{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,16]],"date-time":"2026-10-16T13:12:11Z","timestamp":1792156331285,"version":"4.4.0"},"reference-count":53,"publisher":"JMIR Publications Inc.","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["J Med Internet Res"],"abstract":"Abstract<\/jats:title>\n \n Background<\/jats:title>\n Osteoporosis is a prevalent skeletal disorder characterized by decreased bone mass and increased fracture risk; however, it frequently remains underdiagnosed due to limited health care resources and its asymptomatic progression. Deep learning (DL) provides a promising solution for automated screening using computed tomography (CT) scans, enabling earlier detection and improved management.<\/jats:p>\n <\/jats:sec>\n \n Objective<\/jats:title>\n This systematic review and meta-analysis aimed to investigate the diagnostic performance of DL models in diagnosing osteoporosis based on CT scans.<\/jats:p>\n <\/jats:sec>\n \n Methods<\/jats:title>\n This study was conducted under the PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) guidelines using articles extracted from PubMed, Scopus, Web of Science (Core), and Embase (Ovid). Studies involving adult participants who underwent CT and in which DL was applied for osteoporosis diagnosis were included. The QUADAS-2 (Quality Assessment of Diagnostic Accuracy Studies-2) tool was used to estimate the risk of bias in each study. The confusion matrices from the included studies were extracted to summarize the diagnostic performance of DL models for osteoporosis. Within a bivariate random-effects framework, sensitivity and specificity were jointly synthesized to yield the summary estimates. Heterogeneity was quantified with Higgins I\u00b2 statistics. Subgroup analyses were performed to explore potential sources of heterogeneity among the included studies.<\/jats:p>\n <\/jats:sec>\n \n Results<\/jats:title>\n \n This review included 24 studies, encompassing CT images from 29,808 participants. All studies used conventional CT scans and used DL-based architectures. Fifteen, 6, and 3 studies were assessed as having a low, uncertain, and high risk of bias, respectively. The meta-analysis included 20 studies. The pooled sensitivity and specificity were 0.88 (95% CI 0.85\u20100.91; I\n 2<\/jats:sup>\n =83.69%) and 0.94 (95% CI 0.91\u20100.96; I\n 2<\/jats:sup>\n =95.07%) for osteoporosis diagnosis; 0.81 (95% CI 0.76\u20100.85; I\n 2<\/jats:sup>\n =82.38%) and 0.92 (95% CI 0.90\u20100.94; I\n 2<\/jats:sup>\n =79.05%) for osteopenia identification; and 0.95 (95% CI 0.92\u20100.97; I\n 2<\/jats:sup>\n =98.28%) and 0.93 (95% CI 0.91\u20100.95; I\n 2<\/jats:sup>\n =94.93%) for normal case identification. The area under the curve of the DL models for identifying osteoporosis, osteopenia, and normal cases was 0.96 (95% CI 0.93\u20100.97), 0.94 (95% CI 0.92\u20100.96), and 0.98 (95% CI 0.96\u20100.99), respectively. Subgroup analyses revealed that models based on DenseNet variants (\n P<\/jats:italic>\n <.01), multislice input (\n P<\/jats:italic>\n <.01), 3D architecture (\n P<\/jats:italic>\n <.01), and CT as the reference standard (\n P<\/jats:italic>\n <.01) demonstrated superior diagnostic performance.\n <\/jats:p>\n <\/jats:sec>\n \n Conclusions<\/jats:title>\n This study indicated that CT-based DL models achieve promising diagnostic performance for osteoporosis. However, substantial heterogeneity among the included studies, limited external validation, and incomplete end-to-end pipelines constrain the generalizability of the proposed models. Further research is warranted to support their clinical translation and standardized application.<\/jats:p>\n <\/jats:sec>","DOI":"10.2196\/77155","type":"journal-article","created":{"date-parts":[[2025,10,14]],"date-time":"2025-10-14T15:10:06Z","timestamp":1760454606000},"page":"e77155-e77155","source":"Crossref","is-referenced-by-count":5,"title":["Deep Learning\u2013Assisted Automated Diagnosis of Osteoporosis Based on Computed Tomography Scans: Systematic Review and Meta-Analysis"],"prefix":"10.2196","volume":"27","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3271-1953","authenticated-orcid":false,"given":"Aobo","family":"Wang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1245-378X","authenticated-orcid":false,"given":"Ziqian","family":"Ma","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5016-858X","authenticated-orcid":false,"given":"Tianyi","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-0745-4427","authenticated-orcid":false,"given":"Ruiyuan","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-3022-9281","authenticated-orcid":false,"given":"Yu","family":"Xi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6308-1774","authenticated-orcid":false,"given":"Qichao","family":"Wu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5668-9527","authenticated-orcid":false,"given":"Shuo","family":"Yuan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0095-9476","authenticated-orcid":false,"given":"Ning","family":"Fan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5017-8507","authenticated-orcid":false,"given":"Peng","family":"Du","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1403-4159","authenticated-orcid":false,"given":"Lei","family":"Zang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1010","published-online":{"date-parts":[[2025,11,24]]},"reference":[{"issue":"3","key":"R1","doi-asserted-by":"publisher","first-page":"ITC17","DOI":"10.7326\/AITC201708010","article-title":"Osteoporosis","volume":"167","author":"Ensrud","journal-title":"Ann Intern Med"},{"issue":"10","key":"R2","doi-asserted-by":"publisher","first-page":"2137","DOI":"10.1007\/s00198-022-06454-3","article-title":"Global, regional prevalence, and risk factors of osteoporosis according to the World Health Organization diagnostic criteria: a systematic review and meta-analysis","volume":"33","author":"Xiao","journal-title":"Osteoporos Int"},{"issue":"4","key":"R3","doi-asserted-by":"publisher","first-page":"237","DOI":"10.1007\/s11154-010-9154-0","article-title":"Diagnosis and treatment of osteopenia","volume":"11","author":"Karaguzel","journal-title":"Rev Endocr Metab Disord"},{"issue":"7","key":"R4","doi-asserted-by":"publisher","first-page":"1929","DOI":"10.1007\/s00198-015-3093-2","article-title":"Projection of osteoporosis-related fractures and costs in China: 2010-2050","volume":"26","author":"Si","journal-title":"Osteoporos Int"},{"issue":"3","key":"R5","doi-asserted-by":"publisher","first-page":"529","DOI":"10.1016\/s0749-0690(02)00022-8","article-title":"Osteoporosis in elderly: prevention and treatment","volume":"18","author":"Srivastava","journal-title":"Clin Geriatr Med"},{"issue":"3","key":"R6","doi-asserted-by":"publisher","first-page":"427","DOI":"10.1002\/jbmr.4187","article-title":"Opportunistic screening using low-dose CT and the prevalence of osteoporosis in China: a nationwide, multicenter study","volume":"36","author":"Cheng","journal-title":"J Bone Miner Res"},{"issue":"1","key":"R7","doi-asserted-by":"publisher","DOI":"10.1186\/s13643-023-02181-w","article-title":"Screening for the primary prevention of fragility fractures among adults aged 40 years and older in primary care: systematic reviews of the effects and acceptability of screening and treatment, and the accuracy of risk prediction tools","volume":"12","author":"Gates","journal-title":"Syst Rev"},{"issue":"10","key":"R8","doi-asserted-by":"publisher","first-page":"1681","DOI":"10.1007\/s00198-024-07179-1","article-title":"Artificial intelligence-enhanced opportunistic screening of osteoporosis in CT scan: a scoping review","volume":"35","author":"Paderno","journal-title":"Osteoporos Int"},{"key":"R9","doi-asserted-by":"publisher","DOI":"10.1136\/bmj.n160","article-title":"PRISMA 2020 explanation and elaboration: updated guidance and exemplars for reporting systematic reviews","volume":"372","author":"Page","journal-title":"BMJ"},{"issue":"2","key":"R10","doi-asserted-by":"publisher","DOI":"10.1002\/cl2.1230","article-title":"PRISMA2020: an R package and Shiny app for producing PRISMA 2020-compliant flow diagrams, with interactivity for optimised digital transparency and open synthesis","volume":"18","author":"Haddaway","journal-title":"Campbell Syst Rev"},{"issue":"4","key":"R11","doi-asserted-by":"publisher","first-page":"388","DOI":"10.1001\/jama.2017.19163","article-title":"Preferred Reporting Items for a Systematic Review and Meta-Analysis of diagnostic test accuracy studies: the PRISMA-DTA statement","volume":"319","author":"McInnes","journal-title":"JAMA"},{"issue":"2","key":"R12","doi-asserted-by":"publisher","first-page":"181","DOI":"10.1002\/jrsm.1378","article-title":"Which academic search systems are suitable for systematic reviews or meta-analyses? Evaluating retrieval qualities of Google Scholar, PubMed, and 26 other resources","volume":"11","author":"Gusenbauer","journal-title":"Res Synth Methods"},{"issue":"8","key":"R13","doi-asserted-by":"publisher","first-page":"529","DOI":"10.7326\/0003-4819-155-8-201110180-00009","article-title":"QUADAS-2: a revised tool for the quality assessment of diagnostic accuracy studies","volume":"155","author":"Whiting","journal-title":"Ann Intern Med"},{"issue":"1","key":"R14","doi-asserted-by":"publisher","DOI":"10.3390\/bioengineering11010050","article-title":"Automatic osteoporosis screening system using radiomics and deep learning from low-dose chest CT images","volume":"11","author":"Tong","journal-title":"Bioengineering (Basel)"},{"issue":"21","key":"R15","doi-asserted-by":"publisher","DOI":"10.3390\/s22218189","article-title":"Application of deep convolutional neural networks in the diagnosis of osteoporosis","volume":"22","author":"Dzier\u017cak","journal-title":"Sensors (Basel)"},{"issue":"1","key":"R16","doi-asserted-by":"publisher","DOI":"10.1155\/2023\/3018320","article-title":"End to end multitask joint learning model for osteoporosis classification in CT images","volume":"2023","author":"Zhang","journal-title":"Comput Intell Neurosci"},{"issue":"1","key":"R17","doi-asserted-by":"publisher","DOI":"10.1186\/s13244-024-01817-2","article-title":"Application of deep learning model based on unenhanced chest CT for opportunistic screening of osteoporosis: a multicenter retrospective cohort study","volume":"16","author":"Huang","journal-title":"Insights Imaging"},{"issue":"1296047","key":"R18","doi-asserted-by":"publisher","DOI":"10.3389\/fendo.2024.1296047","article-title":"A comprehensive approach for osteoporosis detection through chest CT analysis and bone turnover markers: harnessing radiomics and deep learning techniques","volume":"15","author":"Fang","journal-title":"Front Endocrinol"},{"issue":"3","key":"R19","doi-asserted-by":"publisher","first-page":"881","DOI":"10.1007\/s00530-021-00884-5","article-title":"A holistic overview of deep learning approach in medical imaging","volume":"28","author":"Yousef","journal-title":"Multimed Syst"},{"issue":"11","key":"R20","doi-asserted-by":"publisher","first-page":"6812","DOI":"10.1016\/j.acra.2025.07.060","article-title":"Deep learning-enhanced opportunistic osteoporosis screening in 100 kV low-voltage chest CT: a novel way toward bone mineral density measurement and radiation dose reduction","volume":"32","author":"Li","journal-title":"Acad Radiol"},{"issue":"7","key":"R21","doi-asserted-by":"publisher","first-page":"4254","DOI":"10.1016\/j.acra.2024.11.062","article-title":"Deep learning-enhanced opportunistic osteoporosis screening in ultralow-voltage (80 kV) chest CT: a preliminary study","volume":"32","author":"Li","journal-title":"Acad Radiol"},{"issue":"1","key":"R22","doi-asserted-by":"publisher","first-page":"39","DOI":"10.1186\/2049-3258-72-39","article-title":"Metaprop: a Stata command to perform meta-analysis of binomial data","volume":"72","author":"Nyaga","journal-title":"Arch Public Health"},{"issue":"4","key":"R23","doi-asserted-by":"publisher","first-page":"2287","DOI":"10.1007\/s00330-024-11046-2","article-title":"Artificial intelligence assisted automatic screening of opportunistic osteoporosis in computed tomography images from different scanners","volume":"35","author":"Wu","journal-title":"Eur Radiol"},{"issue":"4","key":"R24","doi-asserted-by":"publisher","first-page":"2816","DOI":"10.21037\/qims-23-1617","article-title":"Fully automated deep learning system for osteoporosis screening using chest computed tomography images","volume":"14","author":"Wang","journal-title":"Quant Imaging Med Surg"},{"issue":"1","key":"R25","doi-asserted-by":"publisher","first-page":"117","DOI":"10.1007\/s00198-023-06900-w","article-title":"A study on whether deep learning models based on CT images for bone density classification and prediction can be used for opportunistic osteoporosis screening","volume":"35","author":"Peng","journal-title":"Osteoporos Int"},{"issue":"1","key":"R26","doi-asserted-by":"publisher","DOI":"10.1186\/s12891-024-07297-1","article-title":"Effectiveness of opportunistic osteoporosis screening on chest CT using the DCNN model","volume":"25","author":"Pan","journal-title":"BMC Musculoskelet Disord"},{"issue":"3","key":"R27","doi-asserted-by":"publisher","first-page":"467","DOI":"10.1097\/RCT.0000000000001437","article-title":"Feasibility of bone mineral density and bone microarchitecture assessment using deep learning with a convolutional neural network","volume":"47","author":"Yoshida","journal-title":"J Comput Assist Tomogr"},{"issue":"8","key":"R28","doi-asserted-by":"publisher","first-page":"5294","DOI":"10.21037\/qims-22-1438","article-title":"Development and validation of a fully automated system using deep learning for opportunistic osteoporosis screening using low-dose computed tomography scans","volume":"13","author":"Niu","journal-title":"Quant Imaging Med Surg"},{"issue":"4","key":"R29","doi-asserted-by":"publisher","first-page":"1831","DOI":"10.1007\/s00330-020-07312-8","article-title":"Opportunistic osteoporosis screening in multi-detector CT images using deep convolutional neural networks","volume":"31","author":"Fang","journal-title":"Eur Radiol"},{"issue":"6","key":"R30","doi-asserted-by":"publisher","first-page":"3549","DOI":"10.1007\/s00330-020-06677-0","article-title":"Prediction of bone mineral density from computed tomography: application of deep learning with a convolutional neural network","volume":"30","author":"Yasaka","journal-title":"Eur Radiol"},{"issue":"1061911","key":"R31","doi-asserted-by":"publisher","DOI":"10.3389\/fphys.2022.1061911","article-title":"Prediction of bone mineral density in CT using deep learning with explainability","volume":"13","author":"Kang","journal-title":"Front Physiol"},{"issue":"1","key":"R32","doi-asserted-by":"publisher","first-page":"71","DOI":"10.1159\/000542396","article-title":"Prediction of bone mineral density based on computer tomography images using deep learning model","volume":"71","author":"Li","journal-title":"Gerontology"},{"issue":"5","key":"R33","doi-asserted-by":"publisher","first-page":"971","DOI":"10.1007\/s00198-020-05673-w","article-title":"CNN-based qualitative detection of bone mineral density via diagnostic CT slices for osteoporosis screening","volume":"32","author":"Tang","journal-title":"Osteoporos Int"},{"issue":"3","key":"R34","doi-asserted-by":"publisher","first-page":"500","DOI":"10.3803\/EnM.2023.1860","article-title":"End-to-end semi-supervised opportunistic osteoporosis screening using computed tomography","volume":"39","author":"Oh","journal-title":"Endocrinol Metab (Seoul)"},{"issue":"7","key":"R35","doi-asserted-by":"publisher","first-page":"4296","DOI":"10.1002\/mp.16230","article-title":"Opportunistic screening for low bone density using abdominopelvic computed tomography scans","volume":"50","author":"Tariq","journal-title":"Med Phys"},{"issue":"1","key":"R36","doi-asserted-by":"publisher","first-page":"9","DOI":"10.4274\/dir.2023.232116","article-title":"Prediction of osteoporosis using MRI and CT scans with unimodal and multimodal deep-learning models","volume":"30","author":"K\u00fc\u00e7\u00fck\u00e7ilo\u011flu","journal-title":"Diagn Interv Radiol"},{"issue":"7","key":"R37","doi-asserted-by":"publisher","first-page":"4111","DOI":"10.1016\/j.acra.2025.02.041","article-title":"Automated fast prediction of bone mineral density from low-dose computed tomography","volume":"32","author":"Zhou","journal-title":"Acad Radiol"},{"key":"R38","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijmedinf.2025.105901","article-title":"A vision transformer-convolutional neural network framework for decision-transparent dual-energy X-ray absorptiometry recommendations using chest low-dose CT","volume":"199","author":"Kuo","journal-title":"Int J Med Inform"},{"issue":"107916","key":"R39","doi-asserted-by":"publisher","first-page":"107916","DOI":"10.1016\/j.compbiomed.2023.107916","article-title":"DeepmdQCT: a multitask network with domain invariant features and comprehensive attention mechanism for quantitative computer tomography diagnosis of osteoporosis","volume":"170","author":"Zhang","journal-title":"Comput Biol Med"},{"issue":"5S","key":"R40","doi-asserted-by":"publisher","first-page":"S189","DOI":"10.1016\/j.jacr.2017.02.018","article-title":"ACR appropriateness criteria\u00ae osteoporosis and bone mineral density","volume":"14","author":"Expert Panel on Musculoskeletal Imaging","journal-title":"J Am Coll Radiol"},{"issue":"1","key":"R41","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-023-45824-7","article-title":"Evaluation of deep learning-based quantitative computed tomography for opportunistic osteoporosis screening","volume":"14","author":"Oh","journal-title":"Sci Rep"},{"issue":"7","key":"R42","doi-asserted-by":"publisher","first-page":"4107","DOI":"10.1007\/s00330-020-06679-y","article-title":"Automatic opportunistic osteoporosis screening using low-dose chest computed tomography scans obtained for lung cancer screening","volume":"30","author":"Pan","journal-title":"Eur Radiol"},{"issue":"1","key":"R43","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-024-73709-w","article-title":"Automated deep learning-based bone mineral density assessment for opportunistic osteoporosis screening using various CT protocols with multi-vendor scanners","volume":"14","author":"Park","journal-title":"Sci Rep"},{"issue":"1152","key":"R44","doi-asserted-by":"publisher","DOI":"10.1259\/bjr.20230047","article-title":"Automated vertebral bone mineral density measurement with phantomless internal calibration in chest LDCT scans using deep learning","volume":"96","author":"Pan","journal-title":"Br J Radiol"},{"issue":"5","key":"R45","doi-asserted-by":"publisher","DOI":"10.1148\/ryai.220042","article-title":"Improved CT-based osteoporosis assessment with a fully automated deep learning tool","volume":"4","author":"Pickhardt","journal-title":"Radiol Artif Intell"},{"issue":"3","key":"R46","doi-asserted-by":"publisher","first-page":"1229","DOI":"10.1007\/s00261-020-02755-5","article-title":"Fully automated CT imaging biomarkers of bone, muscle, and fat: correcting for the effect of intravenous contrast","volume":"46","author":"Perez","journal-title":"Abdom Radiol (NY)"},{"issue":"7","key":"R47","doi-asserted-by":"publisher","first-page":"1135","DOI":"10.1016\/j.spinee.2024.02.018","article-title":"Using advanced imaging to measure bone density, compression fracture risk, and risk for construct failure after spine surgery","volume":"24","author":"Agaronnik","journal-title":"Spine J"},{"issue":"10","key":"R48","doi-asserted-by":"publisher","first-page":"1693","DOI":"10.1007\/s00198-024-07136-y","article-title":"Diagnostic performance of radiomics for predicting osteoporosis in adults: a systematic review and meta-analysis","volume":"35","author":"Deng","journal-title":"Osteoporos Int"},{"issue":"10","key":"R49","doi-asserted-by":"publisher","first-page":"1738","DOI":"10.1016\/j.spinee.2021.03.008","article-title":"A meta-analysis of the diagnostic accuracy of Hounsfield units on computed topography relative to dual-energy X-ray absorptiometry for the diagnosis of osteoporosis in the spine surgery population","volume":"21","author":"Ahern","journal-title":"Spine J"},{"issue":"11","key":"R50","doi-asserted-by":"publisher","first-page":"12163","DOI":"10.1109\/TCYB.2020.3042837","article-title":"PAM-DenseNet: a deep convolutional neural network for computer-aided COVID-19 diagnosis","volume":"52","author":"Xiao","journal-title":"IEEE Trans Cybern"},{"key":"R51","doi-asserted-by":"publisher","DOI":"10.7717\/peerj-cs.1177","article-title":"Alzheimer\u2019s disease diagnosis and classification using deep learning techniques","volume":"8","author":"Al Shehri","journal-title":"PeerJ Comput Sci"},{"issue":"1","key":"R52","doi-asserted-by":"publisher","DOI":"10.1186\/s12877-023-03963-6","article-title":"Quantitative CT screening improved lumbar BMD evaluation in older patients compared to dual-energy X-ray absorptiometry","volume":"23","author":"Lin","journal-title":"BMC Geriatr"},{"key":"R53","doi-asserted-by":"publisher","DOI":"10.1016\/j.jot.2018.11.003","article-title":"Discordance in diagnosis of osteoporosis by quantitative computed tomography and dual-energy X-ray absorptiometry in Chinese elderly men","volume":"18","author":"Xu","journal-title":"J Orthop Translat"}],"container-title":["Journal of Medical Internet Research"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.jmir.org\/2025\/1\/e77155","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T18:09:13Z","timestamp":1782842953000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.jmir.org\/2025\/1\/e77155"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,24]]},"references-count":53,"URL":"https:\/\/doi.org\/10.2196\/77155","relation":{},"ISSN":["1438-8871"],"issn-type":[{"value":"1438-8871","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,11,24]]},"article-number":"v27i3e77155"}}