{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,2]],"date-time":"2026-09-02T13:08:46Z","timestamp":1788354526645,"version":"build-2803163510"},"reference-count":37,"publisher":"Public Library of Science (PLoS)","issue":"1","license":[{"start":{"date-parts":[[2026,1,7]],"date-time":"2026-01-07T00:00:00Z","timestamp":1767744000000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Clinical Medical Technology Innovation and Guidance Project In Hunan Province","award":["2021SK53510"],"award-info":[{"award-number":["2021SK53510"]}]},{"name":"the Natural Scientific Fund of Hunan Province","award":["2022JJ70139"],"award-info":[{"award-number":["2022JJ70139"]}]}],"content-domain":{"domain":["www.plosdigitalhealth.org"],"crossmark-restriction":false},"short-container-title":["PLOS Digit Health"],"abstract":"<jats:p>This study aimed to develop and validate an artificial intelligence (AI) model for the non-invasive early detection of dyslipidemia using liver chemical shift-encoded MRI (CSE-MRI) fat maps. An automated AI pipeline was developed to predict abnormalities in four lipid indicators: triglyceride, total cholesterol, low-density lipoprotein cholesterol, and high-density lipoprotein cholesterol. The study utilized 1,757 liver CSE-MRI fat images from 89 patients who underwent MRI scans and contemporaneous blood lipid testing. Transfer learning was applied using several pre-trained networks, including ResNet18, MobileNet, DenseNet, AlexNet, and SqueezeNet. Model performance was evaluated via 8-fold cross-validation, with the optimal model further assessed on a held-out test set using confusion matrices and derived metrics. Significant performance differences were observed among models. The optimal model, based on ResNet18, demonstrated high accuracy in the internal validation set. On the independent test set, this model achieved accuracies of 0.853 for triglyceride, 0.833 for total cholesterol, 0.937 for low-density lipoprotein cholesterol, and 0.936 for high-density lipoprotein cholesterol, with corresponding F1-Scores of 0.885, 0.571, 0.886, and 0.897. The AI model based on liver CSE-MRI fat maps shows high accuracy and generalization in predicting abnormalities for three key lipid indices, validating its potential as an early warning tool for dyslipidemia. Expanding the training dataset could further enhance performance for all lipid indices.<\/jats:p>","DOI":"10.1371\/journal.pdig.0001119","type":"journal-article","created":{"date-parts":[[2026,1,7]],"date-time":"2026-01-07T19:10:10Z","timestamp":1767813010000},"page":"e0001119","update-policy":"https:\/\/doi.org\/10.1371\/journal.pdig.corrections_policy","source":"Crossref","is-referenced-by-count":1,"title":["Development and validation of an artificial intelligence model based on liver CSE-MRI fat maps for predicting dyslipidemia"],"prefix":"10.1371","volume":"5","author":[{"given":"Bo","family":"Jiang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Weijun","family":"Situ","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhichao","family":"Feng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jianmin","family":"Yuan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yina","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaofan","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiong","family":"Wu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kai","family":"Deng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Haitao","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiao","family":"Xiao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xi","family":"Guo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4240-724X","authenticated-orcid":true,"given":"Junjiao","family":"Hu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2026,1,7]]},"reference":[{"key":"pdig.0001119.ref001","doi-asserted-by":"crossref","first-page":"5245308","DOI":"10.1155\/2020\/5245308","article-title":"Mechanistic Insights into the Oxidized Low-Density Lipoprotein-Induced Atherosclerosis","volume":"2020","author":"C Khatana","year":"2020","journal-title":"Oxid Med Cell Longev"},{"issue":"6","key":"pdig.0001119.ref002","doi-asserted-by":"crossref","first-page":"1379","DOI":"10.1111\/jdi.13310","article-title":"Low-density lipoprotein cholesterol and stroke: How low should we go?","volume":"11","author":"DT Lui","year":"2020","journal-title":"J Diabetes Invest"},{"issue":"7","key":"pdig.0001119.ref003","first-page":"761","article-title":"Association between Abnormal Serum Lipid Levels in Early Pregnancy and Development of Preeclampsia","volume":"39","author":"EL Ameh","year":"2022","journal-title":"West Afr J Med"},{"issue":"1","key":"pdig.0001119.ref004","doi-asserted-by":"crossref","first-page":"37","DOI":"10.1016\/j.amjms.2022.07.015","article-title":"The association between eosinophil count, serum lipids and metabolic syndrome in Taiwanese","volume":"365","author":"W-Y Lin","year":"2023","journal-title":"Am J Med Sci"},{"issue":"3","key":"pdig.0001119.ref005","first-page":"178","article-title":"Relationships between lipids levels in blood plasma, follicular fluid and seminal plasma with ovarian response and sperm concentration regardless of age and body mass index","volume":"20","author":"R N\u00fa\u00f1ez Calonge","year":"2022","journal-title":"Rev Int Androl"},{"key":"pdig.0001119.ref006","doi-asserted-by":"crossref","first-page":"55","DOI":"10.1016\/j.jpsychires.2023.05.016","article-title":"Prevalence and clinical correlates of abnormal lipid metabolism in first-episode and drug-na\u00efve patients with major depressive disorder: A large-scale cross-sectional study","volume":"163","author":"J Hu","year":"2023","journal-title":"J Psychiatr Res"},{"issue":"5","key":"pdig.0001119.ref007","doi-asserted-by":"crossref","first-page":"1165","DOI":"10.1016\/j.numecd.2022.01.030","article-title":"Dietary patterns and the risk of abnormal blood lipids among young adults: A prospective cohort study","volume":"32","author":"TW Ushula","year":"2022","journal-title":"Nutr Metab Cardiovasc Dis"},{"key":"pdig.0001119.ref008","doi-asserted-by":"crossref","first-page":"138","DOI":"10.1016\/j.jacc.2022.04.046","article-title":"Trends and disparities in cardiometabolic health among U.S. adults, 1999-2018","volume":"80","author":"M O\u2019Hearn","year":"2022","journal-title":"J Am Coll Cardiol"},{"issue":"2","key":"pdig.0001119.ref009","doi-asserted-by":"crossref","first-page":"299","DOI":"10.1016\/j.mcna.2021.11.006","article-title":"Triglycerides: How to Manage Patients with Elevated Triglycerides and When to Refer?","volume":"106","author":"N Bazarbashi","year":"2022","journal-title":"Med Clin North Am"},{"issue":"9","key":"pdig.0001119.ref010","doi-asserted-by":"crossref","first-page":"621","DOI":"10.26599\/1671-5411.2023.09.008","article-title":"2023 China Guidelines for Lipid Management","volume":"20","author":"J-J Li","year":"2023","journal-title":"J Geriatr Cardiol"},{"key":"pdig.0001119.ref011","doi-asserted-by":"crossref","first-page":"487","DOI":"10.1016\/j.ebiom.2019.07.007","article-title":"Genetically-predicted life-long lowering of low-density lipoprotein cholesterol is associated with decreased frailty: A Mendelian randomization study in UK biobank","volume":"45","author":"Q Wang","year":"2019","journal-title":"EBioMedicine"},{"key":"pdig.0001119.ref012","doi-asserted-by":"crossref","first-page":"144","DOI":"10.1016\/j.ijcard.2022.01.029","article-title":"Estimation of low-density lipoprotein cholesterol levels using machine learning","volume":"352","author":"GC Oh","year":"2022","journal-title":"Int J Cardiol"},{"issue":"1","key":"pdig.0001119.ref013","doi-asserted-by":"crossref","first-page":"185","DOI":"10.1186\/s12944-020-01363-y","article-title":"Night sleep duration and risk of each lipid profile abnormality in a Chinese population: a prospective cohort study","volume":"19","author":"Q Song","year":"2020","journal-title":"Lipids Health Dis"},{"issue":"10","key":"pdig.0001119.ref014","doi-asserted-by":"crossref","first-page":"7566","DOI":"10.1007\/s00330-021-07851-8","article-title":"Long-term inter-platform reproducibility, bias, and linearity of commercial PDFF MRI methods for fat quantification: a multi-center, multi-vendor phantom study","volume":"31","author":"E Schneider","year":"2021","journal-title":"Eur Radiol"},{"key":"pdig.0001119.ref015","doi-asserted-by":"crossref","DOI":"10.1148\/rg.220178","article-title":"US quantification of liver fat: past, present, and future","volume":"43","author":"DT Fetzer","year":"2023","journal-title":"Radiographics"},{"issue":"8","key":"pdig.0001119.ref016","doi-asserted-by":"crossref","first-page":"1747","DOI":"10.1002\/jum.16194","article-title":"Ultrasound-Based Machine Learning Approach for Detection of Nonalcoholic Fatty Liver Disease","volume":"42","author":"A Tahmasebi","year":"2023","journal-title":"J Ultrasound Med"},{"issue":"11","key":"pdig.0001119.ref017","doi-asserted-by":"crossref","first-page":"5251","DOI":"10.21037\/qims-22-393","article-title":"The spectrum of magnetic resonance imaging proton density fat fraction (MRI-PDFF), magnetic resonance spectroscopy (MRS), and two different histopathologic methods (artificial intelligence vs. pathologist) in quantifying hepatic steatosis","volume":"12","author":"JW Kim","year":"2022","journal-title":"Quant Imag Med Surg"},{"issue":"1","key":"pdig.0001119.ref018","doi-asserted-by":"crossref","first-page":"3680","DOI":"10.1038\/s41598-023-30521-2","article-title":"Evaluation of the clinical performance of an AI-based application for the automated analysis of chest X-rays","volume":"13","author":"JH Niehoff","year":"2023","journal-title":"Sci Rep"},{"key":"pdig.0001119.ref019","doi-asserted-by":"crossref","first-page":"1430","DOI":"10.1016\/j.acra.2020.03.031","article-title":"Artificial Intelligence and the Role of Radiologists","volume":"27","author":"C Celeng","year":"2020","journal-title":"Acad Radiol"},{"issue":"3","key":"pdig.0001119.ref020","doi-asserted-by":"crossref","first-page":"312","DOI":"10.1016\/j.job.2022.03.003","article-title":"Deep learning models in medical image analysis","volume":"64","author":"M Tsuneki","year":"2022","journal-title":"J Oral Biosci"},{"key":"pdig.0001119.ref021","doi-asserted-by":"crossref","first-page":"101780","DOI":"10.1016\/j.artmed.2019.101780","article-title":"Implementation of artificial intelligence in medicine: Status analysis and development suggestions","volume":"102","author":"Y Xiang","year":"2020","journal-title":"Artif Intell Med"},{"issue":"7","key":"pdig.0001119.ref022","doi-asserted-by":"crossref","first-page":"800","DOI":"10.1097\/GME.0000000000001799","article-title":"Adding marrow R2* to proton density fat fraction improves the discrimination of osteopenia and osteoporosis in postmenopausal women assessed with 3D FACT sequence","volume":"28","author":"G Li","year":"2021","journal-title":"Menopause"},{"key":"pdig.0001119.ref023","doi-asserted-by":"crossref","first-page":"155","DOI":"10.1016\/j.neunet.2022.01.012","article-title":"Low-degree term first in ResNet, its variants and the whole neural network family","volume":"148","author":"T Sun","year":"2022","journal-title":"Neural Netw"},{"issue":"6","key":"pdig.0001119.ref024","doi-asserted-by":"crossref","first-page":"188","DOI":"10.3390\/bios11060188","article-title":"Integrating ECG Monitoring and Classification via IoT and Deep Neural Networks","volume":"11","author":"L-R Yeh","year":"2021","journal-title":"Biosensors (Basel)"},{"issue":"11","key":"pdig.0001119.ref025","doi-asserted-by":"crossref","first-page":"3883","DOI":"10.3390\/s21113883","article-title":"ResNet Based Deep Features and Random Forest Classifier for Diabetic Retinopathy Detection","volume":"21","author":"MK Yaqoob","year":"2021","journal-title":"Sensors (Basel)"},{"key":"pdig.0001119.ref026","doi-asserted-by":"crossref","first-page":"326","DOI":"10.1016\/j.neunet.2022.02.014","article-title":"Efficient learning rate adaptation based on hierarchical optimization approach","volume":"150","author":"GS Na","year":"2022","journal-title":"Neural Netw"},{"issue":"2","key":"pdig.0001119.ref027","article-title":"Evolutionary polynomial regression improved by regularization methods","volume":"18","author":"Y Li","year":"2023","journal-title":"PLoS One"},{"key":"pdig.0001119.ref028","doi-asserted-by":"crossref","first-page":"96","DOI":"10.1016\/j.clinimag.2020.04.025","article-title":"Understanding artificial intelligence based radiology studies: What is overfitting?","volume":"65","author":"S Mutasa","year":"2020","journal-title":"Clin Imaging"},{"key":"pdig.0001119.ref029","doi-asserted-by":"crossref","first-page":"114869","DOI":"10.1016\/j.jenvman.2022.114869","article-title":"Analysis of input set characteristics and variances on k-fold cross validation for a Recurrent Neural Network model on waste disposal rate estimation","volume":"311","author":"HL Vu","year":"2022","journal-title":"J Environ Manage"},{"key":"pdig.0001119.ref030","doi-asserted-by":"crossref","first-page":"8777355","DOI":"10.1155\/2022\/8777355","article-title":"Human-Computer Interaction with Hand Gesture Recognition Using ResNet and MobileNet","volume":"2022","author":"A Alnuaim","year":"2022","journal-title":"Comput Intell Neurosci"},{"issue":"6","key":"pdig.0001119.ref031","doi-asserted-by":"crossref","first-page":"555","DOI":"10.1159\/000527145","article-title":"A Deep Learning Model for Idiopathic Osteosclerosis Detection on Panoramic Radiographs","volume":"31","author":"S Yesiltepe","year":"2022","journal-title":"Med Princ Pract"},{"key":"pdig.0001119.ref032","doi-asserted-by":"crossref","first-page":"28","DOI":"10.1016\/j.mri.2019.04.007","article-title":"Automated and accurate quantification of subcutaneous and visceral adipose tissue from magnetic resonance imaging based on machine learning","volume":"64","author":"N Shen","year":"2019","journal-title":"Magn Reson Imaging"},{"issue":"4","key":"pdig.0001119.ref033","doi-asserted-by":"crossref","first-page":"1567","DOI":"10.1002\/mrm.29525","article-title":"Uncertainty-aware physics-driven deep learning network for free-breathing liver fat and R2 * quantification using self-gated stack-of-radial MRI","volume":"89","author":"S-F Shih","year":"2023","journal-title":"Magn Reson Med"},{"issue":"2","key":"pdig.0001119.ref034","doi-asserted-by":"crossref","first-page":"345","DOI":"10.1148\/radiol.2021211027","article-title":"Automated Whole-Liver MRI Segmentation to Assess Steatosis and Iron Quantification in Chronic Liver Disease","volume":"302","author":"D Mart\u00ed-Aguado","year":"2022","journal-title":"Radiology"},{"issue":"4","key":"pdig.0001119.ref035","article-title":"Multiparametric MR Is a Valuable Modality for Evaluating Disease Severity of Nonalcoholic Fatty Liver Disease","volume":"11","author":"Y-S Lee","year":"2020","journal-title":"Clin Transl Gastroenterol"},{"key":"pdig.0001119.ref036","doi-asserted-by":"crossref","first-page":"107660","DOI":"10.1016\/j.cmpb.2023.107660","article-title":"ResNet and its application to medical image processing: Research progress and challenges","volume":"240","author":"W Xu","year":"2023","journal-title":"Comput Method Prog Biomed"},{"issue":"14","key":"pdig.0001119.ref037","doi-asserted-by":"crossref","first-page":"8272","DOI":"10.3390\/ijerph19148272","article-title":"Serum Cholesterol Levels and Risk of Cardiovascular Death: A Systematic Review and a Dose-Response Meta-Analysis of Prospective Cohort Studies","volume":"19","author":"E Jung","year":"2022","journal-title":"Int J Environ Res Public Health"}],"container-title":["PLOS Digital Health"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pdig.0001119","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,7]],"date-time":"2026-01-07T19:10:17Z","timestamp":1767813017000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pdig.0001119"}},"subtitle":[],"editor":[{"given":"Alexander","family":"Wong","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2026,1,7]]},"references-count":37,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,1,7]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pdig.0001119","relation":{},"ISSN":["2767-3170"],"issn-type":[{"value":"2767-3170","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1,7]]}}}