{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,14]],"date-time":"2026-09-14T20:50:45Z","timestamp":1789419045868,"version":"build-2803163510"},"reference-count":33,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2025,12,18]],"date-time":"2025-12-18T00:00:00Z","timestamp":1766016000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Neurosci."],"abstract":"\n Introduction<\/jats:title>\n 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.<\/jats:p>\n <\/jats:sec>\n \n Methods<\/jats:title>\n \n 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 (\n BET<\/jats:italic>\n ,\n ROBEX<\/jats:italic>\n ,\n HD-BET<\/jats:italic>\n ,\n HD-BET-fast<\/jats:italic>\n ,\n SynthStrip<\/jats:italic>\n ,\n SynthStrip-noCSF<\/jats:italic>\n and\n d-SynthStrip<\/jats:italic>\n ). 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.\n <\/jats:p>\n <\/jats:sec>\n \n Results<\/jats:title>\n \n Only\n BET<\/jats:italic>\n ,\n HD-BET<\/jats:italic>\n ,\n HD-BET-fast<\/jats:italic>\n profited from data preprocessing. Considering this, all models had median Dice scores between 0.88 and 0.96, with\n SynthStrip<\/jats:italic>\n performing best. All models segmented most accurately in the middle axial slices of the brain. Resampling lowered the performance of all models, except\n ROBEX<\/jats:italic>\n . Mean computing times ranged from 2\u202fs (\n BET<\/jats:italic>\n ) to 132\u202fs (\n HD-BET<\/jats:italic>\n ) with\n SynthStrip<\/jats:italic>\n requiring 7\u202fs. per scan.\n SynthStrip<\/jats:italic>\n was prone to not entirely including the\n Sinus sagittalis superior<\/jats:italic>\n , the upper\n Cerebrum<\/jats:italic>\n , the temporal pole, the\n Cerebellum<\/jats:italic>\n and the\n Chiasma opticum<\/jats:italic>\n \/pituitary gland. In contrast, the petrous bone and the skull in the middle axial slices have often been partly included.\n <\/jats:p>\n <\/jats:sec>\n \n Discussion<\/jats:title>\n \n Due to its robustness and quick computation time, we recommend\n SynthStrip<\/jats:italic>\n for skull stripping of pediatric T2-weighted MRI scans. We attribute the observed segmentation errors to the partial volume effect, which should be addressed in future research. Limitations of our study include the monocentric setting, the exclusion of pathological cases and the skewed age distribution in our cohort.\n <\/jats:p>\n <\/jats:sec>","DOI":"10.3389\/fnins.2025.1715514","type":"journal-article","created":{"date-parts":[[2025,12,18]],"date-time":"2025-12-18T06:44:36Z","timestamp":1766040276000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Skull stripping tools in pediatric T2-weighted MRI scans: a retrospective evaluation of segmentation performance"],"prefix":"10.3389","volume":"19","author":[{"given":"Adrian","family":"Schulz","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Eric","family":"Dragendorf","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Katharina","family":"Wendt","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Andr\u00e9","family":"Schomakers","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Eva","family":"B\u00fcltmann","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dominik","family":"Wolff","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2025,12,18]]},"reference":[{"key":"ref1","doi-asserted-by":"publisher","first-page":"1245","DOI":"10.1016\/j.neurobiolaging.2005.05.023","article-title":"Normal neuroanatomical variation due to age: the major lobes and a parcellation of the temporal region","volume":"26","author":"Allen","year":"2005","journal-title":"Neurobiol. Aging"},{"key":"ref2","article-title":"Normal development of the fetal, neonatal, and infant brain, skull, and spine \u2013 milestones","volume-title":"Pediatric neuroimaging","author":"Barkovich","year":"2018"},{"key":"ref3","doi-asserted-by":"publisher","first-page":"64","DOI":"10.1016\/j.artmed.2018.08.008","article-title":"Deep convolutional neural networks for brain image analysis on magnetic resonance imaging: a review","volume":"95","author":"Bernal","year":"2019","journal-title":"Artif. Intell. Med."},{"key":"ref4","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1109\/SIPAIM56729.2023.10373445","article-title":"Comparative skull stripping techniques on pediatric magnetic resonance imaging","volume-title":"2023 19th International Symposium on Medical Information Processing and Analysis (SIPAIM)","author":"Das","year":"2023"},{"key":"ref5","doi-asserted-by":"publisher","first-page":"1496143","DOI":"10.3389\/fninf.2024.1496143","article-title":"Quantitative assessment of neurodevelopmental maturation: a comprehensive systematic literature review of artificial intelligence-based brain age prediction in pediatric populations","volume":"18","author":"Dragendorf","year":"2024","journal-title":"Front. Neuroinform."},{"key":"ref6","doi-asserted-by":"publisher","first-page":"110291","DOI":"10.1016\/j.ejrad.2022.110291","article-title":"Borrowing strength from adults: transferability of AI algorithms for paediatric brain and tumour segmentation","volume":"151","author":"Drai","year":"2022","journal-title":"Eur. J. Radiol."},{"key":"ref7","doi-asserted-by":"publisher","first-page":"2362","DOI":"10.1016\/j.neuroimage.2011.09.012","article-title":"BEaST: brain extraction based on nonlocal segmentation technique","volume":"59","author":"Eskildsen","year":"2012","journal-title":"NeuroImage"},{"key":"ref8","doi-asserted-by":"publisher","first-page":"1443","DOI":"10.1007\/s10278-020-00367-5","article-title":"State-of-the-art traditional to the machine- and deep-learning-based skull stripping techniques, models, and algorithms","volume":"33","author":"Fatima","year":"2020","journal-title":"J. Digit. Imaging"},{"key":"ref9","doi-asserted-by":"publisher","first-page":"1323","DOI":"10.1016\/j.mri.2012.05.001","article-title":"3D slicer as an image computing platform for the quantitative imaging network","volume":"30","author":"Fedorov","year":"2012","journal-title":"Magn. Reson. Imaging"},{"key":"ref10","doi-asserted-by":"publisher","first-page":"118610","DOI":"10.1016\/j.neuroimage.2021.118610","article-title":"A deep learning toolbox for automatic segmentation of subcortical limbic structures from MRI images","volume":"244","author":"Greve","year":"2021","journal-title":"NeuroImage"},{"key":"ref11","doi-asserted-by":"publisher","first-page":"119474","DOI":"10.1016\/j.neuroimage.2022.119474","article-title":"SynthStrip: skull-stripping for any brain image","volume":"260","author":"Hoopes","year":"2022","journal-title":"NeuroImage"},{"key":"ref12","doi-asserted-by":"publisher","first-page":"1617","DOI":"10.1109\/TMI.2011.2138152","article-title":"Robust brain extraction across datasets and comparison with publicly available methods","volume":"30","author":"Iglesias","year":"2011","journal-title":"IEEE Trans. Med. Imaging"},{"key":"ref13","doi-asserted-by":"publisher","first-page":"4952","DOI":"10.1002\/hbm.24750","article-title":"Automated brain extraction of multisequence MRI using artificial neural networks","volume":"40","author":"Isensee","year":"2019","journal-title":"Hum. Brain Mapp."},{"key":"ref14","doi-asserted-by":"publisher","first-page":"365","DOI":"10.1007\/s10278-015-9847-8","article-title":"Methods on skull stripping of MRI head scan images\u2014a review","volume":"29","author":"Kalavathi","year":"2016","journal-title":"J. Digit. Imaging"},{"key":"ref15","doi-asserted-by":"publisher","first-page":"1","DOI":"10.3352\/jeehp.2021.18.17","article-title":"Sample size determination and power analysis using the G*power software","volume":"18","author":"Kang","year":"2021","journal-title":"J. Educ. Eval. Health Prof."},{"key":"ref16","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1109\/ISBI56570.2024.10635307","article-title":"Boosting skull-stripping performance for pediatric brain images","volume-title":"2024 IEEE International Symposium on Biomedical Imaging (ISBI)","author":"Kelley","year":"2024"},{"key":"ref17","first-page":"7136","article-title":"Fuzzy connectedness image segmentation for newborn brain extraction in MR images","author":"Kobashi","year":"2013"},{"key":"ref18","doi-asserted-by":"publisher","first-page":"718","DOI":"10.1016\/j.neubiorev.2006.06.001","article-title":"Brain development in children and adolescents: insights from anatomical magnetic resonance imaging","volume":"30","author":"Lenroot","year":"2006","journal-title":"Neurosci. Biobehav. Rev."},{"key":"ref19","doi-asserted-by":"publisher","first-page":"802","DOI":"10.1007\/s10278-012-9460-z","article-title":"Skull stripping of neonatal brain MRI: using prior shape information with graph cuts","volume":"25","author":"Mahapatra","year":"2012","journal-title":"J. Digit. Imaging"},{"key":"ref20","volume-title":"Data from QIN GBM treatment response","author":"Mamonov","year":"2016"},{"key":"ref21","first-page":"1","article-title":"Quantification of pediatric brain development with X-ray CT images using 3D-CNN","author":"Morita","year":"2022"},{"key":"ref22","doi-asserted-by":"crossref","first-page":"719","DOI":"10.1007\/978-3-642-21227-7_67","article-title":"A hybrid approach to brain extraction from premature infant MRI","volume-title":"Image Analysis","author":"P\u00e9port\u00e9","year":"2011"},{"key":"ref23","doi-asserted-by":"publisher","first-page":"206","DOI":"10.1016\/j.dcn.2017.08.009","article-title":"Processing of structural neuroimaging data in young children: bridging the gap between current practice and state-of-the-art methods","volume":"33","author":"Phan","year":"2018","journal-title":"Dev. Cogn. Neurosci."},{"key":"ref24","doi-asserted-by":"publisher","first-page":"1773","DOI":"10.3390\/app10051773","article-title":"Conventional and deep learning methods for skull stripping in brain MRI","volume":"10","author":"Rehman","year":"2020","journal-title":"Appl. Sci."},{"key":"ref25","first-page":"234","article-title":"U-net: convolutional networks for biomedical image segmentation","volume-title":"Medical image computing and computer-assisted intervention \u2013 MICCAI 2015","author":"Ronneberger","year":"2015"},{"key":"ref26","doi-asserted-by":"publisher","first-page":"1763","DOI":"10.1213\/ANE.0000000000002864","article-title":"Correlation coefficients: appropriate use and interpretation","volume":"126","author":"Schober","year":"2018","journal-title":"Anesth. Analg."},{"key":"ref27","doi-asserted-by":"publisher","first-page":"23470","DOI":"10.1038\/srep23470","article-title":"Accurate learning with few atlases (ALFA): an algorithm for MRI neonatal brain extraction and comparison with 11 publicly available methods","volume":"6","author":"Serag","year":"2016","journal-title":"Sci. Rep."},{"key":"ref28","doi-asserted-by":"publisher","first-page":"856","DOI":"10.1006\/nimg.2000.0730","article-title":"Magnetic resonance image tissue classification using a partial volume model","volume":"13","author":"Shattuck","year":"2001","journal-title":"NeuroImage"},{"key":"ref29","doi-asserted-by":"publisher","first-page":"143","DOI":"10.1002\/hbm.10062","article-title":"Fast robust automated brain extraction","volume":"17","author":"Smith","year":"2002","journal-title":"Hum. Brain Mapp."},{"key":"ref30","doi-asserted-by":"publisher","first-page":"327","DOI":"10.1007\/s11065-010-9148-4","article-title":"The basics of brain development","volume":"20","author":"Stiles","year":"2010","journal-title":"Neuropsychol. Rev."},{"key":"ref31","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.ijmedinf.2008.09.002","article-title":"STARE-HI\u2014statement on reporting of evaluation studies in health informatics","volume":"78","author":"Talmon","year":"2009","journal-title":"Int. J. Med. Inform."},{"key":"ref32","doi-asserted-by":"publisher","first-page":"855","DOI":"10.4329\/wjr.v6.i11.855","article-title":"Partial volume effect modeling for segmentation and tissue classification of brain magnetic resonance images: a review","volume":"6","author":"Tohka","year":"2014","journal-title":"World J. Radiol."},{"key":"ref33","doi-asserted-by":"publisher","first-page":"1339","DOI":"10.3390\/app14041339","article-title":"Brain extraction methods in neonatal brain MRI and their effects on intracranial volumes","volume":"14","author":"Vaz","year":"2024","journal-title":"Appl. Sci."}],"container-title":["Frontiers in Neuroscience"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fnins.2025.1715514\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,18]],"date-time":"2025-12-18T06:44:38Z","timestamp":1766040278000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fnins.2025.1715514\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,18]]},"references-count":33,"alternative-id":["10.3389\/fnins.2025.1715514"],"URL":"https:\/\/doi.org\/10.3389\/fnins.2025.1715514","relation":{},"ISSN":["1662-453X"],"issn-type":[{"value":"1662-453X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,12,18]]},"article-number":"1715514"}}