{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,7]],"date-time":"2026-10-07T13:29:32Z","timestamp":1791379772693,"version":"4.3.3"},"reference-count":28,"publisher":"Public Library of Science (PLoS)","issue":"8","license":[{"start":{"date-parts":[[2025,8,8]],"date-time":"2025-08-08T00:00:00Z","timestamp":1754611200000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["www.plosone.org"],"crossmark-restriction":false},"short-container-title":["PLoS One"],"abstract":"<jats:p>Metabolic dysfunction-associated steatotic liver disease (MASLD) is the most common cause of chronic liver disease worldwide, affecting over 30% of the global general population. Its progressive nature and association with other chronic diseases makes early diagnosis important. MRI Proton Density Fat Fraction (PDFF) is the most accurate noninvasive method for quantitatively assessing liver fat but is expensive and has limited availability; accurately quantifying liver fat from more accessible and affordable imaging could potentially improve patient care. This proof-of-concept study explores the feasibility of inferring liver MRI-PDFF values from contrast-enhanced computed tomography (CECT) using deep learning. In this retrospective, cross-sectional study, we analyzed data from living liver donor candidates who had concurrent CECT and MRI-PDFF as part of their pre-surgical workup between April 2021 and October 2022. Manual MRI-PDFF analysis was performed following a standard of clinical care protocol and used as ground truth. After liver segmentation and registration, a deep neural network (DNN) with 3D U-Net architecture was trained using CECT images as single channel input and the concurrent MRI-PDFF images as single channel output. We evaluated performance using mean absolute error (MAE) and root mean squared error (RMSE), and mean errors (defined as the mean difference of results of comparator groups), with 95% confidence intervals (CIs). We used Kappa statistics and Bland-Altman plots to assess agreement between DNN-predicted PDFF and ground truth steatosis grades and PDFF values, respectively. The final study cohort was of 94 patients, mean PDFF\u2009=\u20093.8%, range 0.2\u201322.3%. When comparing ground truth to segmented reference (MRI-PDFF), our model had an MAE of 0.56, an RMSE of 0.77, and a mean error of 0.06 (\u22121.75,1.86); when comparing medians of the predicted and reference MRI-PDFF images, our model had an MAE, an RMSE, and a mean error of 2.94, 4.27, and 1.28 (\u22124.58,7.14), respectively. We found substantial agreement between categorical steatosis grades obtained from DNN-predicted and clinical ground truth PDFF (kappa\u2009=\u20090.75). While its ability to infer exact MRI-PDFF values from CECT images was limited, categorical classification of fat fraction at lower grades was robust, outperforming other prior attempted methods.<\/jats:p>","DOI":"10.1371\/journal.pone.0328867","type":"journal-article","created":{"date-parts":[[2025,8,8]],"date-time":"2025-08-08T17:36:46Z","timestamp":1754674606000},"page":"e0328867","update-policy":"https:\/\/doi.org\/10.1371\/journal.pone.corrections_policy","source":"Crossref","is-referenced-by-count":6,"title":["Liver MRI proton density fat fraction inference from contrast enhanced CT images using deep learning: A proof-of-concept study"],"prefix":"10.1371","volume":"20","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3955-0996","authenticated-orcid":true,"given":"Md","family":"Nasir","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yixi","family":"Xu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kyle","family":"Hasenstab","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Alekhya","family":"Yechoor","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rahul","family":"Dodhia","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9918-1360","authenticated-orcid":true,"given":"William B.","family":"Weeks","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Juan Lavista","family":"Ferres","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guilherme Moura","family":"Cunha","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2025,8,8]]},"reference":[{"issue":"10290","key":"pone.0328867.ref001","doi-asserted-by":"crossref","first-page":"2212","DOI":"10.1016\/S0140-6736(20)32511-3","article-title":"Non-alcoholic fatty liver disease","volume":"397","author":"EE Powell","year":"2021","journal-title":"Lancet"},{"issue":"4","key":"pone.0328867.ref002","doi-asserted-by":"crossref","first-page":"1335","DOI":"10.1097\/HEP.0000000000000004","article-title":"The global epidemiology of nonalcoholic fatty liver disease (NAFLD) and nonalcoholic steatohepatitis (NASH): a systematic review","volume":"77","author":"ZM Younossi","year":"2023","journal-title":"Hepatology"},{"key":"pone.0328867.ref003","first-page":"884","article-title":"Non-alcoholic fatty liver disease, metabolic syndrome, and type 2 diabetes mellitus: where do we stand today?","volume":"19","author":"B Mitrovic","year":"2022","journal-title":"Arch Med Sci"},{"issue":"11","key":"pone.0328867.ref004","doi-asserted-by":"crossref","first-page":"901","DOI":"10.1016\/S2213-8587(14)70032-4","article-title":"Non-alcoholic fatty liver disease as a cause and a consequence of metabolic syndrome","volume":"2","author":"H Yki-J\u00e4rvinen","year":"2014","journal-title":"Lancet Diabetes Endocrinol"},{"issue":"27","key":"pone.0328867.ref005","first-page":"9026","article-title":"Role of liver biopsy in nonalcoholic fatty liver disease","volume":"20","author":"ILK Nalbantoglu","year":"2014","journal-title":"World J Gastroenterol"},{"issue":"3","key":"pone.0328867.ref006","doi-asserted-by":"crossref","first-page":"745","DOI":"10.1053\/gast.2002.35354","article-title":"The utility of radiological imaging in nonalcoholic fatty liver disease","volume":"123","author":"S Saadeh","year":"2002","journal-title":"Gastroenterology"},{"issue":"2","key":"pone.0328867.ref007","doi-asserted-by":"crossref","first-page":"422","DOI":"10.1148\/radiol.12120896","article-title":"Nonalcoholic fatty liver disease: MR imaging of liver proton density fat fraction to assess hepatic steatosis","volume":"267","author":"A Tang","year":"2013","journal-title":"Radiology"},{"issue":"1","key":"pone.0328867.ref008","doi-asserted-by":"crossref","first-page":"6895","DOI":"10.1038\/s41598-024-57324-3","article-title":"Correlation between magnetic resonance imaging proton density fat fraction (MRI-PDFF) and liver biopsy to assess hepatic steatosis in obesity","volume":"14","author":"P Wibulpolprasert","year":"2024","journal-title":"Sci Rep"},{"key":"pone.0328867.ref009","article-title":"The role of imaging in obesity special feature: review article liver fat imaging \u2014 a clinical overview of ultrasound, CT, and MR imaging","volume":"91","author":"Y Zhang","year":"2018","journal-title":"Br J Radiol"},{"issue":"1","key":"pone.0328867.ref010","doi-asserted-by":"crossref","first-page":"90","DOI":"10.2214\/AJR.18.20947","article-title":"Clinical Implementation of a Focused MRI Protocol for Hepatic Fat and Iron Quantification","volume":"213","author":"BD Pooler","year":"2019","journal-title":"AJR Am J Roentgenol"},{"issue":"3","key":"pone.0328867.ref011","doi-asserted-by":"crossref","first-page":"187","DOI":"10.1016\/j.crad.2022.10.003","article-title":"Ultrasound-based hepatic fat quantification: current status and future directions","volume":"78","author":"N Seneviratne","year":"2023","journal-title":"Clin Radiol"},{"issue":"5","key":"pone.0328867.ref012","doi-asserted-by":"crossref","first-page":"620","DOI":"10.2214\/AJR.23.29607","article-title":"Deep Learning for Inference of Hepatic Proton Density Fat Fraction From T1-Weighted In-Phase and Opposed-Phase MRI: Retrospective Analysis of Population-Based Trial Data","volume":"221","author":"K Wang","year":"2023","journal-title":"AJR Am J Roentgenol"},{"issue":"2","key":"pone.0328867.ref013","doi-asserted-by":"crossref","DOI":"10.1148\/radiol.241171","article-title":"Diagnostic Accuracy of CT for the Detection of Hepatic Steatosis: A Systematic Review and Meta-Analysis","volume":"313","author":"M Haghshomar","year":"2024","journal-title":"Radiology"},{"issue":"3","key":"pone.0328867.ref014","doi-asserted-by":"crossref","first-page":"592","DOI":"10.2214\/AJR.17.17812","article-title":"Standardized Approach for ROI-Based Measurements of Proton Density Fat Fraction and R2* in the Liver","volume":"209","author":"CA Campo","year":"2017","journal-title":"AJR Am J Roentgenol"},{"key":"pone.0328867.ref015","author":"A Pedersen","year":"2023","journal-title":"Andreped\/livermask: v1.5.0"},{"key":"pone.0328867.ref016","doi-asserted-by":"crossref","first-page":"180022","DOI":"10.1148\/ryai.2019180022","article-title":"Automated CT and MRI liver segmentation and biometry using a generalized convolutional neural network","volume":"1","author":"K Wang","year":"2019","journal-title":"Radiol Artif Intell"},{"issue":"6","key":"pone.0328867.ref017","doi-asserted-by":"crossref","first-page":"1310","DOI":"10.1109\/TMI.2010.2046908","article-title":"N4ITK: improved N3 bias correction","volume":"29","author":"NJ Tustison","year":"2010","journal-title":"IEEE Trans Med Imaging"},{"issue":"1","key":"pone.0328867.ref018","doi-asserted-by":"crossref","first-page":"73","DOI":"10.1214\/aoms\/1177703732","article-title":"Robust Estimation of a Location Parameter","volume":"35","author":"PJ Huber","year":"1964","journal-title":"Ann Math Statist"},{"issue":"3","key":"pone.0328867.ref019","doi-asserted-by":"crossref","first-page":"661","DOI":"10.1007\/s00261-019-02350-3","article-title":"Accuracy of common proton density fat fraction thresholds for magnitude- and complex-based chemical shift-encoded MRI for assessing hepatic steatosis in patients with obesity","volume":"45","author":"GM Cunha","year":"2020","journal-title":"Abdom Radiol (NY)"},{"issue":"3","key":"pone.0328867.ref020","doi-asserted-by":"crossref","first-page":"276","DOI":"10.11613\/BM.2012.031","article-title":"Interrater reliability: the kappa statistic","volume":"22","author":"ML McHugh","year":"2012","journal-title":"Biochem Med (Zagreb)"},{"issue":"6","key":"pone.0328867.ref021","doi-asserted-by":"crossref","first-page":"523","DOI":"10.3748\/wjg.v27.i6.523","article-title":"Prevalence of advanced liver fibrosis and steatosis in type-2 diabetics with normal transaminases: A prospective cohort study","volume":"27","author":"J Makker","year":"2021","journal-title":"World J Gastroenterol"},{"key":"pone.0328867.ref022","doi-asserted-by":"crossref","first-page":"223","DOI":"10.1038\/s41575-020-00381-6","article-title":"Global epidemiology of NAFLD-related HCC: trends, predictions, risk factors and prevention","volume":"18","author":"DQ Huang","year":"2021","journal-title":"Nat Rev Gastroenterol Hepatol"},{"key":"pone.0328867.ref023","article-title":"Patient Exposure from Radiologic and Nuclear Medicine Procedures in the United States and Worldwide: 2009\u20132018","volume":"307","author":"M Mahesh","year":"2023","journal-title":"Radiology"},{"issue":"5","key":"pone.0328867.ref024","doi-asserted-by":"crossref","DOI":"10.1148\/radiol.222044","article-title":"Opportunistic Screening: Radiology Scientific Expert Panel","volume":"307","author":"PJ Pickhardt","year":"2023","journal-title":"Radiology"},{"issue":"1","key":"pone.0328867.ref025","doi-asserted-by":"crossref","first-page":"89","DOI":"10.1148\/radiol.2019190467","article-title":"Liver Fat Content Measurement with Quantitative CT Validated against MRI Proton Density Fat Fraction: A Prospective Study of 400 Healthy Volunteers","volume":"294","author":"Z Guo","year":"2020","journal-title":"Radiology"},{"issue":"2","key":"pone.0328867.ref026","doi-asserted-by":"crossref","first-page":"359","DOI":"10.2214\/AJR.20.24415","article-title":"Liver Steatosis Categorization on Contrast-Enhanced CT Using a Fully Automated Deep Learning Volumetric Segmentation Tool: Evaluation in 1204 Healthy Adults Using Unenhanced CT as a Reference Standard","volume":"217","author":"PJ Pickhardt","year":"2021","journal-title":"AJR Am J Roentgenol"},{"issue":"11","key":"pone.0328867.ref027","doi-asserted-by":"crossref","first-page":"7041","DOI":"10.1007\/s00330-024-10816-2","article-title":"Post-contrast CT liver attenuation alone is superior to the liver-spleen difference for identifying moderate hepatic steatosis","volume":"34","author":"PJ Pickhardt","year":"2024","journal-title":"Eur Radiol"},{"issue":"1","key":"pone.0328867.ref028","doi-asserted-by":"crossref","first-page":"55","DOI":"10.1038\/s41574-021-00584-0","article-title":"Non-invasive methods for imaging hepatic steatosis and their clinical importance in NAFLD","volume":"18","author":"N Tamaki","year":"2022","journal-title":"Nat Rev Endocrinol"}],"container-title":["PLOS One"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0328867","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,8]],"date-time":"2025-08-08T17:36:50Z","timestamp":1754674610000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0328867"}},"subtitle":[],"editor":[{"given":"Wan-Long","family":"Chuang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2025,8,8]]},"references-count":28,"journal-issue":{"issue":"8","published-online":{"date-parts":[[2025,8,8]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pone.0328867","relation":{},"ISSN":["1932-6203"],"issn-type":[{"value":"1932-6203","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,8,8]]}}}