{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,4]],"date-time":"2026-11-04T22:53:42Z","timestamp":1793832822627,"version":"4.6.1"},"reference-count":30,"publisher":"Springer Science and Business Media LLC","issue":"5","license":[{"start":{"date-parts":[[2025,12,1]],"date-time":"2025-12-01T00:00:00Z","timestamp":1764547200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2025,12,1]],"date-time":"2025-12-01T00:00:00Z","timestamp":1764547200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100003725","name":"National Research Foundation of Korea","doi-asserted-by":"publisher","award":["2020R1A2C2011587, 2021R1A2C2003410"],"award-info":[{"award-number":["2020R1A2C2011587, 2021R1A2C2003410"]}],"id":[{"id":"10.13039\/501100003725","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Eur Radiol"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Objectives<\/jats:title>\n                    <jats:p>To develop and externally validate a computed tomography (CT)-based multitask learning model to predict fracture risk.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Materials and methods<\/jats:title>\n                    <jats:p>This study was conducted in two parts, using a multitasking learning approach. We developed a cross-sectional vertebral fracture (VF) detection model using abdominal CT scans of 2553 patients aged 50\u201380 years. Then, we leveraged this detection model within a multitask learning framework to develop a longitudinal VF prediction model over a 5-year follow-up period. External testing was performed on 1506 patients from two independent hospitals. The performance was compared between the single-task and multitask models, bone-only and bone+muscle images, and image-only and clinical models.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>\n                      For the cross-sectional fracture detection model, the mean age of the patients was 76.2 years, and 66.7% were female. In the classification task for detection of VF, the model using both bone and muscle showed an area under the receiver operating characteristic curve (AUROC) of 0.82 in the development set and 0.80 in the external test sets. Using multitask learning, the bone\u2009+\u2009muscle image model showed a c-index of 0.68 and had superior performance than the bone-only model in the external test set for 2-year, 3-year, and 5-year AUROCs (0.79 vs. 0.75, 0.71 vs. 0.68, and 0.71 vs. 0.68, respectively, all\n                      <jats:italic>p<\/jats:italic>\n                      \u2009&lt;\u20090.01). Also, the multitask model significantly outperformed the Fracture Risk Assessment Tool (FRAX) (c-index: 0.68 vs. 0.66,\n                      <jats:italic>p<\/jats:italic>\n                      \u2009&lt;\u20090.01).\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>The CT-based multitask learning model integrating both bone and muscle data showed superior predictive performance for VFs compared with models using bone images only and traditional clinical models.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Key Points<\/jats:title>\n                    <jats:p>\n                      <jats:bold>\n                        <jats:italic>Question<\/jats:italic>\n                      <\/jats:bold>\n                      <jats:italic>Vertebral fracture risk remains underestimated in many individuals undergoing CT scans for other reasons, highlighting the need for improved opportunistic prediction tools.<\/jats:italic>\n                    <\/jats:p>\n                    <jats:p>\n                      <jats:bold>\n                        <jats:italic>Findings<\/jats:italic>\n                      <\/jats:bold>\n                      <jats:italic>A multitask deep learning model integrating both bone and muscle features from CT scans demonstrated superior performance compared to bone-only and traditional clinical models, including FRAX.<\/jats:italic>\n                    <\/jats:p>\n                    <jats:p>\n                      <jats:bold>\n                        <jats:italic>Clinical relevance<\/jats:italic>\n                      <\/jats:bold>\n                      <jats:italic>The proposed model enables accurate vertebral fracture risk prediction using routinely acquired CT scans, facilitating early identification and intervention without the need for additional tests.<\/jats:italic>\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Graphical Abstract<\/jats:title>\n                  <\/jats:sec>","DOI":"10.1007\/s00330-025-12049-3","type":"journal-article","created":{"date-parts":[[2025,12,1]],"date-time":"2025-12-01T18:42:02Z","timestamp":1764614522000},"page":"4177-4186","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":7,"title":["Enhancing vertebral fracture prediction using multitask deep learning computed tomography imaging of bone and muscle"],"prefix":"10.1007","volume":"36","author":[{"given":"Sung Hye","family":"Kong","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Saemee","family":"Choi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wonwoo","family":"Cho","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sung Bae","family":"Park","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Seung Shin","family":"Park","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jaegul","family":"Choo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1932-0234","authenticated-orcid":false,"given":"Jung Hee","family":"Kim","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sang Wan","family":"Kim","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chan Soo","family":"Shin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,12,1]]},"reference":[{"key":"12049_CR1","doi-asserted-by":"publisher","first-page":"1195","DOI":"10.1007\/s00198-020-05769-3","volume":"32","author":"O Tran","year":"2021","unstructured":"Tran O, Silverman S, Xu X et al (2021) Long-term direct and indirect economic burden associated with osteoporotic fracture in US postmenopausal women. Osteoporos Int 32:1195\u20131205","journal-title":"Osteoporos Int"},{"key":"12049_CR2","doi-asserted-by":"publisher","first-page":"821","DOI":"10.1177\/1060028020970518","volume":"55","author":"SA Williams","year":"2021","unstructured":"Williams SA, Daigle SG, Weiss R, Wang Y, Arora T, Curtis JR (2021) Economic burden of osteoporosis-related fractures in the US medicare population. Ann Pharmacother 55:821\u2013829","journal-title":"Ann Pharmacother"},{"key":"12049_CR3","doi-asserted-by":"publisher","first-page":"281","DOI":"10.11005\/jbm.2020.27.4.281","volume":"27","author":"SH Ahn","year":"2020","unstructured":"Ahn SH, Park SM, Park SY et al (2020) Osteoporosis and osteoporotic fracture fact sheet in Korea. J Bone Metab 27:281\u2013290","journal-title":"J Bone Metab"},{"key":"12049_CR4","doi-asserted-by":"publisher","first-page":"1947","DOI":"10.1359\/jbmr.2003.18.11.1947","volume":"18","author":"KL Stone","year":"2003","unstructured":"Stone KL, Seeley DG, Lui LY et al (2003) BMD at multiple sites and risk of fracture of multiple types: long-term results from the Study of Osteoporotic Fractures. J Bone Miner Res 18:1947\u20131954","journal-title":"J Bone Miner Res"},{"key":"12049_CR5","doi-asserted-by":"crossref","unstructured":"Amarnath AL, Franks P, Robbins JA, Xing G, Fenton JJ (2015) Underuse and overuse of osteoporosis screening in a regional health system: a retrospective cohort study. J Gen Intern Med 30:1733\u20131740","DOI":"10.1007\/s11606-015-3349-8"},{"key":"12049_CR6","unstructured":"IMV (2022) IMV 2022 CT Market Outlook Report. IMV Medical Information Division, Des Plaines, IL"},{"key":"12049_CR7","doi-asserted-by":"publisher","DOI":"10.1007\/s11926-018-0784-7","volume":"20","author":"L Lenchik","year":"2018","unstructured":"Lenchik L, Weaver AA, Ward RJ, Boone JM, Boutin RD (2018) Opportunistic screening for osteoporosis using computed tomography: state of the art and argument for paradigm shift. Curr Rheumatol Rep 20:74","journal-title":"Curr Rheumatol Rep"},{"key":"12049_CR8","doi-asserted-by":"publisher","first-page":"588","DOI":"10.7326\/0003-4819-158-8-201304160-00003","volume":"158","author":"PJ Pickhardt","year":"2013","unstructured":"Pickhardt PJ, Pooler BD, Lauder T, del Rio AM, Bruce RJ, Binkley N (2013) Opportunistic screening for osteoporosis using abdominal computed tomography scans obtained for other indications. Ann Intern Med 158:588\u2013595","journal-title":"Ann Intern Med"},{"key":"12049_CR9","doi-asserted-by":"publisher","first-page":"983","DOI":"10.1007\/s00198-016-3804-3","volume":"28","author":"E Alacreu","year":"2017","unstructured":"Alacreu E, Moratal D, Arana E (2017) Opportunistic screening for osteoporosis by routine CT in Southern Europe. Osteoporosis Int 28:983\u2013990","journal-title":"Osteoporosis Int"},{"key":"12049_CR10","doi-asserted-by":"publisher","first-page":"e48535","DOI":"10.2196\/48535","volume":"26","author":"SH Kong","year":"2024","unstructured":"Kong SH, Cho W, Park SB et al (2024) A computed tomography-based fracture prediction model with images of vertebral bones and muscles by employing deep learning: development and validation study. J Med Internet Res 26:e48535","journal-title":"J Med Internet Res"},{"key":"12049_CR11","doi-asserted-by":"publisher","first-page":"22","DOI":"10.1080\/13697137.2021.1945027","volume":"25","author":"EV McCloskey","year":"2022","unstructured":"McCloskey EV, Harvey NC, Johansson H et al (2022) Fracture risk assessment by the FRAX model. Climacteric 25:22\u201328","journal-title":"Climacteric"},{"key":"12049_CR12","doi-asserted-by":"publisher","first-page":"2173","DOI":"10.1007\/s00198-021-05963-x","volume":"32","author":"Z Teng","year":"2021","unstructured":"Teng Z, Zhu Y, Teng Y et al (2021) The analysis of osteosarcopenia as a risk factor for fractures, mortality, and falls. Osteoporos Int 32:2173\u20132183","journal-title":"Osteoporos Int"},{"key":"12049_CR13","doi-asserted-by":"publisher","first-page":"103","DOI":"10.1016\/j.regg.2018.09.010","volume":"54","author":"B Cedeno-Veloz","year":"2019","unstructured":"Cedeno-Veloz B, L\u00f3pez-D\u00f3riga Bonnardeauxa P, Duque G (2019) [Osteosarcopenia: A narrative review]. Rev Esp Geriatr Gerontol 54:103\u2013108","journal-title":"Rev Esp Geriatr Gerontol"},{"key":"12049_CR14","doi-asserted-by":"publisher","first-page":"451","DOI":"10.1016\/j.spinee.2015.07.001","volume":"16","author":"M Yagi","year":"2016","unstructured":"Yagi M, Hosogane N, Watanabe K, Asazuma T, Matsumoto M; Keio Spine Research Group (2016) The paravertebral muscle and psoas for the maintenance of global spinal alignment in patient with degenerative lumbar scoliosis. Spine J 16:451\u2013458","journal-title":"Spine J"},{"key":"12049_CR15","doi-asserted-by":"publisher","DOI":"10.1007\/s11657-020-00866-6","volume":"16","author":"H Habibi","year":"2021","unstructured":"Habibi H, Takahashi S, Hoshino M et al (2021) Impact of paravertebral muscle in thoracolumbar and lower lumbar regions on outcomes following osteoporotic vertebral fracture: a multicenter cohort study. Arch Osteoporos 16:2","journal-title":"Arch Osteoporos"},{"key":"12049_CR16","doi-asserted-by":"publisher","first-page":"E798","DOI":"10.1097\/BSD.0000000000000424","volume":"30","author":"MK Choi","year":"2017","unstructured":"Choi MK, Kim SB, Park CK, Malla HP, Kim SM (2017) Cross-sectional area of the lumbar spine trunk muscle and posterior lumbar interbody fusion rate: a retrospective study. Clin Spine Surg 30:E798\u2013e803","journal-title":"Clin Spine Surg"},{"key":"12049_CR17","doi-asserted-by":"publisher","first-page":"75","DOI":"10.11005\/jbm.2013.20.2.75","volume":"20","author":"JY Kim","year":"2013","unstructured":"Kim JY, Chae SU, Kim GD, Cha MS (2013) Changes of paraspinal muscles in postmenopausal osteoporotic spinal compression fractures: magnetic resonance imaging study. J Bone Metab 20:75\u201381","journal-title":"J Bone Metab"},{"key":"12049_CR18","doi-asserted-by":"publisher","first-page":"513","DOI":"10.1359\/jbmr.090807","volume":"25","author":"T Lang","year":"2010","unstructured":"Lang T, Cauley JA, Tylavsky F, Bauer D, Cummings S, Harris TB; Health ABC Study (2010) Computed tomographic measurements of thigh muscle cross-sectional area and attenuation coefficient predict hip fracture: the health, aging, and body composition study. J Bone Miner Res 25:513\u2013519","journal-title":"J Bone Miner Res"},{"key":"12049_CR19","doi-asserted-by":"publisher","first-page":"1161","DOI":"10.3803\/EnM.2021.1348","volume":"36","author":"HK Kim","year":"2021","unstructured":"Kim HK, Kim CH (2021) Quality matters as much as quantity of skeletal muscle: clinical implications of myosteatosis in cardiometabolic health. Endocrinol Metab (Seoul) 36:1161\u20131174","journal-title":"Endocrinol Metab (Seoul)"},{"key":"12049_CR20","doi-asserted-by":"publisher","first-page":"41","DOI":"10.1023\/A:1007379606734","volume":"28","author":"R Caruana","year":"1997","unstructured":"Caruana R (1997) Multitask learning. Machine learning 28:41\u201375","journal-title":"Machine learning"},{"key":"12049_CR21","doi-asserted-by":"publisher","first-page":"30","DOI":"10.1093\/nsr\/nwx105","volume":"5","author":"Y Zhang","year":"2018","unstructured":"Zhang Y, Yang Q (2018) An overview of multi-task learning. National Science Review 5:30\u201343","journal-title":"National Science Review"},{"key":"12049_CR22","doi-asserted-by":"publisher","first-page":"5586","DOI":"10.1109\/TKDE.2021.3070203","volume":"34","author":"Y Zhang","year":"2021","unstructured":"Zhang Y, Yang Q (2022) A survey on multi-task learning. IEEE transactions on knowledge and data engineering 34:5586\u20135609","journal-title":"IEEE transactions on knowledge and data engineering"},{"key":"12049_CR23","doi-asserted-by":"publisher","first-page":"411","DOI":"10.1007\/s11914-018-0450-z","volume":"16","author":"F Johannesdottir","year":"2018","unstructured":"Johannesdottir F, Allaire B, Bouxsein ML (2018) Fracture prediction by computed tomography and finite element analysis: current and future perspectives. Curr Osteoporos Rep 16:411\u2013422","journal-title":"Curr Osteoporos Rep"},{"key":"12049_CR24","doi-asserted-by":"publisher","first-page":"323","DOI":"10.1007\/s00198-018-4716-1","volume":"30","author":"BT Allaire","year":"2019","unstructured":"Allaire BT, Lu D, Johannesdottir F et al (2019) Prediction of incident vertebral fracture using CT-based finite element analysis. Osteoporos Int 30:323\u2013331","journal-title":"Osteoporos Int"},{"key":"12049_CR25","doi-asserted-by":"publisher","first-page":"501","DOI":"10.1007\/s40618-023-02219-9","volume":"47","author":"M Schini","year":"2024","unstructured":"Schini M, Johansson H, Harvey NC, Lorentzon M, Kanis JA, McCloskey EV (2024) An overview of the use of the fracture risk assessment tool (FRAX) in osteoporosis. J Endocrinol Invest 47:501\u2013511","journal-title":"J Endocrinol Invest"},{"key":"12049_CR26","doi-asserted-by":"publisher","first-page":"678","DOI":"10.1148\/radiology.190.3.8115610","volume":"190","author":"V Gilsanz","year":"1994","unstructured":"Gilsanz V, Boechat MI, Gilsanz R, Loro ML, Roe TF, Goodman WG (1994) Gender differences in vertebral sizes in adults: biomechanical implications. Radiology 190:678\u2013682","journal-title":"Radiology"},{"key":"12049_CR27","doi-asserted-by":"publisher","first-page":"674","DOI":"10.3803\/EnM.2022.1461","volume":"37","author":"SH Kong","year":"2022","unstructured":"Kong SH, Lee JW, Bae BU et al (2022) Development of a spine X-ray-based fracture prediction model using a deep learning algorithm. Endocrinol Metab (Seoul) 37:674\u2013683","journal-title":"Endocrinol Metab (Seoul)"},{"key":"12049_CR28","doi-asserted-by":"publisher","first-page":"623","DOI":"10.1016\/j.bone.2012.10.031","volume":"52","author":"GJ Kazakia","year":"2013","unstructured":"Kazakia GJ, Nirody JA, Bernstein G, Sode M, Burghardt AJ, Majumdar S (2013) Age-and gender-related differences in cortical geometry and microstructure: improved sensitivity by regional analysis. Bone 52:623\u2013631","journal-title":"Bone"},{"key":"12049_CR29","doi-asserted-by":"publisher","first-page":"97","DOI":"10.1097\/00007632-198203000-00002","volume":"7","author":"S Bernick","year":"1982","unstructured":"Bernick S, Cailliet R (1982) Vertebral end-plate changes with aging of human vertebrae. Spine (Phila Pa 1976) 7:97\u2013102","journal-title":"Spine (Phila Pa 1976)"},{"key":"12049_CR30","doi-asserted-by":"publisher","first-page":"1562","DOI":"10.3390\/medicina58111562","volume":"58","author":"J Zhong","year":"2022","unstructured":"Zhong J, Xie W, Wang X et al (2022) The prevalence of sarcopenia among Hunan province community-dwelling adults aged 60 years and older and its relationship with lifestyle: diagnostic criteria from the Asian Working Group for sarcopenia 2019 update. Medicina (Kaunas) 58:1562","journal-title":"Medicina (Kaunas)"}],"container-title":["European Radiology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00330-025-12049-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00330-025-12049-3","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00330-025-12049-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,16]],"date-time":"2026-04-16T11:22:56Z","timestamp":1776338576000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00330-025-12049-3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,1]]},"references-count":30,"journal-issue":{"issue":"5","published-online":{"date-parts":[[2026,5]]}},"alternative-id":["12049"],"URL":"https:\/\/doi.org\/10.1007\/s00330-025-12049-3","relation":{},"ISSN":["1432-1084"],"issn-type":[{"value":"1432-1084","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,12,1]]},"assertion":[{"value":"20 May 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"26 August 2025","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"23 September 2025","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"1 December 2025","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Compliance with ethical standards"}},{"value":"The scientific guarantor of this publication is Jung Hee Kim.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Guarantor"}},{"value":"The authors of this manuscript declare no relationships with any companies, whose products or services may be related to the subject matter of the article.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}},{"value":"No complex statistical methods were necessary for this paper.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Statistics and biometry"}},{"value":"Written informed consent was waived by the Institutional Review Board.","order":5,"name":"Ethics","group":{"name":"EthicsHeading","label":"Informed consent"}},{"value":"Institutional Review Board approval was obtained.","order":6,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethical approval"}},{"value":"Some study subjects or cohorts have not been previously reported.","order":7,"name":"Ethics","group":{"name":"EthicsHeading","label":"Study subjects or cohorts overlap"}},{"order":8,"name":"Ethics","group":{"name":"EthicsHeading","label":"Methodology"}}]}}