Skull stripping tools in pediatric T2-weighted MRI scans - a retrospective evaluation of segmentation performance

Sep 28, 2026

Uploaded by Rizky

Evaluation of seven common skull stripping tools for pediatric brain extraction on T2-weighted MRI addresses the gap that most tools are neither targeted to T2-weighted data nor pediatric cohorts. Retrospective analysis used 199 scans from children under 5 years with manually labeled ground truth under expert neuroradiology quality control. Dice score, 95th percentile Hausdorff distance, sensitivity, specificity and computation time were quantified with and without preprocessing. SynthStrip showed the best overall performance but missed parts of key anatomical structures. Robustness and fast runtime support its recommendation.

LanguageEnglish

CategoryHealthcare

FormatPDF

Pages13

Reading Time33 min

AccessFree to download

Introduction

Methods

Results

Discussion

Keywords

TYPE Original Research PUBLISHED 18 December 2025 DOI 10.3389/fnins.2025.1715514 OPEN ACCESS EDITED BY Laura Cabral, University of Pittsburgh, United States REVIEWED BY Yuchuan Zhuang, AbbVie, United States Negar Noorizadeh, College of Medicine, University of Tennessee Health Science Center (UTHSC), United States *CORRESPONDENCE Adrian Schulz [adrian.schulz@plri.de](adrian.schulz@plri.de) †These authors have contributed equally to this work RECEIVED 29 September 2025 REVISED 26 November 2025 ACCEPTED 02 December 2025 PUBLISHED 18 December 2025 CITATION Schulz A, Dragendorf E, Wendt K, Schomakers A, Bültmann E and Wolff D (2025) Skull stripping tools in pediatric T2-weighted MRI scans: a retrospective evaluation of segmentation performance. Front. Neurosci. 19:1715514 . doi: 10.3389/fnins.2025.1715514 COPYRIGHT © 2025 Schulz, Dragendorf, Wendt, Schomakers, Bültmann and Wolff. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY) . The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms. Skull stripping tools in pediatric T2-weighted MRI scans: a retrospective evaluation of segmentation performance Adrian Schulz 1*, Eric Dragendorf 1, Katharina Wendt 1, André Schomakers 1, Eva Bültmann 2† and Dominik Wolff 1† 1Peter L. Reichertz Institute for Medical Informatics of TU Braunschweig and Hannover Medical School, Hannover Medical School, Hannover, Germany, 2Institute of Diagnostic and Interventional Neuroradiology, Hannover Medical School, Hannover, Germany Introduction: For brain maturity assessment of infants aged above 6 months, T2-weighted MRI scans are recommended. Prior to automated brain tissue analysis, skull stripping is typically applied. However, most skull stripping tools neither focus on T2-weighted scans nor on pediatric cohorts. Here, we present the evaluation results of seven common skull stripping tools in a comparably large pediatric cohort. Methods: This study is based on 199 T2-weighted scans of children under the age of 5 years retrospectively acquired from the clinical routine at Hannover Medical School. We established a manually labeled ground truth under quality control of a senior neuroradiologist specialized in pediatric neuroradiology and evaluated seven skull stripping tools (BET, ROBEX, HD-BET, HD-BET-fast, SynthStrip, SynthStrip-noCSF and d-SynthStrip) . Segmentation performance (Dice score, 95th percentile Hausdorff distance, sensitivity, specificity) and computation time were assessed on non-preprocessed and preprocessed scans (zero padding, contrast enhancement, artifact removal and normalization) as well as in different brain regions. For the best performing model, we manually assessed the top and bottom quartile of segmentations with respect to the integrity of different anatomical brain structures. Results: Only BET, HD-BET, HD-BET-fast profited from data preprocessing. Considering this, all models had median Dice scores between 0.88 and 0.96, with SynthStrip performing best. All models segmented most accurately in the middle axial slices of the brain. Resampling lowered the performance of all models, except ROBEX. Mean computing times ranged from 2 s (BET) to 132 s (HD-BET) with SynthStrip requiring 7 s. per scan. SynthStrip was prone to not entirely including the Sinus sagittalis superior, the upper Cerebrum, the temporal pole, the Cerebellum and the Chiasma opticum/pituitary gland. In contrast, the petrous bone and the skull in the middle axial slices have often been partly included. Discussion: Due to its robustness and quick computation time, we recommend SynthStrip for skull stripping of pediatric T2-we

FAQs

Why were skull stripping tools evaluated specifically for pediatric T2-weighted MRI scans?

T2-weighted MRI is recommended for brain maturity assessment in infants above 6 months, but most skull stripping tools do not focus on T2-weighted scans or pediatric cohorts. The study evaluates how common tools perform in this setting.

How was the study dataset and ground truth prepared?

The study used 199 retrospectively acquired T2-weighted scans from children under 5 years. A manually labeled ground truth was created under quality control by a senior neuroradiologist specialized in pediatric neuroradiology.

Which tool performed best and what were its common segmentation issues?

SynthStrip performed best in overall segmentation performance. It was prone to not entirely including structures such as the superior sagittal sinus, upper cerebrum, temporal pole, cerebellum, and the chiasma opticum/pituitary region.

Sep 28, 2026

Uploaded by Rizky