{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T14:03:06Z","timestamp":1773842586838,"version":"3.50.1"},"reference-count":42,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2025,9,25]],"date-time":"2025-09-25T00:00:00Z","timestamp":1758758400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Public Health"],"abstract":"<jats:sec><jats:title>Objectives<\/jats:title><jats:p>This study aims to investigate the efficacy of unsupervised machine learning algorithms, specifically the Gaussian Mixture Model (GMM), K-means clustering, and Otsu automatic threshold partitioning, in predicting sarcopenia based on computed tomography (CT) and magnetic resonance imaging (MRI) data.<\/jats:p><\/jats:sec><jats:sec><jats:title>Methods<\/jats:title><jats:p>A retrospective analysis was conducted on a dataset comprising 191 patients diagnosed with sarcopenia and 327 control patients. Participants were randomly assigned to training and validation cohorts in a 6:4 ratio. The paravertebral muscles at the lumbar 3\/4 intervertebral disc level were manually delineated as the region of interest (ROI) on non-enhanced CT and axial T2-weighted MRI images. Muscle and adipose tissues were automatically segmented from the ROI using GMM, K-means, and Otsu algorithms at the cohort level. Quantitative metrics such as mean, volume, and volume percentage were computed, and these parameters were compared between the sarcopenia and non-sarcopenia groups. Logistic regression analysis was employed to develop predictive models for sarcopenia, with model performance evaluated using the area under the curve (AUC). The stability of the models was assessed through five-fold cross-validation.<\/jats:p><\/jats:sec><jats:sec><jats:title>Results<\/jats:title><jats:p>The study demonstrates that three unsupervised clustering algorithms utilizing CT data surpassed those employing MRI data. Notably, the CT-based Otsu model exhibited the highest predictive performance in both training and validation datasets, with AUC values of 0.986 and 0.958, respectively. This was followed by the CT-based GMM, which achieved AUC values of 0.990 and 0.903, and the K-means model, with AUC values of 0.727 and 0.772. Furthermore, the CT-based GMM model demonstrated superior stability upon five-fold cross-validation, yielding an average AUC of 0.990.<\/jats:p><\/jats:sec><jats:sec><jats:title>Conclusion<\/jats:title><jats:p>The findings indicate that CT-based unsupervised machine learning models outperform their MRI-based counterparts, with the CT-based Otsu and GMM models showing exceptional efficacy in sarcopenia prediction, as evidenced by AUC values exceeding 0.95.<\/jats:p><\/jats:sec>","DOI":"10.3389\/fpubh.2025.1649400","type":"journal-article","created":{"date-parts":[[2025,9,25]],"date-time":"2025-09-25T05:30:22Z","timestamp":1758778222000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["The value of unsupervised machine learning algorithms based on CT and MRI for predicting sarcopenia"],"prefix":"10.3389","volume":"13","author":[{"given":"Huayan","family":"Zuo","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qiu","family":"Bi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaolong","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Guoli","family":"Bi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yijin","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yunzhu","family":"Wu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Guang","family":"Yang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chengxiu","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yang","family":"Song","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gang","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qiyang","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiarong","family":"Gong","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1965","published-online":{"date-parts":[[2025,9,25]]},"reference":[{"key":"ref1","doi-asserted-by":"publisher","first-page":"601","DOI":"10.1093\/ageing\/afz046","article-title":"Sarcopenia: revised European consensus on definition and diagnosis","volume":"48","author":"Cruz-Jentoft","year":"2019","journal-title":"Age Ageing"},{"key":"ref2","doi-asserted-by":"publisher","first-page":"c4097","DOI":"10.1136\/bmj.c4097","article-title":"Sarcopenia","volume":"341","author":"Sayer","year":"2010","journal-title":"BMJ (Clin Res Ed)"},{"key":"ref3","doi-asserted-by":"publisher","first-page":"176","DOI":"10.1016\/j.jamda.2016.10.019","article-title":"Utility of SARC-F for assessing physical function in elderly patients with cardiovascular disease","volume":"18","author":"Tanaka","year":"2017","journal-title":"J Am Med Dir Assoc"},{"key":"ref4","doi-asserted-by":"publisher","first-page":"145","DOI":"10.1002\/jcsm.12890","article-title":"Diagnosis, prevalence, and mortality of sarcopenia in dialysis patients: a systematic review and meta-analysis","volume":"13","author":"Shu","year":"2022","journal-title":"J Cachexia Sarcopenia Muscle"},{"key":"ref5","doi-asserted-by":"publisher","first-page":"1047","DOI":"10.1007\/s40520-016-0589-3","article-title":"The role of DXA in sarcopenia","volume":"28","author":"Guglielmi","year":"2016","journal-title":"Aging Clin Exp Res"},{"key":"ref6","doi-asserted-by":"publisher","first-page":"258","DOI":"10.1053\/j.jrn.2016.02.002","article-title":"Psoas muscle cross-sectional area as a measure of whole-body lean muscle mass in maintenance Hemodialysis patients","volume":"26","author":"Morrell","year":"2016","journal-title":"J Renal Nutr"},{"key":"ref7","doi-asserted-by":"publisher","first-page":"940","DOI":"10.1177\/0148607114550189","article-title":"Lean tissue imaging: a new era for nutritional assessment and intervention","volume":"38","author":"Prado","year":"2014","journal-title":"J Parenter Enter Nutr"},{"key":"ref8","doi-asserted-by":"publisher","first-page":"170","DOI":"10.1186\/s12877-016-0349-4","article-title":"Sarcopenia in daily practice: assessment and management","volume":"16","author":"Beaudart","year":"2016","journal-title":"BMC Geriatr"},{"key":"ref9","doi-asserted-by":"publisher","first-page":"2199","DOI":"10.1007\/s00330-019-06573-2","article-title":"Imaging of sarcopenia: old evidence and new insights","volume":"30","author":"Albano","year":"2020","journal-title":"Eur Radiol"},{"key":"ref10","doi-asserted-by":"publisher","first-page":"11765","DOI":"10.1038\/s41598-020-68797-3","article-title":"Body composition analysis using CT and MRI: intra-individual intermodal comparison of muscle mass and myosteatosis","volume":"10","author":"Faron","year":"2020","journal-title":"Sci Rep"},{"key":"ref11","doi-asserted-by":"publisher","first-page":"307","DOI":"10.1055\/s-0038-1641573","article-title":"Sarcopenia: beyond muscle atrophy and into the new Frontiers of opportunistic imaging, precision medicine, and machine learning","volume":"22","author":"Lenchik","year":"2018","journal-title":"Semin Musculoskelet Radiol"},{"key":"ref12","doi-asserted-by":"publisher","first-page":"696","DOI":"10.1016\/j.nut.2013.11.013","article-title":"A 360-degree overview of body composition in healthy people: relationships among anthropometry, ultrasonography, and dual-energy x-ray absorptiometry","volume":"30","author":"Bazzocchi","year":"2014","journal-title":"Nutrition"},{"key":"ref13","doi-asserted-by":"publisher","first-page":"1519","DOI":"10.1016\/j.ejrad.2016.04.009","article-title":"Imaging of sarcopenia","volume":"85","author":"Sergi","year":"2016","journal-title":"Eur J Radiol"},{"key":"ref14","doi-asserted-by":"publisher","first-page":"2333","DOI":"10.1152\/japplphysiol.00744.2004","article-title":"Total body skeletal muscle and adipose tissue volumes: estimation from a single abdominal cross-sectional image","volume":"97","author":"Shen","year":"2004","journal-title":"J Appl Physiol"},{"key":"ref15","doi-asserted-by":"publisher","first-page":"160","DOI":"10.1016\/j.ejrad.2019.03.019","article-title":"Feasibility of Dixon magnetic resonance imaging to quantify effects of physical training on muscle composition-a pilot study in young and healthy men","volume":"114","author":"Grimm","year":"2019","journal-title":"Eur J Radiol"},{"key":"ref16","doi-asserted-by":"publisher","first-page":"311","DOI":"10.1016\/j.acra.2019.03.011","article-title":"A machine learning algorithm to estimate sarcopenia on abdominal CT","volume":"27","author":"Burns","year":"2020","journal-title":"Acad Radiol"},{"key":"ref17","doi-asserted-by":"publisher","first-page":"111748","DOI":"10.1016\/j.ejrad.2024.111748","article-title":"Comparison of different MRI-based unsupervised segmentation algorithms in predicting sarcopenia","volume":"181","author":"Zuo","year":"2024","journal-title":"Eur J Radiol"},{"key":"ref18","doi-asserted-by":"publisher","first-page":"110218","DOI":"10.1016\/j.ejrad.2022.110218","article-title":"Artificial intelligence for body composition and sarcopenia evaluation on computed tomography: a systematic review and meta-analysis","volume":"149","author":"Bedrikovetski","year":"2022","journal-title":"Eur J Radiol"},{"key":"ref19","doi-asserted-by":"publisher","first-page":"889","DOI":"10.1046\/j.1532-5415.2002.50216.x","article-title":"Low relative skeletal muscle mass (sarcopenia) in older persons is associated with functional impairment and physical disability","volume":"50","author":"Janssen","year":"2002","journal-title":"J Am Geriatr Soc"},{"key":"ref20","doi-asserted-by":"publisher","first-page":"321","DOI":"10.1159\/000521241","article-title":"Definition and diagnostic criteria for sarcopenic obesity: ESPEN and EASO consensus statement","volume":"15","author":"Donini","year":"2022","journal-title":"Obes Facts"},{"key":"ref21","doi-asserted-by":"publisher","first-page":"13","DOI":"10.1097\/MCO.0000000000000519","article-title":"Sarcopenia and obesity","volume":"22","author":"Zamboni","year":"2019","journal-title":"Curr Opin Clin Nutr Metab Care"},{"key":"ref22","doi-asserted-by":"publisher","first-page":"1249","DOI":"10.1007\/s40520-016-0701-8","article-title":"Sarcopenia and sarcopenic obesity in comparison: prevalence, metabolic profile, and key differences. A cross-sectional study in Italian hospitalized elderly","volume":"29","author":"Perna","year":"2017","journal-title":"Aging Clin Exp Res"},{"key":"ref23","doi-asserted-by":"publisher","first-page":"15","DOI":"10.1111\/ggi.12220","article-title":"Incidence, reversibility, risk factors and the protective effect of high body mass index against sarcopenia in community-dwelling older Chinese adults","volume":"14","author":"Yu","year":"2014","journal-title":"Geriatr Gerontol Int"},{"key":"ref24","doi-asserted-by":"publisher","first-page":"937","DOI":"10.1186\/s12877-022-03643-x","article-title":"Association of high body mass index, waist circumference, and body fat percentage with sarcopenia in older women","volume":"22","author":"Yoo","year":"2022","journal-title":"BMC Geriatr"},{"key":"ref25","doi-asserted-by":"publisher","first-page":"775","DOI":"10.3390\/jcm8060775","article-title":"Nutritional laboratory markers in malnutrition","volume":"8","author":"Keller","year":"2019","journal-title":"J Clin Med"},{"key":"ref26","doi-asserted-by":"publisher","first-page":"1719","DOI":"10.2174\/1871530320666200610143724","article-title":"Effects of a Low carb diet and whey proteins on anthropometric, Hematochemical, and cardiovascular parameters in subjects with obesity","volume":"20","author":"De Pergola","year":"2020","journal-title":"Endocr Metab Immune Disord Drug Targets"},{"key":"ref27","doi-asserted-by":"publisher","first-page":"531","DOI":"10.1093\/ajcn\/82.3.531","article-title":"Lower serum albumin concentration and change in muscle mass: the health, aging and body composition study","volume":"82","author":"Visser","year":"2005","journal-title":"Am J Clin Nutr"},{"key":"ref28","doi-asserted-by":"publisher","first-page":"1148809","DOI":"10.3389\/fnut.2023.1148809","article-title":"The correlation of muscle quantity and quality between all vertebra levels and level L3, measured with CT: an exploratory study","volume":"10","author":"Van den Broeck","year":"2023","journal-title":"Front Nutr"},{"key":"ref29","doi-asserted-by":"publisher","first-page":"1339","DOI":"10.1200\/JCO.2015.63.6043","article-title":"Loss of muscle mass during chemotherapy is predictive for poor survival of patients with metastatic colorectal cancer","volume":"34","author":"Blauwhoff-Buskermolen","year":"2016","journal-title":"Clin Oncol"},{"key":"ref30","doi-asserted-by":"publisher","first-page":"898","DOI":"10.1002\/jcsm.12317","article-title":"Screening for low muscularity in colorectal cancer patients: a valid, clinic-friendly approach that predicts mortality","volume":"9","author":"Cespedes Feliciano","year":"2018","journal-title":"J Cachexia Sarcopenia Muscle"},{"key":"ref31","doi-asserted-by":"publisher","first-page":"60","DOI":"10.21037\/qims.2018.01.05","article-title":"Quantitative imaging techniques for the assessment of osteoporosis and sarcopenia","volume":"8","author":"Guerri","year":"2018","journal-title":"Quant Imaging Med Surg"},{"key":"ref32","doi-asserted-by":"publisher","first-page":"2766","DOI":"10.1111\/ajt.13832","article-title":"Comparing the variability between measurements for sarcopenia using magnetic resonance imaging and computed tomography imaging","volume":"16","author":"Tandon","year":"2016","journal-title":"Am J Transplant Off J Am Soc Transplant Am Soc Transplant Surg"},{"key":"ref33","doi-asserted-by":"publisher","first-page":"1716","DOI":"10.1016\/j.ejrad.2016.07.006","article-title":"Measurement of skeletal muscle area: comparison of CT and MR imaging","volume":"85","author":"Sinelnikov","year":"2016","journal-title":"Eur J Radiol"},{"key":"ref34","doi-asserted-by":"publisher","first-page":"260","DOI":"10.1097\/MCO.0b013e328337d826","article-title":"Epidemiology of myosteatosis","volume":"13","author":"Miljkovic","year":"2010","journal-title":"Curr Opin Clin Nutr Metab Care"},{"key":"ref35","doi-asserted-by":"publisher","first-page":"1063","DOI":"10.1093\/gerona\/gly183","article-title":"Opportunistic measurement of skeletal muscle size and muscle attenuation on computed tomography predicts 1-year mortality in Medicare patients","volume":"74","author":"Lenchik","year":"2019","journal-title":"J Gerontol A Biol Sci Med Sci"},{"key":"ref36","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1590\/0100-3984.2017.0211","article-title":"Quantification of visceral adipose tissue by computed tomography and magnetic resonance imaging: reproducibility and accuracy","volume":"52","author":"Pescatori","year":"2019","journal-title":"Radiol Bras"},{"key":"ref37","doi-asserted-by":"publisher","first-page":"1505","DOI":"10.1016\/j.ejrad.2016.03.001","article-title":"Muscle analysis using pQCT, DXA and MRI","volume":"85","author":"Erlandson","year":"2016","journal-title":"Eur J Radiol"},{"key":"ref38","doi-asserted-by":"publisher","first-page":"299","DOI":"10.1016\/j.eswa.2018.09.008","article-title":"Efficient solution of Otsu multilevel image thresholding: a comparative study","volume":"116","author":"Merzban","year":"2019","journal-title":"Expert Syst Appl"},{"key":"ref39","doi-asserted-by":"publisher","first-page":"2984","DOI":"10.1002\/jcsm.13113","article-title":"Comment on \"diagnosis, prevalence, and mortality of sarcopenia in dialysis patients: a systematic review and meta-analysis\" by Shu et al.","volume":"14","author":"Zhang","year":"2023","journal-title":"J Cachexia Sarcopenia Muscle"},{"key":"ref40","author":"Burke","year":"2015"},{"key":"ref41","doi-asserted-by":"publisher","first-page":"12","DOI":"10.3389\/fonc.2022.1037896","article-title":"Visualising spatial heterogeneity in glioblastoma using imaging habitats","volume":"12","author":"Waqar","year":"2022","journal-title":"Front Oncol"},{"key":"ref42","doi-asserted-by":"publisher","first-page":"e009322","DOI":"10.1161\/CIRCHEARTFAILURE.121.009322","article-title":"Current approach to the diagnosis of sarcopenia in heart failure: a narrative review on the role of clinical and imaging assessments","volume":"15","author":"Mirzai","year":"2022","journal-title":"Circ Heart Fail"}],"container-title":["Frontiers in Public Health"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fpubh.2025.1649400\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,25]],"date-time":"2025-09-25T05:30:22Z","timestamp":1758778222000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fpubh.2025.1649400\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,25]]},"references-count":42,"alternative-id":["10.3389\/fpubh.2025.1649400"],"URL":"https:\/\/doi.org\/10.3389\/fpubh.2025.1649400","relation":{},"ISSN":["2296-2565"],"issn-type":[{"value":"2296-2565","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,9,25]]},"article-number":"1649400"}}