Skip to main content

Thank you for visiting nature.com. You are using a browser version with limited support for CSS. To obtain the best experience, we recommend you use a more up to date browser (or turn off compatibility mode in Internet Explorer). In the meantime, to ensure continued support, we are displaying the site without styles and JavaScript.

  • Article
  • Published:

A lifespan-generalizable skull-stripping model for magnetic resonance images that leverages prior knowledge from brain atlases

Nature Biomedical Engineering volume 9, pages 700–715 (2025)Cite this article

Subjects

Abstract

In magnetic resonance imaging of the brain, an imaging-preprocessing step removes the skull and other non-brain tissue from the images. But methods for such a skull-stripping process often struggle with large data heterogeneity across medical sites and with dynamic changes in tissue contrast across lifespans. Here we report a skull-stripping model for magnetic resonance images that generalizes across lifespans by leveraging personalized priors from brain atlases. The model consists of a brain extraction module that provides an initial estimation of the brain tissue on an image, and a registration module that derives a personalized prior from an age-specific atlas. The model is substantially more accurate than state-of-the-art skull-stripping methods, as we show with a large and diverse dataset of 21,334 lifespans acquired from 18 sites with various imaging protocols and scanners, and it generates naturally consistent and seamless lifespan changes in brain volume, faithfully charting the underlying biological processes of brain development and ageing.

Access through your institution
Buy or subscribe

This is a preview of subscription content, access via your institution

Access options

Access through your institution

Buy this article

  • Purchase on SpringerLink
  • Instant access to full article PDF
Buy now

Prices may be subject to local taxes which are calculated during checkout

Fig. 1: T1w MR images and their histograms from different sites across the lifespan.
Fig. 2: Visual comparison of skull-stripping methods on lifespan scans.
Fig. 3: Averaged over- and under-segmentation error maps based on 21,334 lifespan scans.
Fig. 4: A quantitative comparison of skull-stripping performance across BET, 3DSS, ROBEX, FreeSurfer, SynthStrip, HD-BET and our LifespanStrip framework.
Fig. 5: Illustration of brain anatomical distortions and skull-stripping performance related to ACC, MCD, PFM and HD.
Fig. 6: Quantitative comparison of skull-stripping performance in terms of Dice ratio and MSD on 14,303 scans with Siemens, 3,073 scans with Philips and 3,810 scans with GE.
Fig. 7: Ablation study: the importance of prior knowledge.
Fig. 8: Aggregated imaging information for datasets used in this study.

Similar content being viewed by others

Data availability

The large-scale images (N = 21,334) used in this study come from the following publicly available datasets: dHCP (https://biomedia.github.io/dHCP-release-notes/), MAP (https://circlelab.unc.edu/studies/completed-data-collection/multi-visit-advanced-pediatric-brain-imaging-map/), BCP (https://nda.nih.gov/edit_collection.html?id=2848), NDAR (https://nda.nih.gov/edit_collection.html?id=19), HBN (http://fcon_1000.projects.nitrc.org/indi/cmi_healthy_brain_network/), ABIDE (https://fcon_1000.projects.nitrc.org/indi/abide/), IXI (https://brain-development.org/ixi-dataset/), CCNP (https://ccnp.scidb.cn/en/detail?dataSetId=826407529641672704&version=V3&code=o00133), ICBM (https://ida.loni.usc.edu/login.jsp), HCP (https://www.humanconnectome.org/study/hcp-young-adult), SLIM (http://fcon_1000.projects.nitrc.org/indi/retro/southwestuni_qiu_index.html), SALD (http://fcon_1000.projects.nitrc.org/indi/retro/sald.html), DLBS (https://fcon_1000.projects.nitrc.org/indi/retro/dlbs.html), Chinese Adult Brain (https://www.nitrc.org/projects/adultatlas), ABVIB (https://ida.loni.usc.edu/login.jsp), AIBL (https://ida.loni.usc.edu/login.jsp), OASIS3 (https://www.oasis-brains.org) and ADNI (https://ida.loni.usc.edu). Additional images are available at the following links: https://brainlife.io/pub/60ddea776f0f540a79ca53d8 (EMEDEA-PED), https://surfer.nmr.mgh.harvard.edu/docs/synthstrip/ (SynthStrip dataset) and https://fcon_1000.projects.nitrc.org/indi/indiPRIME.html (An Open Resource for Non-human Primate Imaging). Source data are provided with this paper.

Code availability

The source code, training data and trained model are available on GitHub at https://github.com/DBC-Lab/Atlases-empowered_Lifespan_Skull_Stripping. The model is also available for use in iBEAT V2.0 Cloud/Docker (http://www.ibeat.cloud). The source codes of competing methods are also available; BET, https://ftp.nmr.mgh.harvard.edu/pub/dist/freesurfer/tutorial_packages/centos6/fsl_507/doc/wiki/BET(2f)UserGuide.html; 3DSS, https://afni.nimh.nih.gov/pub/dist/doc/program_help/3dSkullStrip.html; ROBEX, https://www.nitrc.org/projects/robex; FreeSurfer, https://surfer.nmr.mgh.harvard.edu/fswiki, version 7.2.0; SynthStrip, https://surfer.nmr.mgh.harvard.edu/docs/synthstrip/#tool; HD-BET, https://github.com/MIC-DKFZ/HD-BET. To assess the significance of the results quantitatively, we conducted statistical analyses P value using one-way ANOVA with repeated measures followed by Dunnett’s multiple comparisons tests. P values were denoted by asterisks: * for P < 0.05, ** for P < 0.01 and *** for P < 0.001. Besides, we used Cohen’s d score as a pivotal metric to convey and quantify the magnitude of the observed effect within the results, using Effect Size Calculators (https://lbecker.uccs.edu).

References

  1. Giedd, J. N. Structural magnetic resonance imaging of the adolescent brain. Ann. N. Y. Acad. Sci. 1021, 77–85 (2004).

    PubMed  Google Scholar 

  2. Hahn, H. K. & Peitgen, H.-O. The skull stripping problem in MRI solved by a single 3D watershed transform. In Medical Image Computing and Computer-Assisted Intervention—MICCAI 2000 (eds Delp, S. L., DiGoia, A. M. & Jaramaz, B.) 134–143 (Springer, 2000).

  3. Tustison, N. J. et al. N4ITK: improved N3 bias correction. IEEE Trans. Med. Imaging 29, 1310–1320 (2010).

    PubMed  PubMed Central  Google Scholar 

  4. Fatima, A., Shahid, A. R., Raza, B., Madni, T. M. & Janjua, U. I. State-of-the-art traditional to the machine-and deep-learning-based skull stripping techniques, models, and algorithms. J. Digit. Imaging 33, 1443–1464 (2020).

    PubMed  PubMed Central  Google Scholar 

  5. Gibou, F., Fedkiw, R. & Osher, S. A review of level-set methods and some recent applications. J. Comput. Phys. 353, 82–109 (2018).

    Google Scholar 

  6. Li, C., Xu, C., Gui, C. & Fox, M. D. Distance regularized level set evolution and its application to image segmentation. IEEE Trans. Image Process. 19, 3243–3254 (2010).

    PubMed  Google Scholar 

  7. Ziou, D. & Tabbone, S. Edge detection techniques—an overview. Pattern Recognit. Image Anal. 8, 537–559 (1998).

    Google Scholar 

  8. Yi, F. & Moon, I. Image segmentation: a survey of graph-cut methods. In 2012 International Conference on Systems and Informatics (ICSAI2012) https://doi.org/10.1109/ICSAI19873.2012 (IEEE, 2012).

  9. Jenkinson, M. BET2: MR-based estimation of brain, skull and scalp surfaces. In Eleventh Annual Meeting of the Organization for Human Brain Mapping (2005).

  10. Smith, S. M. Fast robust automated brain extraction. Hum. Brain Mapp. 17, 143–155 (2002).

    PubMed  PubMed Central  Google Scholar 

  11. Zeng, X., Staib, L. H., Schultz, R. T. & Duncan, J. S. Segmentation and measurement of the cortex from 3-D MR images using coupled-surfaces propagation. IEEE Trans. Med. Imaging 18, 927–937 (1999).

    CAS  PubMed  Google Scholar 

  12. Shattuck, D. W., Sandor-Leahy, S. R., Schaper, K. A., Rottenberg, D. A. & Leahy, R. M. Magnetic resonance image tissue classification using a partial volume model. NeuroImage 13, 856–876 (2001).

    CAS  PubMed  Google Scholar 

  13. Shanthi, K. & Kumar, M. S. Skull stripping and automatic segmentation of brain MRI using seed growth and threshold techniques. In 2007 International Conference on Intelligent and Advanced Systems https://doi.org/10.1109/ICIAS12643.2007 (IEEE, 2007).

  14. Mohsin, S., Sajjad, S., Malik, Z. & Abdullah, A. H. Efficient way of skull stripping in MRI to detect brain tumor by applying morphological operations, after detection of false background. Int. J. Inform. Educ. Technol. 2, 335–337 (2012).

    Google Scholar 

  15. Fein, G. et al. Statistical parametric mapping of brain morphology: sensitivity is dramatically increased by using brain-extracted images as inputs. NeuroImage 30, 1187–1195 (2006).

    PubMed  Google Scholar 

  16. Somasundaram, K. & Kalavathi, P. Brain segmentation in magnetic resonance human head scans using multi-seeded region growing. Imaging Sci. J. 62, 273–284 (2014).

    Google Scholar 

  17. Eskildsen, S. F. et al. BEaST: brain extraction based on nonlocal segmentation technique. NeuroImage 59, 2362–2373 (2012).

    PubMed  Google Scholar 

  18. Huang, A., Abugharbieh, R., Tam, R. & Traboulsee, A. MRI brain extraction with combined expectation maximization and geodesic active contours. In 2006 IEEE International Symposium on Signal Processing and Information Technology https://doi.org/10.1109/ISSPIT11677.2006 (IEEE, 2006).

  19. Rehm, K. et al. Putting our heads together: a consensus approach to brain/non-brain segmentation in T1-weighted MR volumes. NeuroImage 22, 1262–1270 (2004).

    PubMed  Google Scholar 

  20. Somasundaram, K. & Shankar, R. S. Skull stripping of MRI using clustering and 2D region growing method. In Image Processing NCIMP (eds Somasundaram, K.) 1–12 (Allied Publishers Pvt, 2010).

  21. Somasundaram, K. & Shankar, R. S. Automated skull stripping method using clustering and histogram analysis for MRI human head scans. Int. J. Adv. Res. Comput. Sci. Technol. 2, 117–122 (2014).

    Google Scholar 

  22. Rigatti, S. J. Random forest. J. Insur. Med. 47, 31–39 (2017).

    PubMed  Google Scholar 

  23. Cox, R. W. AFNI: software for analysis and visualization of functional magnetic resonance neuroimages. Comput. Biomed. Res. 29, 162–173 (1996).

    CAS  PubMed  Google Scholar 

  24. Fischl, B. FreeSurfer. NeuroImage 62, 774–781 (2012).

    PubMed  Google Scholar 

  25. Iglesias, J. E., Liu, C.-Y., Thompson, P. M. & Tu, Z. Robust brain extraction across datasets and comparison with publicly available methods. IEEE Trans. Med. Imaging 30, 1617–1634 (2011).

    PubMed  Google Scholar 

  26. Pei, L. et al. A general skull stripping of multiparametric brain MRIs using 3D convolutional neural network. Sci. Rep. 12, 10826 (2022).

    CAS  PubMed  PubMed Central  Google Scholar 

  27. Lucena, O., Souza, R., Rittner, L., Frayne, R. & Lotufo, R. Convolutional neural networks for skull-stripping in brain MR imaging using silver standard masks. Artif. Intell. Med. 98, 48–58 (2019).

    PubMed  Google Scholar 

  28. Kleesiek, J. et al. Deep MRI brain extraction: a 3D convolutional neural network for skull stripping. NeuroImage 129, 460–469 (2016).

    PubMed  Google Scholar 

  29. Hwang, H., Rehman, H. Z. U. & Lee, S. 3D U-Net for skull stripping in brain MRI. Appl. Sci. 9, 569–584 (2019).

    Google Scholar 

  30. Isensee, F. et al. Automated brain extraction of multisequence MRI using artificial neural networks. Hum. Brain Mapp. 40, 4952–4964 (2019).

    PubMed  PubMed Central  Google Scholar 

  31. Hoopes, A., Mora, J. S., Dalca, A. V., Fischl, B. & Hoffmann, M. SynthStrip: skull-stripping for any brain image. NeuroImage 260, 119474 (2022).

    PubMed  Google Scholar 

  32. Sun, Y. et al. Multi-site infant brain segmentation algorithms: the iSeg-2019 challenge. IEEE Trans. Med. Imaging 40, 1363–1376 (2021).

    PubMed  PubMed Central  Google Scholar 

  33. Fischl, B. et al. Whole brain segmentation: automated labeling of neuroanatomical structures in the human brain. Neuron 33, 341–355 (2002).

    CAS  PubMed  Google Scholar 

  34. Avants, B. B., Tustison, N. J., Wu, J., Cook, P. A. & Gee, J. C. An open source multivariate framework for n-tissue segmentation with evaluation on public data. Neuroinformatics 9, 381–400 (2011).

    PubMed  PubMed Central  Google Scholar 

  35. Cabezas, M., Oliver, A., Lladó, X., Freixenet, J. & Cuadra, M. B. A review of atlas-based segmentation for magnetic resonance brain images. Comput. Methods Programs Biomed. 104, 158–177 (2011).

    Google Scholar 

  36. Sabuncu, M. R., Yeo, B. T., Van Leemput, K., Fischl, B. & Golland, P. A generative model for image segmentation based on label fusion. IEEE Trans. Med. Imaging 29, 1714–1729 (2010).

    PubMed  PubMed Central  Google Scholar 

  37. Puonti, O., Iglesias, J. E. & Van Leemput, K. Fast and sequence-adaptive whole-brain segmentation using parametric Bayesian modeling. NeuroImage 143, 235–249 (2016).

    PubMed  Google Scholar 

  38. Chen, L. et al. A 4D infant brain volumetric atlas based on the UNC/UMN baby connectome project (BCP) cohort. NeuroImage 253, 119097 (2022).

    PubMed  Google Scholar 

  39. Wu, Y. et al. High resolution 0.5 mm isotropic T1-weighted and diffusion tensor templates of the brain of non-demented older adults in a common space for the MIITRA atlas. NeuroImage 282, 120387 (2023).

    CAS  PubMed  Google Scholar 

  40. Hughes, E. J. et al. A dedicated neonatal brain imaging system. Magn. Reson. Med. 78, 794–804 (2017).

    CAS  PubMed  Google Scholar 

  41. Cordero-Grande, L. et al. Sensitivity encoding for aligned multishot magnetic resonance reconstruction. IEEE Trans. Comput. Imaging 2, 266–280 (2016).

    Google Scholar 

  42. Hazlett, H. C. et al. Brain volume findings in 6-month-old infants at high familial risk for autism. Am. J. Psychiatry 169, 601–608 (2012).

    PubMed  PubMed Central  Google Scholar 

  43. Di Martino, A. et al. Enhancing studies of the connectome in autism using the autism brain imaging data exchange II. Sci. Data 4, 1–15 (2017).

    Google Scholar 

  44. Gao, P. et al. A Chinese multi-modal neuroimaging data release for increasing diversity of human brain mapping. Sci. Data 9, 286–296 (2022).

    PubMed  PubMed Central  Google Scholar 

  45. Liu, S. et al. Chinese Color Nest Project: an accelerated longitudinal brain-mind cohort. Dev. Cogn. Neurosci. 52, 101020 (2021).

    PubMed  PubMed Central  Google Scholar 

  46. Weiner, M. W. et al. The Alzheimer’s disease neuroimaging initiative 3: continued innovation for clinical trial improvement. Alzheimer’s Dement. 13, 561–571 (2017).

    Google Scholar 

  47. Jenkinson, M., Beckmann, C. F., Behrens, T. E., Woolrich, M. W. & Smith, S. M. FSL. NeuroImage 62, 782–790 (2012).

    PubMed  Google Scholar 

  48. Howell, B. R. et al. The UNC/UMN Baby Connectome Project (BCP): an overview of the study design and protocol development. NeuroImage 185, 891–905 (2019).

    PubMed  Google Scholar 

  49. Woodburn, M. A. Trajectories of Group and Individual-Level Structural Brain Network Organization from Birth to Childhood and Their Cognitive Relevance. MA Thesis (The University of North Carolina at Chapel Hill, 2020).

  50. Bethlehem, R. A. et al. Brain charts for the human lifespan. Nature 604, 525–533 (2022).

    CAS  PubMed  PubMed Central  Google Scholar 

  51. Lai, M. M. et al. Relationship of established cardiovascular risk factors and peripheral biomarkers on cognitive function in adults at risk of cognitive deterioration. J. Alzheimer’s Dis. 74, 163–171 (2020).

    CAS  Google Scholar 

  52. Alexander, L. M. et al. An open resource for transdiagnostic research in pediatric mental health and learning disorders. Sci. Data 4, 1–26 (2017).

    CAS  Google Scholar 

  53. Van Essen, D. C. & Glasser, M. F. The human connectome project: progress and prospects. In Cerebrum: The Dana Forum on Brain Science https://pmc.ncbi.nlm.nih.gov/articles/PMC5198757 (Dana Foundation, 2016).

  54. LaMontagne, P. J. et al. OASIS-3: longitudinal neuroimaging, clinical, and cognitive dataset for normal aging and Alzheimer disease. Preprint at medRxiv https://doi.org/10.1101/2019.12.13.19014902 (2019).

  55. Zöllei, L., Iglesias, J. E., Ou, Y., Grant, P. E. & Fischl, B. Infant FreeSurfer: an automated segmentation and surface extraction pipeline for T1-weighted neuroimaging data of infants 0–2 years. NeuroImage 218, 116946 (2020).

    PubMed  Google Scholar 

  56. Amorosino, G. et al. DBB-A distorted brain benchmark for automatic tissue segmentation in paediatric patients. NeuroImage 260, 119486 (2022).

    PubMed  Google Scholar 

  57. Rohlfing, T., Zahr, N. M., Sullivan, E. V. & Pfefferbaum, A. The SRI24 multichannel atlas of normal adult human brain structure. Hum. Brain Mapp. 31, 798–819 (2010).

    PubMed  Google Scholar 

  58. Milham, M. P. et al. An open resource for non-human primate imaging. Neuron 100, 61–7462 (2018).

    CAS  PubMed  PubMed Central  Google Scholar 

  59. Nerland, S. et al. A comparison of intracranial volume estimation methods and their cross-sectional and longitudinal associations with age. Hum. Brain Mapp. 43, 4620–4639 (2022).

    PubMed  PubMed Central  Google Scholar 

  60. Sgouros, S., Goldin, J. H., Hockley, A. D., Wake, M. J. & Natarajan, K. Intracranial volume change in childhood. J. Neurosurg. 91, 610–616 (1999).

    CAS  PubMed  Google Scholar 

  61. Kamdar, M. R., Gomez, R. A. & Ascherman, J. A. Intracranial volumes in a large series of healthy children. Plast. Reconstr. Surg. 124, 2072–2075 (2009).

    CAS  PubMed  Google Scholar 

  62. Hill, C. A. et al. Intracranial volume and whole brain volume in infants with unicoronal craniosynostosis. Cleft Palate-Craniofacial J. 48, 394–398 (2011).

    Google Scholar 

  63. Royle, N. A. et al. Estimated maximal and current brain volume predict cognitive ability in old age. Neurobiol. Aging 34, 2726–2733 (2013).

    PubMed  PubMed Central  Google Scholar 

  64. Dimitrova, R. et al. Phenotyping the preterm brain: characterizing individual deviations from normative volumetric development in two large infant cohorts. Cereb. Cortex 31, 3665–3677 (2021).

    PubMed  PubMed Central  Google Scholar 

  65. Zacharia, A. et al. Early assessment of brain maturation by MR imaging segmentation in neonates and premature infants. Am. J. Neuroradiol. 27, 972–977 (2006).

    CAS  PubMed  PubMed Central  Google Scholar 

  66. Blatter, D. D. et al. Quantitative volumetric analysis of brain MR: normative database spanning 5 decades of life. Am. J. Neuroradiol. 16, 241–251 (1995).

    CAS  PubMed  PubMed Central  Google Scholar 

  67. Reite, M. et al. Brain size and brain/intracranial volume ratio in major mental illness. BMC Psychiatry 10, 1–9 (2010).

    Google Scholar 

  68. Tanskanen, P. et al. Volumes of brain, grey and white matter and cerebrospinal fluid in schizophrenia in the Northern Finland 1966 Birth Cohort: an epidemiological approach to analysis. Psychiatry Res. Neuroimaging 174, 116–120 (2009).

    Google Scholar 

  69. Narr, K. L. et al. Increases in regional subarachnoid CSF without apparent cortical gray matter deficits in schizophrenia: modulating effects of sex and age. Am. J. Psychiatry 160, 2169–2180 (2003).

    PubMed  Google Scholar 

  70. Arango, C. et al. Patterns of cranial, brain and sulcal CSF volumes in male and female deficit and nondeficit patients with schizophrenia. Psychiatry Res. Neuroimaging 162, 91–100 (2008).

    Google Scholar 

  71. Matsumae, M. et al. Age-related changes in intracranial compartment volumes in normal adults assessed by magnetic resonance imaging. J. Neurosurg. 84, 982–991 (1996).

    CAS  PubMed  Google Scholar 

  72. Jenkins, R., Fox, N. C., Rossor, A. M., Harvey, R. J. & Rossor, M. N. Intracranial volume and Alzheimer disease: evidence against the cerebral reserve hypothesis. Archives Neurol. 57, 220–224 (2000).

    CAS  Google Scholar 

  73. Edland, S. et al. Total intracranial volume: normative values and lack of association with Alzheimer’s disease. Neurology 59, 272–274 (2002).

    CAS  PubMed  Google Scholar 

  74. Lenroot, R. K. et al. Sexual dimorphism of brain developmental trajectories during childhood and adolescence. NeuroImage 36, 1065–1073 (2007).

    PubMed  Google Scholar 

  75. Lenroot, R. K. & Giedd, J. N. Sex differences in the adolescent brain. Brain Cogn. 72, 46–55 (2010).

    PubMed  Google Scholar 

  76. Kempton, M. J. et al. A comprehensive testing protocol for MRI neuroanatomical segmentation techniques: evaluation of a novel lateral ventricle segmentation method. NeuroImage 58, 1051–1059 (2011).

    PubMed  Google Scholar 

  77. Gulban, O. F., Schneider, M., Marquardt, I., Haast, R. A. M. & De Martino, F. A scalable method to improve gray matter segmentation at ultra high field MRI. PLoS ONE 13, 1–31 (2018).

    Google Scholar 

  78. Hoffmann, M., Hoopes, A., Fischl, B. & Dalca, A. V. Anatomy-specific acquisition-agnostic affine registration learned from fictitious images. In Proc. SPIE 12464, Medical Imaging 2023: Image Processing, 1246402 (ed Olivier, C.) https://doi.org/10.1117/12.2653251 (SPIE, 2023).

  79. Hoffmann, M. et al. SynthMorph: learning contrast-invariant registration without acquired images. IEEE Trans. Med. Imaging 41, 543–558 (2021).

    Google Scholar 

  80. Caspi, Y. et al. Changes in the intracranial volume from early adulthood to the sixth decade of life: a longitudinal study. NeuroImage 220, 116842 (2020).

    PubMed  Google Scholar 

  81. Dosovitskiy, A. et al. An image is worth 16 × 16 words: transformers for image recognition at scale. In International Conference on Learning Representations 2021 https://openreview.net/pdf?id=YicbFdNTTy (ICLR, 2021).

  82. Wang, W. et al. Pyramid vision transformer: a versatile backbone for dense prediction without convolutions. In Proc. IEEE/CVF International Conference on Computer Vision https://doi.org/10.1109/ICCV48922.2021 (IEEE, 2021).

  83. Vaswani, A. Attention is all you need. In 31st Conference on Neural Information Processing Systems (eds Luxburg, U. et al.) https://papers.nips.cc/paper_files/paper/2017/file/3f5ee243547dee91fbd053c1c4a845aa-Paper.pdf (NIPS, 2017).

  84. Xu, J., Li, Z., Du, B., Zhang, M. & Liu, J. Reluplex made more practical: Leaky ReLU. In 2020 IEEE Symposium on Computers and Communications (ISCC) https://doi.org/10.1109/ISCC50000.2020 (IEEE Computer Society, 2020).

  85. Li, J., Wang, Y., Wang, S., Zhang, K. & Li, G. Landmark-guided rigid registration for temporomandibular joint MRI-CBCT images with large field-of-view difference. In Machine Learning in Medical Imaging: 12th International Workshop (eds Lian, C. et al.) 527–536 (Springer, 2021).

  86. Balakrishnan, G., Zhao, A., Sabuncu, M. R., Guttag, J. & Dalca, A. V. VoxelMorph: a learning framework for deformable medical image registration. IEEE Trans. Med. Imaging 38, 1788–1800 (2019).

    Google Scholar 

  87. Jaderberg, M. et al. Spatial transformer networks. In Advances in Neural Information Processing Systems (eds Cortes, C. et al.) 28 (Curran Associates Inc, 2015).

  88. Fonov, V. et al. Unbiased average age-appropriate atlases for pediatric studies. NeuroImage 54, 313–327 (2011).

    PubMed  Google Scholar 

  89. Mazziotta, J. et al. A probabilistic atlas and reference system for the human brain: International Consortium for Brain Mapping (ICBM). Phil. Trans. R. Soc. B 356, 1293–1322 (2001).

    CAS  PubMed  PubMed Central  Google Scholar 

  90. Liu, W. et al. Longitudinal test–retest neuroimaging data from healthy young adults in southwest China. Sci. Data 4, 1–9 (2017).

    Google Scholar 

  91. Wei, D. et al. Structural and functional brain scans from the cross-sectional Southwest University Adult Lifespan Dataset. Sci. Data 5, 1–10 (2018).

    CAS  Google Scholar 

  92. Zhu, J. & Qiu, A. Chinese adult brain atlas with functional and white matter parcellation. Sci. Data 9, 352–362 (2022).

    PubMed  PubMed Central  Google Scholar 

Download references

Acknowledgements

Limei Wang, Y.S. and Li Wang were supported by the National Institute of Mental Health under award numbers MH133845, MH117943, MH123202 and MH116225. G.L. was supported by the National Institutes of Health under award numbers MH133845, MH117943, MH123202, MH116225, AG075582 and NS128534. The content is solely the responsibility of the authors and does not necessarily represent the official views of the National Institutes of Health. This work also utilizes approaches developed by NIH grants (U01MH110274 and R01MH104324) and the efforts of the UNC/UMN Baby Connectome Project Consortium.

Author information

Authors and Affiliations

  1. Developing Brain Computing Lab, Department of Radiology and Biomedical Research Imaging Center, University of North Carolina at Chapel Hill, Chapel Hill, NC, USA

    Limei Wang, Yue Sun & Li Wang

  2. Joint Department of Biomedical Engineering, University of North Carolina at Chapel Hill and North Carolina State University, Chapel Hill, NC, USA

    Limei Wang & Yue Sun

  3. Department of Psychiatry, University of Pennsylvania, Philadelphia, PA, USA

    Jakob Seidlitz, Aaron Alexander-Bloch & Lena Dorfschmidt

  4. Department of Child and Adolescent Psychiatry and Behavioral Science, The Children’s Hospital of Philadelphia, Philadelphia, PA, USA

    Jakob Seidlitz, Aaron Alexander-Bloch & Lena Dorfschmidt

  5. Lifespan Brain Institute, The Children’s Hospital of Philadelphia and Penn Medicine, Philadelphia, PA, USA

    Jakob Seidlitz, Aaron Alexander-Bloch & Lena Dorfschmidt

  6. Department of Psychology, University of Cambridge, Cambridge, UK

    Richard A. I. Bethlehem

  7. Department of Radiology and Biomedical Research Imaging Center, University of North Carolina at Chapel Hill, Chapel Hill, NC, USA

    Gang Li & Weili Lin

  8. Institute of Child Development, University of Minnesota, Minneapolis, MN, USA

    Jed T. Elison

Authors
  1. Limei Wang
    View author publications

    Search author on:PubMed Google Scholar

  2. Yue Sun
    View author publications

    Search author on:PubMed Google Scholar

  3. Jakob Seidlitz
    View author publications

    Search author on:PubMed Google Scholar

  4. Richard A. I. Bethlehem
    View author publications

    Search author on:PubMed Google Scholar

  5. Aaron Alexander-Bloch
    View author publications

    Search author on:PubMed Google Scholar

  6. Lena Dorfschmidt
    View author publications

    Search author on:PubMed Google Scholar

  7. Gang Li
    View author publications

    Search author on:PubMed Google Scholar

  8. Jed T. Elison
    View author publications

    Search author on:PubMed Google Scholar

  9. Weili Lin
    View author publications

    Search author on:PubMed Google Scholar

  10. Li Wang
    View author publications

    Search author on:PubMed Google Scholar

Contributions

Limei Wang: methodology, implementation, validation, writing and editing; Y.S.: validation, review and editing; J.S., R.A.I.B., A.A.-B. and L.D.: editing and providing brain volumes by FreeSurfer/Infant FreeSurfer and so on; G.L.: review; J.T.E.: resources; W.L.: resources; Li Wang: methodology, validation, supervision, review, editing, resources, project administration and funding acquisition.

Corresponding author

Correspondence to Li Wang.

Ethics declarations

Competing interests

The authors declare no competing interests.

Peer review

Peer review information

Nature Biomedical Engineering thanks Guray Erus, Philipp Vollmuth, Xi-Nian Zuo and the other, anonymous, reviewer(s) for their contribution to the peer review of this work. Peer reviewer reports are available.

Additional information

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

Extended data

Extended Data Fig. 1 Comparison of lifespan brain volume by the LifespanStrip method and by previous work.

Lifespan charts in terms of total brain volume (mm3) by previous work50 (left) and by the LifespanStrip framework (right).

Source data

Extended Data Fig. 2 Flowchart of the atlases-powered lifespan skull-stripping (LifespanStrip) framework.

a, The LifespanStrip framework consists of a brain-extraction module and a registration module. The brain-extraction module is designed to generate an initial estimation of brain intracranial cavity. The registration module aligns an atlas with the estimated brain to offer personalized prior knowledge. Subsequently, the deformation field is applied to the atlas, resulting in the final brain mask. b, The brain-extraction network integrates dual convolution (DC) and dual transformer (DT), detailed in the bottom right corner. c, The registration module includes both rigid registration and deformable registration components.

Supplementary information

Supplementary Information

Supplementary Note, Figures and Tables.

Reporting Summary

Peer Review File

Source data

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

Wang, L., Sun, Y., Seidlitz, J. et al. A lifespan-generalizable skull-stripping model for magnetic resonance images that leverages prior knowledge from brain atlases. Nat. Biomed. Eng 9, 700–715 (2025). https://doi.org/10.1038/s41551-024-01337-w

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1038/s41551-024-01337-w

Search

Advanced search

Quick links

Nature Briefing

Sign up for the Nature Briefing newsletter — what matters in science, free to your inbox daily.

Get the most important science stories of the day, free in your inbox. Sign up for Nature Briefing