{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,23]],"date-time":"2026-07-23T05:03:30Z","timestamp":1784783010728,"version":"3.55.0"},"reference-count":38,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,7,23]],"date-time":"2026-07-23T00:00:00Z","timestamp":1784764800000},"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. Endocrinol."],"abstract":"<jats:sec>\n                    <jats:title>Purpose<\/jats:title>\n                    <jats:p>To develop and validate an AI algorithm that enables dual-site (spine and hip) BMD assessment for opportunistic osteoporosis screening using a single kidney-ureter-bladder (KUB) radiograph.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Materials and methods<\/jats:title>\n                    <jats:p>In this institutional review board approved prospective study, we developed the SHield pipeline for opportunistic osteoporosis screening. From an initial dataset of 15,175 KUB images, a final cohort of 4,436 patients (mean age 69.0 \u00b1 12.2 years) was included for model development after exclusions for suboptimal quality or incomplete region of interests. The pipeline analyzes both the spine and hip regions on a single KUB to predict site-specific BMD values. Finally, it integrates these dual-site predictions to determine the lowest T-score, mimicking the standard clinical DXA reporting protocol which evaluates both the lumbar spine and proximal femur.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>\n                      On the internal test set (628 patients), the hip and spine AI models demonstrated Pearson correlation coefficients of 0.887 and 0.921 and RMSEs of 0.057 and 0.062, respectively, compared to DXA-measured BMD, achieving AUCs of 0.894 and 0.956 for predicting T-scores \u2264-2.5. In a subsequent prospective feasibility study (51 patients), we employed a conservative detection threshold of T\n                      <jats:sub>m<\/jats:sub>\n                      -score \u2264-2.8 to minimize false positives and unnecessary referrals. The final AI pipeline achieved a Pearson correlation of 0.959, an AUC of 0.969, 100% PPV, 100% specificity, and 83.8% NPV.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>This paper presents the first AI pipeline that enables gold-standard-aligned, dual-site BMD estimation and opportunistic osteoporosis screening from a single KUB radiograph. Validated prospectively, its high accuracy and specificity confirm its potential to significantly increase early detection rates without overwhelming clinical workflows.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fendo.2026.1906679","type":"journal-article","created":{"date-parts":[[2026,7,23]],"date-time":"2026-07-23T04:29:51Z","timestamp":1784780991000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Comprehensive opportunistic osteoporosis screening with AI: retrospective development and prospective validation of dual-site BMD prediction from a single radiograph"],"prefix":"10.3389","volume":"17","author":[{"given":"Hsuan-Yin","family":"Lin","sequence":"first","affiliation":[{"name":"Department of Medical Imaging, Taichung Veterans General Hospital","place":["Taichung, Taiwan"]},{"name":"School of Medicine, College of Medicine, National Yang Ming Chiao Tung University","place":["Taipei, Taiwan"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jyh-Wen","family":"Chai","sequence":"additional","affiliation":[{"name":"Department of Medical Imaging, Taichung Veterans General Hospital","place":["Taichung, Taiwan"]},{"name":"School of Medicine, College of Medicine, National Yang Ming Chiao Tung University","place":["Taipei, Taiwan"]},{"name":"Department of Medical Research, Taichung Veterans General Hospital","place":["Taichung, Taiwan"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qingzong","family":"Tseng","sequence":"additional","affiliation":[{"name":"Alpha Intelligence Manifolds","place":["New Taipei City, Taiwan"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Cheng-Wei","family":"Lin","sequence":"additional","affiliation":[{"name":"Alpha Intelligence Manifolds","place":["New Taipei City, Taiwan"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kuan-Jung","family":"Pan","sequence":"additional","affiliation":[{"name":"Department of Medical Imaging, Taichung Veterans General Hospital","place":["Taichung, Taiwan"]},{"name":"Department of Medical Research, Taichung Veterans General Hospital","place":["Taichung, Taiwan"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kai-Wei","family":"Liu","sequence":"additional","affiliation":[{"name":"Master of Computational Data Science, Carnegie Mellon University","place":["Pittsburgh, PA, United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ya-Chu","family":"Shih","sequence":"additional","affiliation":[{"name":"Department of Medical Imaging, Taichung Veterans General Hospital","place":["Taichung, Taiwan"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,7,23]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","DOI":"10.1001\/jama.285.6.785","article-title":"Osteoporosis prevention, diagnosis, and therapy","volume":"285","year":"2001","journal-title":"JAMA"},{"key":"B2","doi-asserted-by":"publisher","first-page":"46","DOI":"10.5152\/eurjrheum.2016.048","article-title":"An overview and management of osteoporosis","volume":"4","author":"S\u00f6zen","year":"2017","journal-title":"Eur J Rheumatol"},{"key":"B3","doi-asserted-by":"publisher","DOI":"10.1001\/jama.2009.50","article-title":"Mortality risk associated with low-trauma osteoporotic fracture and subsequent fracture in men and women","volume":"301","author":"Bliuc","year":"2009","journal-title":"JAMA"},{"key":"B4","doi-asserted-by":"publisher","DOI":"10.1007\/s00198-006-0172-4","article-title":"An estimate of the worldwide prevalence and disability associated with osteoporotic fractures","volume":"17","author":"Johnell","year":"2006","journal-title":"Osteoporos Int"},{"key":"B5","doi-asserted-by":"publisher","DOI":"10.5694\/j.1326-5377.2004.tb05908.x","article-title":"Osteoporosis: underrated, underdiagnosed and undertreated","volume":"180","author":"Nguyen","year":"2004","journal-title":"Med J Aust"},{"key":"B6","doi-asserted-by":"publisher","DOI":"10.1016\/j.jfma.2023.05.001","article-title":"Epidemiology and clinical impact of osteoporosis in Taiwan: A 12-year trend of a nationwide population-based study","volume":"122","author":"Lee","year":"2023","journal-title":"J Formos Med Assoc"},{"key":"B7","doi-asserted-by":"publisher","DOI":"10.7326\/0003-4819-158-8-201304160-00003","article-title":"Opportunistic screening for osteoporosis using abdominal computed tomography scans obtained for other indications","volume":"158","author":"Pickhardt","year":"2013","journal-title":"Ann Intern Med"},{"key":"B8","doi-asserted-by":"publisher","DOI":"10.1109\/RBME.2018.2852620","article-title":"Current and emerging diagnostic imaging-based techniques for assessment of osteoporosis and fracture risk","volume":"12","author":"Areeckal","year":"2019","journal-title":"IEEE Rev BioMed Eng"},{"key":"B9","doi-asserted-by":"publisher","DOI":"10.1259\/0007-1285-49-587-912","article-title":"Quantitative radiology: radiogrammetry of cortical bone","volume":"49","author":"Dequeker","year":"1976","journal-title":"Br J Radiol"},{"key":"B10","doi-asserted-by":"publisher","DOI":"10.1016\/j.bone.2016.02.011","article-title":"Digital X-ray radiogrammetry in the study of osteoporotic fractures: Comparison to dual energy X-ray absorptiometry and FRAX","volume":"86","author":"Kalvesten","year":"2016","journal-title":"Bone"},{"key":"B11","doi-asserted-by":"publisher","DOI":"10.1148\/radiol.231937","article-title":"Osteoporotic precise screening using chest radiography and artificial neural network: The OPSCAN randomized controlled trial","volume":"311","author":"Lin","year":"2024","journal-title":"Radiology"},{"key":"B12","doi-asserted-by":"publisher","DOI":"10.1016\/j.bone.2020.115561","article-title":"Deep learning of lumbar spine X-ray for osteopenia and osteoporosis screening: A multicenter retrospective cohort study","volume":"140","author":"Zhang","year":"2020","journal-title":"Bone"},{"key":"B13","doi-asserted-by":"publisher","DOI":"10.3389\/fendo.2022.971877","article-title":"Deep learning for screening primary osteopenia and osteoporosis using spine radiographs and patient clinical covariates in a Chinese population","volume":"13","author":"Mao","year":"2022","journal-title":"Front Endocrinol"},{"key":"B14","doi-asserted-by":"publisher","DOI":"10.1002\/jbmr.4814","article-title":"Deep-learning-based detection of vertebral fracture and osteoporosis using lateral spine X-ray radiography","volume":"38","author":"Hong","year":"2023","journal-title":"J Bone Miner Res"},{"key":"B15","doi-asserted-by":"publisher","DOI":"10.1148\/ryai.210212","article-title":"Deep radiomics-based approach to the diagnosis of osteoporosis using hip radiographs","volume":"4","author":"Kim","year":"2022","journal-title":"Radiol Artif Intell"},{"key":"B16","doi-asserted-by":"publisher","DOI":"10.3390\/medicina57080846","article-title":"Effect of patient clinical variables in osteoporosis classification using hip X-rays in deep learning analysis","volume":"57","author":"Yamamoto","year":"2021","journal-title":"Med (Kaunas)"},{"key":"B17","doi-asserted-by":"publisher","first-page":"153","DOI":"10.1007\/s11657-021-00985-8","article-title":"Application of deep learning neural network in predicting bone mineral density from plain X-ray radiography","volume":"16","author":"Ho","year":"2021","journal-title":"Arch Osteoporos"},{"key":"B18","doi-asserted-by":"publisher","first-page":"5472","DOI":"10.1038\/s41467-021-25779-x","article-title":"Automated bone mineral density prediction and fracture risk assessment using plain radiographs via deep learning","volume":"12","author":"Hsieh","year":"2021","journal-title":"Nat Commun"},{"key":"B19","doi-asserted-by":"publisher","DOI":"10.1001\/jama.2009.1462","article-title":"Incidence and mortality of hip fractures in the United States","volume":"302","author":"Brauer","year":"2009","journal-title":"JAMA"},{"key":"B20","doi-asserted-by":"crossref","DOI":"10.1109\/CVPR.2016.91","article-title":"You only look once: Unified, real-time object detection","author":"Redmon","year":"2016"},{"key":"B21","doi-asserted-by":"crossref","DOI":"10.1109\/ICPR.2006.479","article-title":"Efficient non-maximum suppression","author":"Neubeck","year":"2006"},{"key":"B22","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2110.09408","article-title":"HRFormer: high-resolution transformer for dense prediction","author":"Yuan","year":"2021"},{"key":"B23","doi-asserted-by":"publisher","DOI":"10.1049\/ipr2.12404","article-title":"A scale\u2010sensitive heatmap representation for multi\u2010person pose estimation","volume":"16","author":"Du","year":"2022","journal-title":"IET Image Proc"},{"key":"B24","doi-asserted-by":"crossref","DOI":"10.1109\/CVPR42600.2020.01044","article-title":"Designing network design spaces","author":"Radosavovic","year":"2020"},{"key":"B25","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-031-20050-2_26","article-title":"Domain generalization by mutual-information regularization with pre-trained models","author":"Cha","year":"2022"},{"key":"B26","doi-asserted-by":"publisher","first-page":"453","DOI":"10.1016\/j.jocd.2019.07.001","article-title":"Executive Summary of the 2019 ISCD Position Development Conference on Monitoring Treatment, DXA Cross-calibration and Least Significant Change, Spinal Cord Injury, Peri-prosthetic and Orthopedic Bone Health, Transgender Medicine, and Pediatrics","volume":"22","author":"Shuhart","year":"2019","journal-title":"J Clin Densitom"},{"key":"B27","doi-asserted-by":"publisher","DOI":"10.1016\/j.bone.2007.11.001","article-title":"A reference standard for the description of osteoporosis","volume":"42","author":"Kanis","year":"2008","journal-title":"Bone"},{"key":"B28","doi-asserted-by":"publisher","first-page":"60","DOI":"10.1016\/j.media.2017.07.005","article-title":"A survey on deep learning in medical image analysis","volume":"42","author":"Litjens","year":"2017","journal-title":"Med Image Anal"},{"key":"B29","doi-asserted-by":"publisher","DOI":"10.1148\/rg.2017160130","article-title":"Machine learning for medical imaging","volume":"37","author":"Erickson","year":"2017","journal-title":"RadioGraphics"},{"key":"B30","doi-asserted-by":"publisher","DOI":"10.1148\/radiol.2015151169","article-title":"Radiomics: Images are more than pictures, they are data","volume":"278","author":"Gillies","year":"2016","journal-title":"Radiology"},{"key":"B31","doi-asserted-by":"publisher","DOI":"10.1016\/s0140-6736(02)07948-5","article-title":"Uses and abuses of screening tests","volume":"359","author":"Grimes","year":"2002","journal-title":"Lancet"},{"key":"B32","doi-asserted-by":"publisher","DOI":"10.1136\/bmjopen-2016-012799","article-title":"STARD 2015 guidelines for reporting diagnostic accuracy studies: explanation and elaboration","volume":"6","author":"Cohen","year":"2016","journal-title":"BMJ Open"},{"key":"B33","doi-asserted-by":"publisher","DOI":"10.3389\/fpubh.2017.00307","article-title":"Sensitivity, specificity, and predictive values: Foundations, pliabilities, and pitfalls in research and practice","volume":"5","author":"Trevethan","year":"2017","journal-title":"Front Public Health"},{"key":"B34","doi-asserted-by":"crossref","first-page":"22","DOI":"10.1007\/978-3-319-26757-9_3","article-title":"Evaluation of fracture risk","volume-title":"Pocket Reference to Osteoporosis","author":"McCloskey","year":"2019"},{"key":"B35","doi-asserted-by":"publisher","DOI":"10.1148\/radiol.2019181648","article-title":"Opportunistic osteoporosis screening at routine abdominal and thoracic CT: Normative L1 trabecular attenuation values in more than 20 000 adults","volume":"291","author":"Jang","year":"2019","journal-title":"Radiology"},{"key":"B36","doi-asserted-by":"publisher","DOI":"10.1186\/1472-6823-5-3","article-title":"Discordance in diagnosis of osteoporosis using spine and hip bone densitometry","volume":"5","author":"Moayyeri","year":"2005","journal-title":"BMC Endocr Disord"},{"key":"B37","doi-asserted-by":"publisher","first-page":"77","DOI":"10.1038\/s41591-019-0720-z","article-title":"Automated opportunistic osteoporotic fracture risk assessment using computed tomography scans to aid in FRAX underutilization","volume":"26","author":"Dagan","year":"2020","journal-title":"Nat Med"},{"key":"B38","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s00521-019-04051-w","article-title":"The importance of interpretability and visualization in machine learning for applications in medicine and health care","volume":"32","author":"Vellido","year":"2020","journal-title":"Neural Comput Appl"}],"container-title":["Frontiers in Endocrinology"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fendo.2026.1906679\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,23]],"date-time":"2026-07-23T04:29:52Z","timestamp":1784780992000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fendo.2026.1906679\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,23]]},"references-count":38,"alternative-id":["10.3389\/fendo.2026.1906679"],"URL":"https:\/\/doi.org\/10.3389\/fendo.2026.1906679","relation":{},"ISSN":["1664-2392"],"issn-type":[{"value":"1664-2392","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,23]]},"article-number":"1906679"}}