{"database":"biostudies-literature","file_versions":[],"scores":null,"additional":{"submitter":["Tai J"],"funding":["Chang Gung Memorial Hospital"],"pagination":["267"],"full_dataset_link":["https://www.ebi.ac.uk/biostudies/studies/S-EPMC12840080"],"repository":["biostudies-literature"],"omics_type":["Unknown"],"volume":["16(2)"],"pubmed_abstract":["<b>Background:</b> Liver steatosis assessment by 2D ultrasound is widely used but remains subjective. We previously developed a deep learning (DL) algorithm for objective steatosis quantification. This study aimed to (1) establish histology-based cutoffs, (2) evaluate their transferability across different imaging views, and (3) validate performance on a new scanner not included in training. <b>Methods:</b> We retrospectively analyzed 588 ultrasound studies from 457 histology-proven cases and prospectively collected paired scans using a new scanner (Philips Affiniti 70). Images from right intercostal, left hepatic lobe, and subcostal views were processed with the DL algorithm, and mean values from 3-5 images per view were correlated with histology. <b>Results:</b> Across three views, the D"],"journal":["Diagnostics (Basel, Switzerland)"],"pubmed_title":["Clinical Validation of a Deep Learning-Based 2D Ultrasound Steatosis Algorithm: Cutoff Transferability, Scanner Generalizability, and Comparison with FibroScan."],"pmcid":["PMC12840080"],"funding_grant_id":["CMRPG3P0261"],"pubmed_authors":["Chang ML","Lu L","Chen CJ","Harrison AP","Lin C","Huang SF","Tai DI","Tai J","Hsu TH"],"additional_accession":[]},"is_claimable":false,"name":"Clinical Validation of a Deep Learning-Based 2D Ultrasound Steatosis Algorithm: Cutoff Transferability, Scanner Generalizability, and Comparison with FibroScan.","description":"<b>Background:</b> Liver steatosis assessment by 2D ultrasound is widely used but remains subjective. We previously developed a deep learning (DL) algorithm for objective steatosis quantification. This study aimed to (1) establish histology-based cutoffs, (2) evaluate their transferability across different imaging views, and (3) validate performance on a new scanner not included in training. <b>Methods:</b> We retrospectively analyzed 588 ultrasound studies from 457 histology-proven cases and prospectively collected paired scans using a new scanner (Philips Affiniti 70). Images from right intercostal, left hepatic lobe, and subcostal views were processed with the DL algorithm, and mean values from 3-5 images per view were correlated with histology. <b>Results:</b> Across three views, the D","dates":{"release":"2026-01-01T00:00:00Z","publication":"2026 Jan","modification":"2026-06-13T03:14:20.699Z","creation":"2026-06-13T03:08:55.233Z"},"accession":"S-EPMC12840080","cross_references":{"pubmed":["41594243"],"doi":["10.3390/diagnostics16020267"]}}