{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,16]],"date-time":"2026-09-16T06:04:54Z","timestamp":1789538694588,"version":"build-2803163510"},"reference-count":46,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,9,16]],"date-time":"2026-09-16T00:00:00Z","timestamp":1789516800000},"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. Aging Neurosci."],"abstract":"<jats:sec>\n                    <jats:title>Objective<\/jats:title>\n                    <jats:p>White matter hyperintensities (WMH) are key neuroimaging markers of cerebral small vessel disease, associated with cognitive decline and stroke risk. Accurate quantification is essential yet manual segmentation is time-consuming and variable. We systematically evaluated AI performance for automated WMH segmentation across disease contexts and identified factors influencing model performance.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>Following PRISMA guidelines, we searched PubMed, Embase, Web of Science, Scopus, and IEEE Xplore from database inception to February 3, 2026 (PROSPERO: CRD420261355769). Studies employing AI-based WMH segmentation and reporting Dice similarity coefficient (DSC) were included. A random-effects meta-analysis was conducted, along with subgroup analyses, meta-regression, sensitivity analyses, and publication bias assessment.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>\n                      26 studies comprising 4,288 participants contributed to quantitative syntheses: 13 evaluated WMH segmentation in general cohorts, and 13 evaluated AD or CSVD-specific cohorts. In the general cohort meta-analysis, the pooled DSC was 0.78 (95% CI, 0.74\u20130.82). Disease-specific pooled DSC estimates were 0.75 for AD and 0.78 for CSVD. Exploratory meta-regression suggested an association between scanning parameters and DSC (\n                      <jats:italic>p<\/jats:italic>\n                      =\u202f0.042), whereas magnetic field strength showed a borderline association (\n                      <jats:italic>p<\/jats:italic>\n                      =\u202f0.052).\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>AI demonstrates promising performance for automated WMH segmentation, with U-Net\u2013based architectures showing superior accuracy. However, substantial heterogeneity highlights the need for standardized imaging protocols and robust external validation. Future multicenter studies are essential to improve model generalizability and facilitate clinical translation.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fnagi.2026.1930675","type":"journal-article","created":{"date-parts":[[2026,9,16]],"date-time":"2026-09-16T05:32:30Z","timestamp":1789536750000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Artificial intelligence for white matter hyperintensity segmentation: performance, determinants, and clinical implications"],"prefix":"10.3389","volume":"18","author":[{"given":"Jinhua","family":"Hu","sequence":"first","affiliation":[{"name":"Department of Radiology, Affiliated Hospital of Youjiang Medical University for Nationalities","place":["Baise, China"]},{"name":"School of Medical Laboratory Science, Affiliated Hospital of Youjiang Medical University for Nationalities","place":["Baise, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhihao","family":"Zhang","sequence":"additional","affiliation":[{"name":"Department of Radiology, Affiliated Hospital of Youjiang Medical University for Nationalities","place":["Baise, China"]},{"name":"School of Medical Laboratory Science, Affiliated Hospital of Youjiang Medical University for Nationalities","place":["Baise, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Peng","family":"Lei","sequence":"additional","affiliation":[{"name":"Department of Radiology, Affiliated Hospital of Youjiang Medical University for Nationalities","place":["Baise, China"]},{"name":"School of Medical Laboratory Science, Affiliated Hospital of Youjiang Medical University for Nationalities","place":["Baise, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jupeng","family":"Zhang","sequence":"additional","affiliation":[{"name":"Department of Radiology, Affiliated Hospital of Youjiang Medical University for Nationalities","place":["Baise, China"]},{"name":"School of Medical Laboratory Science, Affiliated Hospital of Youjiang Medical University for Nationalities","place":["Baise, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiqi","family":"Zhu","sequence":"additional","affiliation":[{"name":"Department of Radiology, Affiliated Hospital of Youjiang Medical University for Nationalities","place":["Baise, China"]},{"name":"Guangxi Key Laboratory of Artificial Intelligence for Genetic Diseases of Long-dwelling Nationalities","place":["Baise, Guangxi, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Baosheng","family":"Li","sequence":"additional","affiliation":[{"name":"Department of Radiology, Affiliated Hospital of Youjiang Medical University for Nationalities","place":["Baise, China"]},{"name":"Guangxi Key Laboratory of Artificial Intelligence for Genetic Diseases of Long-dwelling Nationalities","place":["Baise, Guangxi, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,9,16]]},"reference":[{"key":"ref1","doi-asserted-by":"publisher","first-page":"e220232","DOI":"10.1148\/ryai.220232","article-title":"A guide to cross-validation for artificial intelligence in medical imaging","volume":"5","author":"Bradshaw","year":"2023","journal-title":"Radiol. Artif. Intell."},{"key":"ref2","doi-asserted-by":"publisher","first-page":"e70553","DOI":"10.1002\/alz.70553","article-title":"Long-term impact of white matter hyperintensities and amyloid beta on thalamic subregions in cerebral small vessel disease: a prospective cohort study","volume":"21","author":"Cheng","year":"2025","journal-title":"Alzheimers Dement."},{"key":"ref3","doi-asserted-by":"publisher","first-page":"602","DOI":"10.1016\/S1474-4422(23)00131-X","article-title":"Neuroimaging standards for research into small vessel disease-advances since 2013","volume":"22","author":"Duering","year":"2023","journal-title":"Lancet Neurol."},{"key":"ref4","volume-title":"2023 International Conference on Computer Science, Information Technology and Engineering (ICCoSITE)","author":"Eldianto","year":"2023"},{"key":"ref5","doi-asserted-by":"publisher","first-page":"429","DOI":"10.1007\/s12021-019-09439-6","article-title":"Automated white matter hyperintensity segmentation using Bayesian model selection: assessment and correlations with cognitive change","volume":"18","author":"Fiford","year":"2020","journal-title":"Neuroinformatics"},{"key":"ref6","doi-asserted-by":"publisher","first-page":"121279","DOI":"10.1016\/j.neuroimage.2025.121279","article-title":"A robust automated segmentation method for white matter hyperintensity of vascular-origin","volume":"315","author":"He","year":"2025","journal-title":"NeuroImage"},{"key":"ref7","doi-asserted-by":"publisher","first-page":"16742","DOI":"10.1038\/s41598-019-52966-0","article-title":"Performance of five automated white matter hyperintensity segmentation methods in a multicenter dataset","volume":"9","author":"Heinen","year":"2019","journal-title":"Sci. Rep."},{"key":"ref8","doi-asserted-by":"publisher","first-page":"1481","DOI":"10.1002\/hbm.25739","article-title":"Performance of three freely available methods for extracting white matter hyperintensities: FreeSurfer, UBO detector, and BIANCA","volume":"43","author":"Hotz","year":"2022","journal-title":"Hum. Brain Mapp."},{"key":"ref9","doi-asserted-by":"publisher","first-page":"1344","DOI":"10.1002\/hbm.26109","article-title":"Semisupervised white matter hyperintensities segmentation on MRI","volume":"44","author":"Huang","year":"2023","journal-title":"Hum. Brain Mapp."},{"key":"ref10","doi-asserted-by":"publisher","first-page":"e27398","DOI":"10.1016\/j.heliyon.2024.e27398","article-title":"Reviewing 3D convolutional neural network approaches for medical image segmentation","volume":"10","author":"Ilesanmi","year":"2024","journal-title":"Heliyon"},{"key":"ref11","doi-asserted-by":"publisher","first-page":"630","DOI":"10.1136\/jnnp-2025-337689","article-title":"Clinically reported covert cerebrovascular disease and risk of neurological disease: a whole-population cohort of 367 988 people using natural language processing","volume":"97","author":"Iveson","year":"2026","journal-title":"J. Neurol. Neurosurg. Psychiatry"},{"key":"ref12","doi-asserted-by":"publisher","first-page":"660","DOI":"10.1177\/0271678X241235494","article-title":"Sporadic cerebral small vessel disease and cognitive decline in healthy older adults: a systematic review and meta-analysis","volume":"44","author":"Jansma","year":"2024","journal-title":"J. Cereb. Blood Flow Metab."},{"key":"ref13","doi-asserted-by":"publisher","first-page":"4812","DOI":"10.1007\/s00330-025-12174-z","article-title":"Development and validation of a deep learning-based automatic segmentation and classification of cerebral white matter hyperintensities","volume":"36","author":"Jeong","year":"2025","journal-title":"Eur. Radiol."},{"key":"ref14","doi-asserted-by":"publisher","first-page":"225","DOI":"10.1159\/000548650","article-title":"Association between intracerebral artery stenosis and cortical infarcts, lacunes, white matter hyperintensities and brain atrophy: results from a population-based study","volume":"15","author":"Johnsen","year":"2025","journal-title":"Cerebrovasc. Dis. Extra"},{"key":"ref15","doi-asserted-by":"publisher","first-page":"101851","DOI":"10.1016\/j.media.2020.101851","article-title":"Boundary loss for highly unbalanced segmentation","volume":"67","author":"Kervadec","year":"2021","journal-title":"Med. Image Anal."},{"key":"ref16","doi-asserted-by":"publisher","first-page":"2556","DOI":"10.1109\/TMI.2019.2905770","article-title":"Standardized assessment of automatic segmentation of white matter hyperintensities and results of the WMH segmentation challenge","volume":"38","author":"Kuijf","year":"2019","journal-title":"IEEE Trans. Med. Imaging"},{"key":"ref17","doi-asserted-by":"publisher","first-page":"929","DOI":"10.1002\/hbm.25695","article-title":"White matter hyperintensities segmentation using an ensemble of neural networks","volume":"43","author":"Li","year":"2022","journal-title":"Hum. Brain Mapp."},{"key":"ref18","doi-asserted-by":"publisher","first-page":"101873","DOI":"10.1016\/j.compmedimag.2021.101873","article-title":"An anatomical knowledge-based MRI deep learning pipeline for white matter hyperintensity quantification associated with cognitive impairment","volume":"89","author":"Liang","year":"2021","journal-title":"Comput. Med. Imaging Graph."},{"key":"ref19","volume-title":"ACM International Conference Proceeding Series","author":"Lo","year":"2024"},{"key":"ref20","doi-asserted-by":"publisher","first-page":"195","DOI":"10.1038\/s41592-023-02151-z","article-title":"Metrics reloaded: recommendations for image analysis validation","volume":"21","author":"Maier-Hein","year":"2024","journal-title":"Nat. Methods"},{"key":"ref21","doi-asserted-by":"publisher","first-page":"388","DOI":"10.1001\/jama.2017.19163","article-title":"Preferred reporting items for a systematic review and meta-analysis of diagnostic test accuracy studies: the PRISMA-DTA statement","volume":"319","author":"McInnes","year":"2018","journal-title":"JAMA"},{"key":"ref22","doi-asserted-by":"publisher","first-page":"2089","DOI":"10.1002\/hbm.25784","article-title":"Deep Bayesian networks for uncertainty estimation and adversarial resistance of white matter hyperintensity segmentation","volume":"43","author":"Mojiri Forooshani","year":"2022","journal-title":"Hum. Brain Mapp."},{"key":"ref23","doi-asserted-by":"publisher","first-page":"e200029","DOI":"10.1148\/ryai.2020200029","article-title":"Checklist for artificial intelligence in medical imaging (CLAIM): a guide for authors and reviewers","volume":"2","author":"Mongan","year":"2020","journal-title":"Radiol. Artif. Intell."},{"key":"ref24","doi-asserted-by":"publisher","first-page":"24","DOI":"10.47936\/encephalitis.2022.00108","article-title":"Improving performance robustness of subject-based brain segmentation software","volume":"3","author":"Park","year":"2023","journal-title":"Encephalitis"},{"key":"ref25","volume-title":"ACM International Conference Proceeding Series","author":"Pham","year":"2021"},{"key":"ref26","doi-asserted-by":"publisher","first-page":"368504261432413","DOI":"10.1177\/00368504261432413","article-title":"MSA(2)-net: utilizing self-adaptive convolution module to extract multi-scale information in medical image segmentation","volume":"109","author":"Qin","year":"2026","journal-title":"Sci. Prog."},{"key":"ref27","doi-asserted-by":"publisher","first-page":"121515","DOI":"10.1016\/j.neuroimage.2025.121515","article-title":"White matter hyperintensity-associated iron overload links glymphatic system dysfunction to cognitive impairment in cerebral small vessel disease","volume":"321","author":"Qiu","year":"2025","journal-title":"NeuroImage"},{"key":"ref28","doi-asserted-by":"publisher","first-page":"28","DOI":"10.1016\/j.compmedimag.2018.02.002","article-title":"Segmentation of white matter hyperintensities using convolutional neural networks with global spatial information in routine clinical brain MRI with none or mild vascular pathology","volume":"66","author":"Rachmadi","year":"2018","journal-title":"Comput. Med. Imaging Graph."},{"key":"ref29","doi-asserted-by":"publisher","first-page":"963","DOI":"10.1016\/j.neuroimage.2010.09.013","article-title":"Lesion explorer: a comprehensive segmentation and parcellation package to obtain regional volumetrics for subcortical hyperintensities and intracranial tissue","volume":"54","author":"Ramirez","year":"2011","journal-title":"NeuroImage"},{"key":"ref30","doi-asserted-by":"publisher","first-page":"182","DOI":"10.1038\/s41592-023-02150-0","article-title":"Understanding metric-related pitfalls in image analysis validation","volume":"21","author":"Reinke","year":"2024","journal-title":"Nat. Methods"},{"key":"ref31","doi-asserted-by":"publisher","first-page":"720","DOI":"10.3390\/brainsci11060720","article-title":"Semi-supervised learning in medical MRI segmentation: brain tissue with white matter hyperintensity segmentation using FLAIR MRI","volume":"11","author":"Rieu","year":"2021","journal-title":"Brain Sci."},{"key":"ref32","doi-asserted-by":"publisher","first-page":"e0285683","DOI":"10.1371\/journal.pone.0285683","article-title":"Segmenting white matter hyperintensities on isotropic three-dimensional fluid attenuated inversion recovery magnetic resonance images: assessing deep learning tools on a Norwegian imaging database","volume":"18","author":"R\u00f8vang","year":"2023","journal-title":"PLoS One"},{"key":"ref33","doi-asserted-by":"publisher","first-page":"681183","DOI":"10.3389\/fmed.2021.681183","article-title":"Segmentation of cerebral small vessel diseases-white matter hyperintensities based on a deep learning system","volume":"8","author":"Shan","year":"2021","journal-title":"Front. Med. (Lausanne)"},{"key":"ref34","volume-title":"2022 IEEE 19th International Symposium on Biomedical Imaging (ISBI)","author":"Sundaresan","year":"2022"},{"key":"ref35","doi-asserted-by":"publisher","first-page":"e26548","DOI":"10.1002\/hbm.26548","article-title":"Early detection of white matter hyperintensities using SHIVA-WMH detector","volume":"45","author":"Tsuchida","year":"2024","journal-title":"Hum. Brain Mapp."},{"key":"ref36","doi-asserted-by":"publisher","first-page":"102357","DOI":"10.1016\/j.nicl.2020.102357","article-title":"Comparison and validation of seven white matter hyperintensities segmentation software in elderly patients","volume":"27","author":"Vanderbecq","year":"2020","journal-title":"Neuroimage Clin."},{"key":"ref37","volume-title":"2022 IEEE ANDESCON","author":"Viteri","year":"2022"},{"key":"ref38","doi-asserted-by":"publisher","first-page":"822","DOI":"10.1016\/S1474-4422(13)70124-8","article-title":"Neuroimaging standards for research into small vessel disease and its contribution to ageing and neurodegeneration","volume":"12","author":"Wardlaw","year":"2013","journal-title":"Lancet Neurol."},{"key":"ref39","doi-asserted-by":"publisher","first-page":"990","DOI":"10.1212\/WNL.57.6.990","article-title":"A prospective study of cerebral white matter abnormalities in older people with gait dysfunction","volume":"57","author":"Whitman","year":"2001","journal-title":"Neurology"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/s10278-025-01808-9","article-title":"Benchmark white matter Hyperintensity segmentation methods fail on heterogeneous clinical MRI: a new dataset and deep learning-based solutions","author":"Wu","year":"2026","journal-title":"J. Imaging Inform. Med."},{"key":"ref41","doi-asserted-by":"publisher","first-page":"155194","DOI":"10.1109\/access.2019.2948476","article-title":"Skip connection U-Net for white matter hyperintensities segmentation from MRI","volume":"7","author":"Wu","year":"2019","journal-title":"IEEE Access"},{"key":"ref42","doi-asserted-by":"publisher","first-page":"105395","DOI":"10.1016\/j.cmpb.2020.105395","article-title":"DENSE-INception U-Net for medical image segmentation","volume":"192","author":"Zhang","year":"2020","journal-title":"Comput. Methods Prog. Biomed."},{"key":"ref43","volume-title":"2018 IEEE 23rd International Conference on Digital Signal Processing (DSP)","author":"Zhang","year":"2018"},{"key":"ref44","volume-title":"2021 14th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics","author":"Zhang","year":"2021"},{"key":"ref45","volume-title":"Communications in Computer and Information Science","author":"Zhao","year":"2021"},{"key":"ref46","doi-asserted-by":"publisher","first-page":"1540923","DOI":"10.3389\/fneur.2025.1540923","article-title":"Deep learning-based automated segmentation for the quantitative diagnosis of cerebral small vessel disease via multisequence MRI","volume":"16","author":"Zhao","year":"2025","journal-title":"Front. Neurol."}],"container-title":["Frontiers in Aging Neuroscience"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fnagi.2026.1930675\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,16]],"date-time":"2026-09-16T05:32:33Z","timestamp":1789536753000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fnagi.2026.1930675\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9,16]]},"references-count":46,"alternative-id":["10.3389\/fnagi.2026.1930675"],"URL":"https:\/\/doi.org\/10.3389\/fnagi.2026.1930675","relation":{},"ISSN":["1663-4365"],"issn-type":[{"value":"1663-4365","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9,16]]},"article-number":"1930675"}}