{"database":"biostudies-literature","file_versions":[],"scores":null,"additional":{"submitter":["Strain JF"],"funding":["McDonnell Center for Systems Neuroscience","NIA NIH HHS","Foundation for Barnes-Jewish Hospital","National Institutes of Health","James S. McDonnell Foundation","National Institute on Aging"],"pagination":["120494"],"full_dataset_link":["https://www.ebi.ac.uk/biostudies/studies/S-EPMC11534282"],"repository":["biostudies-literature"],"omics_type":["Unknown"],"volume":["285"],"pubmed_abstract":["White matter hyperintensities (WMH) are nearly ubiquitous in the aging brain, and their topography and overall burden are associated with cognitive decline. Given their numerosity, accurate methods to automatically segment WMH are needed. Recent developments, including the availability of challenge data sets and improved deep learning algorithms, have led to a new promising deep-learning based automated segmentation model called TrUE-Net, which has yet to undergo rigorous independent validation. Here, we compare TrUE-Net to six established automated WMH segmentation tools, including a semi-manual method. We evaluated the techniques at both global and regional level to compare their ability to detect the established relationship between WMH burden and age. We found that TrUE-Net was highly "],"journal":["NeuroImage"],"pubmed_title":["Accuracy of TrUE-Net in comparison to established white matter hyperintensity segmentation methods: An independent validation study."],"pmcid":["PMC11534282"],"funding_grant_id":["R01 AG057536","R01 AG053503","P01AG026276","R01AG057536","R01 AG058676","R01AG058676","R01AG053503","RF1 AG073210","RF1AG073210","P30 AG066444","P01AG003991","P30AG066444","P01 AG026276","P01 AG003991"],"pubmed_authors":["Womack K","Goyal MS","Rahmani M","Jafri H","Weiner M","Vlassenko AG","Morris JC","Dierker D","Tosun D","Strain JF","Lee JM","ADOPIC and ADNI Investigators","Benzinger TLS","Masters C","Owen C","Fripp J"],"additional_accession":[]},"is_claimable":false,"name":"Accuracy of TrUE-Net in comparison to established white matter hyperintensity segmentation methods: An independent validation study.","description":"White matter hyperintensities (WMH) are nearly ubiquitous in the aging brain, and their topography and overall burden are associated with cognitive decline. Given their numerosity, accurate methods to automatically segment WMH are needed. Recent developments, including the availability of challenge data sets and improved deep learning algorithms, have led to a new promising deep-learning based automated segmentation model called TrUE-Net, which has yet to undergo rigorous independent validation. Here, we compare TrUE-Net to six established automated WMH segmentation tools, including a semi-manual method. We evaluated the techniques at both global and regional level to compare their ability to detect the established relationship between WMH burden and age. We found that TrUE-Net was highly ","dates":{"release":"2024-01-01T00:00:00Z","publication":"2024 Jan","modification":"2025-04-04T07:28:24.259Z","creation":"2025-04-04T07:28:24.259Z"},"accession":"S-EPMC11534282","cross_references":{"pubmed":["38086495"],"doi":["10.1016/j.neuroimage.2023.120494"]}}