{"database":"biostudies-literature","file_versions":[],"scores":null,"additional":{"omics_type":["Unknown"],"volume":["3(1)"],"submitter":["Slutsky-Ganesh AB"],"pubmed_abstract":["<h4>Background</h4>Accurate thigh muscle segmentation from magnetic resonance imaging (MRI) enables quantitative assessment of muscle health. Although manual segmentation is the gold standard, it is labor-intensive and variable, and existing automated/semi-automatic approaches remain limited by segmentation errors/user dependence, restricting scalability. Defining data requirements for robust automated segmentation therefore remains a critical unmet need.<h4>Purpose</h4>To determine the number of annotated lower extremity MRI studies needed to train an accurate deep learning (DL) model for thigh muscle segmentation and to assess the effect of training size on agreement of downstream quantitative measures.<h4>Materials and methods</h4>Lower extremity MR images were obtained from competitive"],"journal":["Radiology advances"],"pagination":["umag005"],"full_dataset_link":["https://www.ebi.ac.uk/biostudies/studies/S-EPMC12906233"],"repository":["biostudies-literature"],"pubmed_title":["Optimizing MRI annotation workflows for high-accuracy deep learning thigh muscle segmentation in athletes."],"pmcid":["PMC12906233"],"pubmed_authors":["Baup S","Slaton JA","Bharadwaj UU","Warren SM","Zuleger TM","Ogier AC","van Heeswijk RB","Slutsky-Ganesh AB","Xerogeanes JW","Diekfuss JA","Barber Foss KD","Valencia M","Myer GD","Hammond K"],"additional_accession":[]},"is_claimable":false,"name":"Optimizing MRI annotation workflows for high-accuracy deep learning thigh muscle segmentation in athletes.","description":"<h4>Background</h4>Accurate thigh muscle segmentation from magnetic resonance imaging (MRI) enables quantitative assessment of muscle health. Although manual segmentation is the gold standard, it is labor-intensive and variable, and existing automated/semi-automatic approaches remain limited by segmentation errors/user dependence, restricting scalability. Defining data requirements for robust automated segmentation therefore remains a critical unmet need.<h4>Purpose</h4>To determine the number of annotated lower extremity MRI studies needed to train an accurate deep learning (DL) model for thigh muscle segmentation and to assess the effect of training size on agreement of downstream quantitative measures.<h4>Materials and methods</h4>Lower extremity MR images were obtained from competitive","dates":{"release":"2026-01-01T00:00:00Z","publication":"2026 Jan","modification":"2026-07-09T13:23:28.835Z","creation":"2026-07-09T13:10:09.29Z"},"accession":"S-EPMC12906233","cross_references":{"pubmed":["41694457"],"doi":["10.1093/radadv/umag005"]}}