ClinSeg: Robust Brain Segmentation for Clinically Acquired Pediatric MRI
- 1Children's Hospital of Philadelphia
Abstract
Clinical brain MRIs from pediatric health systems represent a viable resource for modeling early neurodevelopmental trajectories and studying neurodevelopmental risk in real-world populations. However, a limitation to date has been the performance of existing segmentation tools for measuring various brain phenotypes in clinical scans. In particular, many tools underperform in infant scans due to morphological and physical changes such as rapid myelination. Here, we introduce ClinSeg: a robust segmentation approach tailored to early-life clinical MRIs with variable orientation, resolution, and contrast. We leverage existing registration and synthetic data generation tools to construct a training corpus for a 3d U-Net spanning anatomical and contrast diversity, including scans with morphological abnormalities from a pediatric hospital. Validated against manual segmentations, ClinSeg outperforms existing models in infancy while matching them in childhood and adolescence. Finally, ClinSeg enables the construction of reference brain growth trajectories in 11,699 individuals from 0-21 years of age, leading to the detection of more nuanced age-related findings in clinical groups.
Related
- Automated voxel-based prostate volumetry improves PSA density-based detection of clinically significant prostate cancer in the PSA gray zone: comparison with manual segmentation and the ellipsoid formula.
- Managing Pediatric Acquired Hemophilia A When Guideline-Recommended Bypassing Agents Are Unavailable: A Case Report
- Rehabilitation in Pediatric Patients with Acute and Subacute Acquired Brain Injury: A Scoping Review on Non-Pharmacological Interventions
- Time to recovery and its predictors among pediatric patients with severe community-acquired pneumonia admitted to public general hospitals in Tigray, Ethiopia, 2025: A prospective follow-up study
- Swin-WaveNet: frequency-guided boundary restoration for robust skin lesion segmentation.
BibTeX
@misc{levitis2026clinseg,
title = {{ClinSeg: Robust Brain Segmentation for Clinically Acquired Pediatric MRI}},
author = {E. Levitis and H. F. J. Tregidgo and D. Zimmerman and B. Jung and S. Karandikar and M. Gardner and P. Mattisson and E. Kafadar and A. Zapaishchykova and B. H. Kann and S. T. Sotardi and A. Vossough and H. Huang and B. Billot and J. E. Iglesias Gonzales and D. C. Alexander and A. F. Alexander-Bloch and J. Seidlitz},
howpublished = {medRxiv},
year = {2026},
month = aug,
doi = {10.64898/2026.08.28.26361643},
url = {https://www.medrxiv.org/content/10.64898/2026.08.28.26361643v1},
note = {CC BY-NC},
}
RIS
TY - UNPB
TI - ClinSeg: Robust Brain Segmentation for Clinically Acquired Pediatric MRI
AU - E. Levitis
AU - H. F. J. Tregidgo
AU - D. Zimmerman
AU - B. Jung
AU - S. Karandikar
AU - M. Gardner
AU - P. Mattisson
AU - E. Kafadar
AU - A. Zapaishchykova
AU - B. H. Kann
AU - S. T. Sotardi
AU - A. Vossough
AU - H. Huang
AU - B. Billot
AU - J. E. Iglesias Gonzales
AU - D. C. Alexander
AU - A. F. Alexander-Bloch
AU - J. Seidlitz
PY - 2026
DA - 2026/08/28
PB - medRxiv
DO - 10.64898/2026.08.28.26361643
UR - https://www.medrxiv.org/content/10.64898/2026.08.28.26361643v1
AB - Clinical brain MRIs from pediatric health systems represent a viable resource for modeling early neurodevelopmental trajectories and studying neurodevelopmental risk in real-world populations. However, a limitation to date has been the performance of existing segmentation tools for measuring various brain phenotypes in clinical scans. In particular, many tools underperform in infant scans due to morphological and physical changes such as rapid myelination. Here, we introduce ClinSeg: a robust segmentation approach tailored to early-life clinical MRIs with variable orientation, resolution, and contrast. We leverage existing registration and synthetic data generation tools to construct a training corpus for a 3d U-Net spanning anatomical and contrast diversity, including scans with morphological abnormalities from a pediatric hospital. Validated against manual segmentations, ClinSeg outperforms existing models in infancy while matching them in childhood and adolescence. Finally, ClinSeg enables the construction of reference brain growth trajectories in 11,699 individuals from 0-21 years of age, leading to the detection of more nuanced age-related findings in clinical groups.
ER -