Cite this article
Shen, D.D., Bao, S.L., Wang, Y. et al. An automatic and accurate deep learning-based neuroimaging pipeline for the neonatal brain. Pediatr Radiol 53, 1685–1697 (2023). https://doi.org/10.1007/s00247-023-05620-x
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00247-023-05620-x