pith. sign in

arxiv: 2508.15034 · v4 · pith:7SLBUMAMnew · submitted 2025-08-20 · 🧬 q-bio.QM

An MRI Atlas of the Human Fetal Brain: Reference and Segmentation Tools for Fetal Brain MRI Analysis

Mahdi Bagheri , Clemente Velasco-Annis , Jian Wang , Razieh Faghihpirayesh , Shadab Khan , Camilo Calixto , Camilo Jaimes , Lana Vasung
show 5 more authors
Abdelhakim Ouaalam Onur Afacan Simon K. Warfield Caitlin K. Rollins Ali Gholipour
This is my paper

Pith reviewed 2026-05-18 21:48 UTC · model grok-4.3

classification 🧬 q-bio.QM
keywords fetal brain MRIspatiotemporal atlasbrain segmentationneurodevelopmentgestational ageMRI parcellationdeep learning segmentationfetal atlas
0
0 comments X

The pith

A new 4D MRI atlas maps fetal brain development from 21 to 37 weeks with 126-region parcellation and segmentation tools.

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

The authors construct the CRL-2025 fetal brain atlas from MRI scans of 159 fetuses with typical development between 21 and 37 gestational weeks. They apply diffeomorphic deformable registration and kernel regression on age to produce average templates that include detailed tissue segmentations, transient white matter compartments, and labels for 126 anatomical regions. This version adds substantially more anatomical detail than the prior CRL-2017 atlas and supplies a deep learning segmentation tool plus released subject-level data. A sympathetic reader would care because the atlas supplies a practical reference for studying in-utero neurodevelopment and for analyzing both typical and atypical trajectories at scale.

Core claim

We present the CRL-2025 fetal brain atlas, a spatiotemporal (4D) atlas of the developing fetal brain between 21 and 37 gestational weeks. This atlas is constructed from MRI scans of 159 fetuses with typically developing brains using a diffeomorphic deformable registration framework integrated with kernel regression on age. CRL-2025 uniquely includes detailed tissue segmentations, transient white matter compartments, and parcellation into 126 anatomical regions. It offers significantly enhanced anatomical details over the CRL-2017 atlas and is presented along with a re-release of the CRL diffusion MRI atlas featuring newly created tissue segmentation and labels.

What carries the argument

Diffeomorphic deformable registration framework integrated with kernel regression on gestational age, used to build average templates, tissue segmentations, and 126-region parcellations.

If this is right

  • Researchers can perform scalable, automatic segmentation of fetal brain MRI using the released deep learning tool.
  • Normative trajectories of tissue and regional development become available for comparison with atypical cases.
  • Reproducibility of fetal brain studies increases through the release of de-identified subject-level datasets.
  • The atlas supports longitudinal analysis of brain maturation across the second and third trimesters.

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

  • Individual fetal scans could be compared against the atlas trajectories to flag early deviations linked to later neurodevelopmental issues.
  • Extending the same registration approach to a wider gestational range or adding diffusion and functional data would test whether the current templates generalize.
  • The released datasets could serve as training material for other machine-learning models aimed at fetal brain analysis.

Load-bearing premise

The 159 fetuses with typically developing brains form a representative sample whose aligned images, after diffeomorphic registration and kernel regression on gestational age, accurately reflect continuous population-level developmental trajectories without systematic bias from subject selection or registration artifacts.

What would settle it

An independent validation study that applies the CRL-2025 templates and FetalSEG tool to a new cohort of fetal MRIs and finds large discrepancies between automated labels and expert manual segmentations in multiple regions.

Figures

Figures reproduced from arXiv: 2508.15034 by Abdelhakim Ouaalam, Ali Gholipour, Caitlin K. Rollins, Camilo Calixto, Camilo Jaimes, Clemente Velasco-Annis, Jian Wang, Lana Vasung, Mahdi Bagheri, Onur Afacan, Razieh Faghihpirayesh, Shadab Khan, Simon K. Warfield.

Figure 1
Figure 1. Figure 1: Frequency distribution of subjects contributed to atlas construction at each gestational age point in weeks. Pre-processing of T2w Images Pre-processing of structural T2-weighted HASTE scans, illustrated in the top row of Fig.2, included the following steps: 1. Individual stacks were excluded if severe fetal or maternal motion persisted throughout the stack or image artifacts obscured the fetal brain; 2. S… view at source ↗
Figure 2
Figure 2. Figure 2: Overview of fetal MRI processing for spatiotemporal atlas generation a) Spatiotemporal anatomical atlas generation process based on fast T2-weighted MRI scans; b) Spatiotemporal diffusion MRI atlas generation process based on 1) motion-tracking based slice-to-volume registration for robust diffusion tensor image reconstruction52, 2) diffusion tensor atlas construction24, and 3) diffusion tensor atlas label… view at source ↗
Figure 3
Figure 3. Figure 3: Comparison of spatiotemporal fetal brain MRI atlases ( CRL-2025 vs. CRL-2017) at six representative gestational ages: 22, 25, 28, 31, 34, and 37 weeks. Axial, coronal, and sagittal views are presented for each atlas at each age. Labels were generated on the spatiotemporal fetal brain MRI atlases following the procedure described in the Methods section. As illustrated in [PITH_FULL_IMAGE:figures/full_fig_p… view at source ↗
Figure 4
Figure 4. Figure 4: Tissue and regional segmentations and structural labels overlaid on axial views of the CRL-2025 spatiotemporal fetal brain MRI atlas at six representative gestational age (GA) weeks. All label schemes have subcortical structures including lentiform and caudate nuclei, internal capsules, thalami, and hippocampi separately on each hemisphere. Tissue segmentation labels (middle row) delineate the cortical pla… view at source ↗
Figure 5
Figure 5. Figure 5: Diffusion Atlas, gestational age (GA) weeks 23-35. Top row: Color fractional anisotropy (FA). Middle row: Tissue segmentation. Bottom row: Regional segmentation. weaker on the FeTA data. This could have several sources: first, the FeTA data intentionally include low-quality reconstructed images (images with motion artifacts and those reconstructed from thick-slice acquisitions) and also include images from… view at source ↗
Figure 6
Figure 6. Figure 6: presents boxplots of the DSC across the 31 segmentation regions for the BCH test subjects. The results indicate relatively reliable automatic segmentations were achieved by all models for most of the major structures such as the cortical plate, subplate, CSF, ventricles, corpus callosum, and thalamus. On the other hand, segmentations were more difficult, with lower DSCs and higher HDs, for small and/or cha… view at source ↗
read the original abstract

Characterizing in-utero brain development is essential for understanding typical and atypical neurodevelopment. Building on prior spatiotemporal fetal brain MRI atlases, we present the CRL-2025 fetal brain atlas, a spatiotemporal (4D) atlas of the developing fetal brain between 21 and 37 gestational weeks. This atlas is constructed from MRI scans of 159 fetuses with typically developing brains using a diffeomorphic deformable registration framework integrated with kernel regression on age. CRL-2025 uniquely includes detailed tissue segmentations, transient white matter compartments, and parcellation into 126 anatomical regions. It offers significantly enhanced anatomical details over the CRL-2017 atlas and is presented along with a re-release of the CRL diffusion MRI atlas featuring newly created tissue segmentation and labels. We release de-identified, processed subject-level fetal MRI datasets used to generate CRL-2025, providing input-output transparency and reproducibility. We also provide FetalSEG, a deep learning-based multiclass segmentation tool to facilitate automatic fetal brain MRI segmentation. The CRL-2025 atlas and its tools enable scalable fetal brain MRI segmentation, analysis, and neurodevelopmental research for the broader community.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Referee Report

3 major / 1 minor

Summary. The paper claims to introduce the CRL-2025 spatiotemporal (4D) atlas of the human fetal brain from 21 to 37 gestational weeks, constructed from MRI scans of 159 fetuses with typically developing brains using a diffeomorphic deformable registration framework combined with kernel regression on gestational age. It includes detailed tissue segmentations, transient white matter compartments, and parcellation into 126 anatomical regions, offering enhanced anatomical details compared to the CRL-2017 atlas. The work also re-releases the CRL diffusion MRI atlas with new segmentations and provides the FetalSEG deep learning tool for automatic segmentation, along with releasing the processed subject-level datasets for reproducibility.

Significance. If the central claims hold, this atlas would represent a significant advancement in fetal neuroimaging by providing higher-resolution anatomical detail and comprehensive labels for studying in-utero brain development. The inclusion of transient white matter compartments and fine parcellation could facilitate more precise analyses of neurodevelopmental trajectories. Strengths include the release of de-identified processed datasets and the open-source FetalSEG segmentation tool, which promote reproducibility and community use.

major comments (3)
  1. The construction relies on diffeomorphic registration and kernel regression, but no quantitative validation metrics such as landmark-based Dice coefficients, Jacobian determinant statistics, or cross-validation error on held-out subjects are provided to confirm that registration artifacts do not distort fine-scale structures or that the atlas accurately captures population-level trajectories.
  2. Detailed per-week sample sizes, inclusion/exclusion criteria, and any assessment of cohort representativeness are not reported, which is critical to evaluate potential systematic biases from subject selection or uneven age distribution in the 159 fetuses.
  3. The claim of 'significantly enhanced anatomical details' over the CRL-2017 atlas lacks supporting quantitative comparison statistics, error maps, or direct side-by-side metrics in the results.
minor comments (1)
  1. The abstract mentions 'significantly enhanced anatomical details' without specifying the nature of the enhancement or providing a brief quantitative indicator.

Simulated Author's Rebuttal

3 responses · 0 unresolved

We thank the referee for their detailed and constructive review of our manuscript on the CRL-2025 fetal brain atlas. We address each of the major comments below and indicate the revisions we will make to improve the paper.

read point-by-point responses

  1. Referee: The construction relies on diffeomorphic registration and kernel regression, but no quantitative validation metrics such as landmark-based Dice coefficients, Jacobian determinant statistics, or cross-validation error on held-out subjects are provided to confirm that registration artifacts do not distort fine-scale structures or that the atlas accurately captures population-level trajectories.

    Authors: We agree that quantitative validation metrics would enhance the credibility of the atlas construction. In the revised manuscript, we will add results from a cross-validation experiment on held-out subjects, reporting Dice coefficients for major tissue classes and structures. We will also include statistics on the Jacobian determinants to demonstrate that deformations are smooth and do not introduce artifacts. Landmark-based validation is limited in fetal MRI due to the absence of clear anatomical landmarks, but we will incorporate age-prediction accuracy as an indirect measure of trajectory capture. revision: yes

  2. Referee: Detailed per-week sample sizes, inclusion/exclusion criteria, and any assessment of cohort representativeness are not reported, which is critical to evaluate potential systematic biases from subject selection or uneven age distribution in the 159 fetuses.

    Authors: This is a valid concern. We will revise the methods section to include a detailed breakdown of the number of subjects per gestational week, explicitly state the inclusion and exclusion criteria (such as gestational age range, absence of known neurological conditions, and quality control for MRI scans), and provide an assessment of cohort representativeness, including any available demographic information and discussion of potential biases. revision: yes

  3. Referee: The claim of 'significantly enhanced anatomical details' over the CRL-2017 atlas lacks supporting quantitative comparison statistics, error maps, or direct side-by-side metrics in the results.

    Authors: We acknowledge that the claim would benefit from quantitative support. In the revision, we will include a direct comparison section with metrics such as the increase in the number of parcellated regions (from previous to 126), volume overlap or difference maps for key structures, and Dice similarity coefficients between segmentations from both atlases where applicable. Side-by-side figures will be supplemented with these statistics. revision: yes

Circularity Check

0 steps flagged

No circularity: atlas derived from primary data via standard registration and regression

full rationale

The paper constructs the CRL-2025 atlas directly from MRI scans of 159 fetuses using a diffeomorphic deformable registration framework integrated with kernel regression on gestational age. This process uses primary input data and standard techniques without any equations or steps that reduce the output to fitted parameters or results from the authors' prior work by construction. References to the CRL-2017 atlas are for comparison of enhanced detail only and are not load-bearing for the derivation chain. The release of subject-level datasets further supports independent verification. No self-definitional, fitted-prediction, or self-citation reductions are present in the described methods.

Axiom & Free-Parameter Ledger

0 free parameters · 2 axioms · 0 invented entities

The construction rests on standard image-registration assumptions and kernel regression for age; no free parameters or new entities are specified in the abstract.

axioms (2)
  • domain assumption Diffeomorphic deformable registration can align fetal brain MRI scans across gestational ages while preserving topology
    Invoked to build the spatiotemporal average from the 159 subject scans.
  • domain assumption Kernel regression on gestational age produces a continuous 4D atlas from discrete subject data
    Used to interpolate the atlas between 21 and 37 weeks.

pith-pipeline@v0.9.0 · 5794 in / 1413 out tokens · 78852 ms · 2026-05-18T21:48:07.465135+00:00 · methodology

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Lean theorems connected to this paper

Citations machine-checked in the Pith Canon. Every link opens the source theorem in the public Lean library.

What do these tags mean?
matches
The paper's claim is directly supported by a theorem in the formal canon.
supports
The theorem supports part of the paper's argument, but the paper may add assumptions or extra steps.
extends
The paper goes beyond the formal theorem; the theorem is a base layer rather than the whole result.
uses
The paper appears to rely on the theorem as machinery.
contradicts
The paper's claim conflicts with a theorem or certificate in the canon.
unclear
Pith found a possible connection, but the passage is too broad, indirect, or ambiguous to say the theorem truly supports the claim.

Reference graph

Works this paper leans on

81 extracted references · 81 canonical work pages · 1 internal anchor

  1. [1]

    & Barone Jr, S

    Rice, D. & Barone Jr, S. Critical periods of vulnerability for the developing nervous system: evidence from humans and animal models. Environmental health perspectives 108, 511–533 (2000)

    work page 2000

  2. [2]

    & Inder, T

    Rees, S. & Inder, T. Fetal and neonatal origins of altered brain development. Early human development 81, 753–761 (2005)

    work page 2005

  3. [3]

    O’Donnell, K. J. & Meaney, M. J. Fetal origins of mental health: the developmental origins of health and disease hypothesis. American Journal of Psychiatry 174, 319–328 (2017)

    work page 2017

  4. [4]

    Van den Bergh, B. R. et al. Prenatal developmental origins of behavior and mental health: The influence of maternal stress in pregnancy. Neuroscience & Biobehavioral Reviews 117, 26–64 (2020)

    work page 2020

  5. [5]

    Lautarescu, A., Craig, M. C. & Glover, V . Prenatal stress: Effects on fetal and child brain development. International review of neurobiology 150, 17–40 (2020)

    work page 2020

  6. [6]

    & Limperopoulos, C

    Wu, Y ., De Asis-Cruz, J. & Limperopoulos, C. Brain structural and functional outcomes in the offspring of women experiencing psychological distress during pregnancy. Molecular psychiatry 29, 2223–2240 (2024)

    work page 2024

  7. [7]

    V olpe, J. J. Perinatal brain injury: from pathogenesis to neuroprotection.Mental retardation and developmental disabilities research reviews7, 56–64 (2001)

    work page 2001

  8. [8]

    Fetal origin of brain dysmaturation in congenital heart disease–challenges and opportunities for interventions

    V olpe, J. Fetal origin of brain dysmaturation in congenital heart disease–challenges and opportunities for interventions. Journal of Neonatal-Perinatal Medicine 15, 489–494 (2022)

    work page 2022

  9. [9]

    Sidman, R. L. & Rakic, P. Neuronal migration, with special reference to developing human brain: a review. Brain research 62, 1–35 (1973)

    work page 1973

  10. [10]

    Specification of cerebral cortical areas

    Rakic, P. Specification of cerebral cortical areas. Science 241, 170–176 (1988)

    work page 1988

  11. [11]

    & Hrabaˇc, P

    Kostovi´c, I., Judaˇs, M., Radoˇs, M. & Hrabaˇc, P. Laminar organization of the human fetal cerebrum revealed by histochemical markers and magnetic resonance imaging. Cerebral Cortex 12, 536–544 (2002)

    work page 2002

  12. [12]

    & Kostovi´c, I

    Radoˇs, M., Judaˇs, M. & Kostovi´c, I. In vitro MRI of brain development. European journal of radiology 57, 187–198 (2006)

    work page 2006

  13. [13]

    & Juda ˇs, M

    Kostovi´c, I. & Juda ˇs, M. Transient patterns of cortical lamination during prenatal life: do they have implications for treatment? Neuroscience & Biobehavioral Reviews 31, 1157–1168 (2007)

    work page 2007

  14. [14]

    & Rakic, P

    Bystron, I., Blakemore, C. & Rakic, P. Development of the human cerebral cortex: Boulder committee revisited. Nature Reviews Neuroscience 9, 110–122 (2008)

    work page 2008

  15. [15]

    & Vasung, L

    Kostovic, I. & Vasung, L. Insights from in vitro fetal magnetic resonance imaging of cerebral development. In Seminars in perinatology, vol. 33, 220–233 (Elsevier, 2009)

    work page 2009

  16. [16]

    Ball, G. et al. Development of cortical microstructure in the preterm human brain. Proceedings of the National Academy of Sciences 110, 9541–9546 (2013)

    work page 2013

  17. [17]

    Kostovi´c, I. et al. Perinatal and early postnatal reorganization of the subplate and related cellular compartments in the human cerebral wall as revealed by histological and MRI approaches. Brain Structure and Function 219, 231–253 (2014)

    work page 2014

  18. [18]

    Vasung, L. et al. Quantitative and qualitative analysis of transient fetal compartments during prenatal human brain development. Frontiers in neuroanatomy10 (2016)

    work page 2016

  19. [19]

    Habas, P. A. et al. A spatiotemporal atlas of mr intensity, tissue probability and shape of the fetal brain with application to segmentation. Neuroimage 53, 460–470 (2010)

    work page 2010

  20. [20]

    Serag, A. et al. Construction of a consistent high-definition spatio-temporal atlas of the developing brain using adaptive kernel regression. Neuroimage 59, 2255–2265 (2012)

    work page 2012

  21. [21]

    Dittrich, E. et al. A spatio-temporal latent atlas for semi-supervised learning of fetal brain segmentations and morphological age estimation. Medical image analysis 18, 9–21 (2014)

    work page 2014

  22. [22]

    Gholipour, A. et al. A normative spatiotemporal mri atlas of the fetal brain for automatic segmentation and analysis of early brain growth. Scientific reports 7, 476 (2017)

    work page 2017

  23. [23]

    Schuh, A. et al. Unbiased construction of a temporally consistent morphological atlas of neonatal brain development. BioRxiv 251512 (2018)

    work page 2018

  24. [24]

    Khan, S. et al. Fetal brain growth portrayed by a spatiotemporal diffusion tensor mri atlas computed from in utero images. NeuroImage 185, 593–608 (2019). 14/17

    work page 2019

  25. [25]

    Wu, J. et al. Age-specific structural fetal brain atlases construction and cortical development quantification for chinese population. Neuroimage 241, 118412 (2021)

    work page 2021

  26. [26]

    Calixto, C. et al. A detailed spatiotemporal atlas of the white matter tracts for the fetal brain. Proceedings of the National Academy of Sciences 122, e2410341121 (2025)

    work page 2025

  27. [27]

    Bethlehem, R. A. I., Seidlitz, J., White, S. R. et al. Brain charts for the human lifespan. Nature 604, 525–533 (2022)

    work page 2022

  28. [28]

    Calixto, C. et al. Advances in fetal brain imaging. Magnetic Resonance Imaging Clinics 32, 459–478 (2024)

    work page 2024

  29. [29]

    Vasung, L. et al. Cross-sectional observational study of typical in utero fetal movements using machine learning. Developmental neuroscience 45, 105–114 (2023)

    work page 2023

  30. [30]

    Rousseau, F. et al. Registration-based approach for reconstruction of high-resolution in utero fetal MR brain images. Academic Radiology 13, 1072 – 1081 (2006)

    work page 2006

  31. [31]

    Jiang, S. et al. MRI of moving subjects using multislice snapshot images with volume reconstruction (SVR): application to fetal, neonatal, and adult brain studies. Medical Imaging, IEEE Transactions on 26, 967–980 (2007)

    work page 2007

  32. [32]

    & Warfield, S

    Gholipour, A., Estroff, J. & Warfield, S. Robust super-resolution volume reconstruction from slice acquisitions: application to fetal brain MRI. Medical Imaging, IEEE Trans 29, 1739–1758 (2010)

    work page 2010

  33. [33]

    Kim, K. et al. Intersection based motion correction of multi-slice MRI for 3D in utero fetal brain image formation. IEEE transactions on medical imaging 29, 146 (2010)

    work page 2010

  34. [34]

    A., Hajnal, J

    Kuklisova-Murgasova, M., Quaghebeur, G., Rutherford, M. A., Hajnal, J. V . & Schnabel, J. A. Reconstruction of fetal brain MRI with intensity matching and complete outlier removal. Medical image analysis 16, 1550–1564 (2012)

    work page 2012

  35. [35]

    Tourbier, S. et al. An efficient total variation algorithm for super-resolution in fetal brain MRI with adaptive regularization. NeuroImage 118, 584–597 (2015)

    work page 2015

  36. [36]

    Kainz, B. et al. Fast V olume Reconstruction From Motion Corrupted Stacks of 2D Slices. Med Imaging, IEEE T 34, 1901–1913 (2015)

    work page 1901

  37. [37]

    Automated template-based brain localization and extraction for fetal brain mri reconstruction.NeuroImage 155, 460–472 (2017)

    Tourbier, S.et al. Automated template-based brain localization and extraction for fetal brain mri reconstruction.NeuroImage 155, 460–472 (2017)

    work page 2017

  38. [38]

    Ebner, M. et al. An automated framework for localization, segmentation and super-resolution reconstruction of fetal brain mri. NeuroImage 206, 116324 (2020)

    work page 2020

  39. [39]

    Uus, A. et al. Deformable slice-to-volume registration for motion correction of fetal body and placenta mri. IEEE transactions on medical imaging 39, 2750–2759 (2020)

    work page 2020

  40. [40]

    Uus, A. U. et al. Retrospective motion correction in foetal mri for clinical applications: existing methods, applications and integration into clinical practice. The British journal of radiology 96, 20220071 (2023)

    work page 2023

  41. [41]

    Xu, J. et al. Nesvor: implicit neural representation for slice-to-volume reconstruction in mri. IEEE transactions on medical imaging 42, 1707–1719 (2023)

    work page 2023

  42. [42]

    A dynamic 4D probabilistic atlas of the developing brain

    Kuklisova-Murgasova, M., Aljabar, P.et al. A dynamic 4D probabilistic atlas of the developing brain. NeuroImage 54, 2750–2763 (2011)

    work page 2011

  43. [43]

    Rueckert, D. et al. Nonrigid registration using free-form deformations: application to breast MR images. Medical Imaging, IEEE Transactions on 18, 712–721 (1999)

    work page 1999

  44. [44]

    Makropoulos, A. et al. Regional growth and atlasing of the developing human brain. NeuroImage 125, 456–478 (2016)

    work page 2016

  45. [45]

    Schuh, A. et al. Construction of a 4d brain atlas and growth model using diffeomorphic registration. In Spatio-temporal Image Analysis for Longitudinal and Time-Series Image Data, 27–37 (Springer, 2014)

    work page 2014

  46. [46]

    Ciceri, T. et al. Fetal brain mri atlases and datasets: A review. NeuroImage 120603 (2024)

    work page 2024

  47. [47]

    & Gee, J

    Avants, B., Epstein, C., Grossman, M. & Gee, J. Symmetric diffeomorphic image registration with cross-correlation: Evaluating automated labeling of elderly and neurodegenerative brain. Medical image analysis 12, 26 (2008)

    work page 2008

  48. [48]

    Namburete, A. I. et al. Normative spatiotemporal fetal brain maturation with satisfactory development at 2 years. Nature 623, 106–114 (2023)

    work page 2023

  49. [49]

    Urru, A. et al. An automatic pipeline for atlas-based fetal and neonatal brain segmentation and analysis. Computer methods and programs in biomedicine 230, 107334 (2023)

    work page 2023

  50. [50]

    Li, G. et al. Construction of 4d high-definition cortical surface atlases of infants: Methods and applications. Medical image analysis 25, 22–36 (2015). 15/17

    work page 2015

  51. [51]

    Fidon, L. et al. A dempster-shafer approach to trustworthy ai with application to fetal brain mri segmentation. IEEE transactions on pattern analysis and machine intelligence 46, 3784–3795 (2024)

    work page 2024

  52. [52]

    Marami, B. et al. Temporal slice registration and robust diffusion-tensor reconstruction for improved fetal brain structural connectivity analysis. NeuroImage 156, 475–488 (2017)

    work page 2017

  53. [53]

    N., Deng, H., Gholipour, A., Warfield, S

    Mallela, A. N., Deng, H., Gholipour, A., Warfield, S. K. & Goldschmidt, E. Heterogeneous growth of the insula shapes the human brain. Proceedings of the National Academy of Sciences 120, e2220200120 (2023)

    work page 2023

  54. [54]

    Calixto, C. et al. Characterizing microstructural development in the fetal brain using diffusion mri from 23 to 36 weeks of gestation. Cerebral Cortex 34, bhad409 (2024)

    work page 2024

  55. [55]

    Chen, R. et al. Deciphering the developmental order and microstructural patterns of early white matter pathways in a diffusion mri based fetal brain atlas. Neuroimage 264, 119700 (2022)

    work page 2022

  56. [56]

    Uus, A. et al. Multi-channel spatio-temporal mri atlas of the normal fetal brain development from the developing human connectome project. G-Node doi 10, 2023 (2023)

    work page 2023

  57. [57]

    Price, A. N. et al. The developing human connectome project (dhcp): fetal acquisition protocol. In Proceedings of the annual meeting of the International Society of Magnetic Resonance in Medicine (ISMRM), vol. 244 (International Society for Magnetic Resonance in Medicine (ISMRM), 2019)

    work page 2019

  58. [58]

    F., Kohl, S

    Isensee, F., Jaeger, P. F., Kohl, S. A., Petersen, J. & Maier-Hein, K. H. nnu-net: a self-configuring method for deep learning-based biomedical image segmentation. Nature methods 18, 203–211 (2021)

    work page 2021

  59. [59]

    Hatamizadeh, A., Yang, D., Roth, H. & Xu, D. Unetr: Transformers for 3d medical image segmentation. 2022 ieee. In CVF Winter Conference on Applications of Computer Vision (WACV), 1748–1758 (2021)

    work page 2022

  60. [60]

    Hatamizadeh, A. et al. Swin unetr: Swin transformers for semantic segmentation of brain tumors in mri images. In International MICCAI brainlesion workshop, 272–284 (Springer, 2021)

    work page 2021

  61. [61]

    Cao, H. et al. Swin-unet: Unet-like pure transformer for medical image segmentation. In European conference on computer vision, 205–218 (Springer, 2022)

    work page 2022

  62. [62]

    Liao, W. et al. Lightm-unet: Mamba assists in lightweight unet for medical image segmentation (2024). 2403.05246

    work page arXiv 2024

  63. [63]

    Tustison, N. J. et al. N4ITK: improved N3 bias correction. Medical Imaging, IEEE Transactions on 29, 1310–1320 (2010)

    work page 2010

  64. [64]

    F., Behrens, T

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

    work page 2012

  65. [65]

    Yushkevich, P. A.et al. User-guided 3D active contour segmentation of anatomical structures: significantly improved efficiency and reliability. Neuroimage 31, 1116–1128 (2006)

    work page 2006

  66. [66]

    & Ayache, N

    Arsigny, V ., Commowick, O., Pennec, X. & Ayache, N. A log-euclidean framework for statistics on diffeomorphisms. In International Conference on Medical Image Computing and Computer-Assisted Intervention, 924–931 (Springer, 2006)

    work page 2006

  67. [67]

    Rollins, C. K. et al. Regional brain growth trajectories in fetuses with congenital heart disease. Annals of neurology 89, 143–157 (2021)

    work page 2021

  68. [68]

    & Warfield, S

    Akhondi-Asl, A. & Warfield, S. Simultaneous truth and performance level estimation through fusion of probabilistic segmentations. Medical Imaging, IEEE Transactions on 32, 1840–1852 (2013)

    work page 2013

  69. [69]

    Gousias, I. S. et al. Magnetic resonance imaging of the newborn brain: automatic segmentation of brain images into 50 anatomical regions. PloS one 8, e59990 (2013)

    work page 2013

  70. [70]

    Blesa, M. et al. Parcellation of the healthy neonatal brain into 107 regions using atlas propagation through intermediate time points in childhood. Frontiers in neuroscience10 (2016)

    work page 2016

  71. [71]

    Vasung, L. et al. Quantitative in vivo mri assessment of structural asymmetries and sexual dimorphism of transient fetal compartments in the human brain. Cerebral Cortex 30, 1752–1767 (2020)

    work page 2020

  72. [72]

    Schnabel, J. A. et al. A generic framework for non-rigid registration based on non-uniform multi-level free-form deformations. In International Conference on Medical Image Computing and Computer-Assisted Intervention, 573–581 (Springer, 2001)

    work page 2001

  73. [73]

    Avants, B. B. et al. A reproducible evaluation of ANTs similarity metric performance in brain image registration. Neuroimage 54, 2033–2044 (2011)

    work page 2033

  74. [74]

    & Wells, W

    Warfield, S., Zou, K. & Wells, W. Simultaneous truth and performance level estimation (STAPLE): an algorithm for the validation of image segmentation. Medical Imaging, IEEE Transactions on 23, 903–921 (2004). 16/17

    work page 2004

  75. [75]

    Wang, H. et al. Multi-atlas segmentation with joint label fusion. IEEE transactions on pattern analysis and machine intelligence 35, 611–623 (2012)

    work page 2012

  76. [76]

    Gholipour, A., Akhondi-Asl, A., Estroff, J. A. & Warfield, S. K. Multi-atlas multi-shape segmentation of fetal brain mri for volumetric and morphometric analysis of ventriculomegaly. NeuroImage 60, 1819–1831 (2012)

    work page 2012

  77. [77]

    Decoupled Weight Decay Regularization

    Loshchilov, I. Decoupled weight decay regularization. arXiv preprint arXiv:1711.05101 (2017)

    work page internal anchor Pith review Pith/arXiv arXiv 2017

  78. [78]

    Payette, K. et al. An automatic multi-tissue human fetal brain segmentation benchmark using the fetal tissue annotation dataset. Scientific data 8, 167 (2021)

    work page 2021

  79. [79]

    Payette, K. et al. Fetal brain tissue annotation and segmentation challenge results. Medical image analysis 88, 102833 (2023)

    work page 2023

  80. [80]

    Payette, K. et al. Multi-center fetal brain tissue annotation (feta) challenge 2022 results. IEEE transactions on medical imaging (2024)

    work page 2022

Showing first 80 references.