{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,6]],"date-time":"2026-10-06T16:16:13Z","timestamp":1791303373530,"version":"4.1.0"},"reference-count":58,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T00:00:00Z","timestamp":1777420800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100014882","name":"Department of Finance of Hebei","doi-asserted-by":"publisher","award":["LS202203, ZF2026070, HR202502086"],"award-info":[{"award-number":["LS202203, ZF2026070, HR202502086"]}],"id":[{"id":"10.13039\/501100014882","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Endocrinol."],"abstract":"<jats:sec>\n                    <jats:title>Objective<\/jats:title>\n                    <jats:p>To establish a sequence-specific predictive model for spinal bone loss by leveraging conventional lumbar MRI, targeting abnormal bone density or osteoporosis differentiations.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>A total of 320 MR scans from 160 patients (52 men and 108 women; mean age 61.27 \u00b1 12.72 years) who underwent lumbar MRI and quantitative computed tomography (QCT) examinations were retrospectively enrolled in this study cohort. Radiomic features were extracted from the lumbar spine MR images. With QCT as the reference standard, six radiomic-based machine learning models including K-nearest neighbor (KNN), support vector machine (SVM), Linear Discriminant Analysis (LDA), logistic regression (LR), stochastic gradient descent (SGD), Gaussian NB were developed to predict abnormal bone density and osteoporosis using T1WI alone, T2WI alone, and the combined T1WI+T2WI. The dataset was randomly split into a training\/validation set and a testing set in a 7:3 ratio. The performance metrics of the models were calculated and evaluated.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>Among the six machine learning models evaluated, T1WI and T2WI each exhibited prominent advantages for predicting osteoporosis and abnormal bone mass, respectively. Take KNN as an example. T1WI achieved the highest AUC (0.821) for predicting osteoporosis on test set (mean of 10 repeated evaluations), significantly higher than T2WI (AUC\u00a0=\u00a00.782) and the combined T1WI+T2WI approach (AUC\u00a0=\u00a00.775). In contrast, T2WI demonstrated superior performance for the prediction of abnormal bone density, with an AUC of 0.942 (T1WI and T1WI+T2WI were 0.884 and 0.923, respectively).<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>Our investigation into predicting abnormal bone density and osteoporosis from lumbar spine MRI sequences shows that predictive efficacy is sequence-dependent. T1WI features proved more effective for osteoporosis identification, while T2WI features were better for abnormal bone density prediction, highlighting the importance of sequence selection based on target pathology.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fendo.2026.1823826","type":"journal-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T01:10:18Z","timestamp":1777425018000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Sequence-specific radiomics for diagnosis of spinal bone loss"],"prefix":"10.3389","volume":"17","author":[{"given":"Tingyu","family":"Xue","sequence":"first","affiliation":[{"name":"Department of Radiology and Nuclear Medicine, The First Hospital of Hebei Medical University","place":["Hebei, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yaguang","family":"Li","sequence":"additional","affiliation":[{"name":"Department of Radiology and Nuclear Medicine, The First Hospital of Hebei Medical University","place":["Hebei, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Huayi","family":"Zhao","sequence":"additional","affiliation":[{"name":"Department of Radiology and Nuclear Medicine, The First Hospital of Hebei Medical University","place":["Hebei, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tianzi","family":"Zhang","sequence":"additional","affiliation":[{"name":"Department of Radiology and Nuclear Medicine, The First Hospital of Hebei Medical University","place":["Hebei, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiayi","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Radiology and Nuclear Medicine, The First Hospital of Hebei Medical University","place":["Hebei, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"WenHao","family":"Jiang","sequence":"additional","affiliation":[{"name":"Department of Radiology and Nuclear Medicine, The First Hospital of Hebei Medical University","place":["Hebei, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Licun","family":"Lei","sequence":"additional","affiliation":[{"name":"Department of Radiology and Nuclear Medicine, The First Hospital of Hebei Medical University","place":["Hebei, China"]},{"name":"School of Medical Imaging, Hebei Medical University","place":["Hebei, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yong","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Radiology and Nuclear Medicine, The First Hospital of Hebei Medical University","place":["Hebei, China"]},{"name":"School of Medical Imaging, Hebei Medical University","place":["Hebei, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,4,29]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","DOI":"10.1007\/s00198-014-2655-z","article-title":"The clinical diagnosis of osteoporosis: A position statement from the National Bone Health Alliance Working Group","volume":"25","author":"Siris","year":"2014","journal-title":"Osteoporos Int"},{"key":"B2","doi-asserted-by":"publisher","DOI":"10.17179\/excli2020-2591","article-title":"Osteoporosis: Pathophysiology and therapeutic options","volume":"19","author":"F\u00f6ger-Samwald","year":"2020","journal-title":"EXCLI J"},{"key":"B3","doi-asserted-by":"publisher","DOI":"10.1007\/s00198-015-3093-2","article-title":"Projection of osteoporosis-related fractures and costs in China: 2010-2050","volume":"26","author":"Si","year":"2015","journal-title":"Osteoporos Int"},{"key":"B4","doi-asserted-by":"publisher","DOI":"10.1016\/j.jrras.2024.100958","article-title":"Diagnostic significance of multisequence MRI radiomics models in distinguishing benign and malignant spinal fractures","volume":"17","author":"Xu","year":"2024","journal-title":"J Radiat Res Appl Sci"},{"key":"B5","doi-asserted-by":"publisher","first-page":"235","DOI":"10.1186\/s12880-025-01743-9","article-title":"Radiomics and machine learning for osteoporosis detection using abdominal computed tomography: A retrospective multicenter study","volume":"25","author":"Liu","year":"2025","journal-title":"BMC Med Imaging"},{"key":"B6","doi-asserted-by":"publisher","DOI":"10.1016\/s0140-6736(02)08761-5","article-title":"Diagnosis of osteoporosis and assessment of fracture risk","volume":"359","author":"Kanis","year":"2002","journal-title":"Lancet"},{"key":"B7","doi-asserted-by":"publisher","DOI":"10.1053\/j.semnuclmed.2023.10.008","article-title":"State of the art imaging of osteoporosis","volume":"54","author":"Chen","year":"2024","journal-title":"Semin Nucl Med"},{"key":"B8","doi-asserted-by":"publisher","first-page":"195","DOI":"10.1016\/j.bone.2003.10.001","article-title":"Fracture incidence and association with bone mineral density in elderly men and women: The Rotterdam Study","volume":"34","author":"Schuit","year":"2004","journal-title":"Bone"},{"key":"B9","doi-asserted-by":"publisher","DOI":"10.1016\/j.jocd.2025.101561","article-title":"Evaluation of lumbar vertebral bone quality using T1-weighted mri: Can it differentiate normal, osteopenia, and osteoporosis","volume":"28","author":"Emir","year":"2025","journal-title":"J Clin Densitom"},{"key":"B10","doi-asserted-by":"publisher","DOI":"10.14740\/jocmr2970w","article-title":"Gender disparities in osteoporosis","volume":"9","author":"Alswat","year":"2017","journal-title":"J Clin Med Res"},{"key":"B11","doi-asserted-by":"publisher","DOI":"10.1007\/s11547-025-02029-4","article-title":"Emerging mri-based spine scoring techniques targeting bone quality to assess osteoporosis, vertebral fracture risk, other spinal degenerative diseases, and post-surgical outcomes","volume":"130","author":"Din","year":"2025","journal-title":"Radiol Med"},{"key":"B12","doi-asserted-by":"publisher","DOI":"10.1002\/jmri.27858","article-title":"Diagnostic role of magnetic resonance imaging in low back pain caused by vertebral endplate degeneration","volume":"55","author":"Din","year":"2022","journal-title":"J Magn Reson Imaging"},{"key":"B13","doi-asserted-by":"publisher","DOI":"10.1007\/s00198-021-06129-5","article-title":"Opportunistic use of lumbar magnetic resonance imaging for osteoporosis screening","volume":"33","author":"Kadri","year":"2022","journal-title":"Osteoporos Int"},{"key":"B14","doi-asserted-by":"publisher","DOI":"10.3389\/fendo.2016.00074","article-title":"Mr-based assessment of bone marrow fat in osteoporosis, diabetes, and obesity","volume":"7","author":"Cordes","year":"2016","journal-title":"Front Endocrinol"},{"key":"B15","first-page":"391","article-title":"Chapter 14 - Chemical shift encoding-based water-fat separation","volume-title":"Advances in magnetic resonance technology and applications","author":"Ruschke","year":"2022"},{"key":"B16","doi-asserted-by":"publisher","first-page":"99","DOI":"10.1038\/s41467-024-55422-4","article-title":"Deep learning and genome-wide association meta-analyses of bone marrow adiposity in the UK Biobank","volume":"16","author":"Xu","year":"2025","journal-title":"Nat Commun"},{"key":"B17","doi-asserted-by":"publisher","first-page":"101511","DOI":"10.1016\/j.beem.2021.101511","article-title":"Clinical imaging of marrow adiposity","volume":"35","author":"Jarraya","year":"2021","journal-title":"Best Pract Res Clin Endocrinol Metab"},{"key":"B18","doi-asserted-by":"publisher","first-page":"991","DOI":"10.1186\/s12891-024-08120-7","article-title":"Diagnostic accuracy of deep learning in prediction of osteoporosis: A systematic review and meta-analysis","volume":"25","author":"Amani","year":"2024","journal-title":"BMC Musculoskeletal Disord"},{"key":"B19","doi-asserted-by":"publisher","DOI":"10.1007\/s00198-025-07541-x","article-title":"Machine learning is changing osteoporosis detection: An integrative review","volume":"36","author":"Zhang","year":"2025","journal-title":"Osteoporos Int"},{"key":"B20","doi-asserted-by":"publisher","DOI":"10.3389\/fimmu.2025.1532248","article-title":"Interpretable machine learning and radiomics in hip MRI diagnostics: Comparing ONFH and OA predictions to experts","volume":"16","author":"Alkhatatbeh","year":"2025","journal-title":"Front Immunol"},{"key":"B21","doi-asserted-by":"publisher","DOI":"10.1016\/j.jot.2023.10.003","article-title":"Radiomics signature of osteoarthritis: Current status and perspective","volume":"45","author":"Jiang","year":"2024","journal-title":"J Orthop Transl"},{"key":"B22","doi-asserted-by":"publisher","DOI":"10.12015\/issn.1674-8034.2023.11.020","article-title":"Diagnosis of osteoporosis by radiomics on T2WI sequence of lumbar magnetic resonance imaging","volume":"14","author":"Kang","year":"2025","journal-title":"Chin J Magn Reson Imaging"},{"key":"B23","doi-asserted-by":"publisher","DOI":"10.21037\/qims-21-587","article-title":"Fully automated radiomic screening pipeline for osteoporosis and abnormal bone density with a deep learning-based segmentation using a short lumbar mdixon sequence","volume":"12","author":"Zhao","year":"2022","journal-title":"Quant Imaging Med Surg"},{"key":"B24","doi-asserted-by":"publisher","DOI":"10.1007\/s00586-024-08463-8","article-title":"Estimating lumbar bone mineral density from conventional mri and radiographs with deep learning in spine patients","volume":"33","author":"Galbusera","year":"2024","journal-title":"Eur Spine J"},{"key":"B25","doi-asserted-by":"publisher","first-page":"22052","DOI":"10.1038\/s41598-023-49540-0","article-title":"Radiomics model based on multi-sequence mri for preoperative prediction of Ki-67 expression levels in early endometrial cancer","volume":"13","author":"Ding","year":"2023","journal-title":"Sci Rep"},{"key":"B26","doi-asserted-by":"publisher","first-page":"137","DOI":"10.1186\/s12880-022-00865-8","article-title":"Multiparametric mr radiomics in brain glioma: Models comparation to predict biomarker status","volume":"22","author":"He","year":"2022","journal-title":"BMC Med Imaging"},{"key":"B27","doi-asserted-by":"publisher","first-page":"185","DOI":"10.1186\/s12891-024-07309-0","article-title":"Comparative evaluation of multiparametric lumbar mri radiomic models for detecting osteoporosis","volume":"25","author":"Zhen","year":"2024","journal-title":"BMC Musculoskelet Disord"},{"key":"B28","doi-asserted-by":"publisher","DOI":"10.1016\/j.aej.2022.10.069","article-title":"A novel multi-level feature selection method for radiomics","volume":"66","author":"Wang","year":"2023","journal-title":"Alex Eng J"},{"key":"B29","doi-asserted-by":"publisher","DOI":"10.3389\/fbioe.2024.1471692","article-title":"A single sequence MRI-based deep learning radiomics model in the diagnosis of early osteonecrosis of femoral head","volume":"12","author":"Alkhatatbeh","year":"2024","journal-title":"Front Bioeng Biotechnol"},{"key":"B30","doi-asserted-by":"publisher","DOI":"10.21037\/apm-21-612","article-title":"Application of bone turnover markers and DXA and QCT in an elderly Chinese male population","volume":"10","author":"Yuan","year":"2021","journal-title":"Ann Palliat Med"},{"key":"B31","doi-asserted-by":"publisher","DOI":"10.47723\/kcmj.v19i1.864","article-title":"Comparison between quantitative computed tomography and dual-energy X-ray absorptiometry in the detection of osteoporosis in postmenopausal women","volume":"19","author":"Hammood","year":"2023","journal-title":"Al-Kindy Coll Med J"},{"key":"B32","doi-asserted-by":"publisher","first-page":"103244","DOI":"10.1016\/j.eclinm.2025.103244","article-title":"Criteria for osteoporosis diagnosis: A systematic review and meta-analysis of osteoporosis diagnostic studies with DXA and QCT","volume":"83","author":"Yang","year":"2025","journal-title":"eClinicalMedicine"},{"key":"B33","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","year":"2024","journal-title":"Diagn Interv Radiol"},{"key":"B34","doi-asserted-by":"publisher","DOI":"10.1016\/s0020-1383(16)47003-8","article-title":"Bone mechanical properties and changes with osteoporosis","author":"Osterhoff","year":"2016","journal-title":"Injury"},{"key":"B35","doi-asserted-by":"publisher","DOI":"10.1007\/s11914-016-0319-y","article-title":"Cortical bone porosity: What is it, why is it important, and how can we detect it","volume":"14","author":"Cooper","year":"2016","journal-title":"Curr Osteoporos Rep"},{"key":"B36","doi-asserted-by":"publisher","DOI":"10.1002\/jbmr.2007","article-title":"Dysapoptosis of osteoblasts and osteocytes increases cancellous bone formation but exaggerates cortical porosity with age","volume":"29","author":"Jilka","year":"2013","journal-title":"J Bone Miner Res"},{"key":"B37","doi-asserted-by":"publisher","first-page":"2073","DOI":"10.3390\/cells9092073","article-title":"Osteoblast-osteoclast communication and bone homeostasis","volume":"9","author":"Kim","year":"2020","journal-title":"Cells"},{"key":"B38","doi-asserted-by":"publisher","DOI":"10.3389\/fendo.2015.00040","article-title":"Marrow fat and bone: Review of clinical findings","volume":"6","author":"Schwartz","year":"2015","journal-title":"Front Endocrinol"},{"key":"B39","doi-asserted-by":"publisher","DOI":"10.2214\/ajr.11.7420","article-title":"Mri of spinal bone marrow: Part 2, T1-weighted imaging-based differential diagnosis","volume":"197","author":"Hanrahan","year":"2011","journal-title":"AJR Am J Roentgenol"},{"key":"B40","doi-asserted-by":"publisher","DOI":"10.1002\/jmri.25647","article-title":"Mri assessment of bone structure and microarchitecture","volume":"46","author":"Chang","year":"2017","journal-title":"J Magn Reson Imaging"},{"key":"B41","doi-asserted-by":"publisher","DOI":"10.1158\/0008-5472.CAN-17-0339","article-title":"Computational radiomics system to decode the radiographic phenotype","volume":"77","author":"Griethuysen","year":"2017","journal-title":"Cancer Res"},{"key":"B42","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejrad.2011.04.052","article-title":"T2wi mri and mri-mdct correlations of the osteoporotic vertebral compressive fractures","volume":"81","author":"Kazawa","year":"2012","journal-title":"Eur J Radiol"},{"key":"B43","doi-asserted-by":"publisher","DOI":"10.1007\/s11914-012-0104-5","article-title":"Pathways for bone loss in inflammatory disease","volume":"10","author":"Braun","year":"2012","journal-title":"Curr Osteoporos Rep"},{"key":"B44","doi-asserted-by":"publisher","DOI":"10.1359\/jbmr.080233","article-title":"Compromised bone marrow perfusion in osteoporosis","volume":"23","author":"Griffith","year":"2008","journal-title":"J Bone Miner Res"},{"key":"B45","doi-asserted-by":"publisher","first-page":"100","DOI":"10.1186\/s12891-022-06096-w","article-title":"Prediction of osteoporosis using radiomics analysis derived from single source dual energy ct","volume":"24","author":"Wang","year":"2023","journal-title":"BMC Musculoskelet Disord"},{"key":"B46","doi-asserted-by":"publisher","DOI":"10.1016\/j.acra.2024.04.022","article-title":"Predicting osteoporosis and osteopenia by fusing deep transfer learning features and classical radiomics features based on single-source dual-energy ct imaging","volume":"31","author":"Wang","year":"2024","journal-title":"Acad Radiol"},{"key":"B47","doi-asserted-by":"publisher","DOI":"10.1007\/s00198-022-06491-y","article-title":"Opportunistic osteoporosis screening using chest ct with artificial intelligence","volume":"33","author":"Yang","year":"2022","journal-title":"Osteoporos Int"},{"key":"B48","doi-asserted-by":"publisher","DOI":"10.1007\/s00198-024-07378-w","article-title":"A novel hybrid deep learning framework based on biplanar x-ray radiography images for bone density prediction and classification","volume":"36","author":"Zhou","year":"2025","journal-title":"Osteoporos Int"},{"key":"B49","doi-asserted-by":"publisher","first-page":"893","DOI":"10.1007\/s00198-024-07338-4","article-title":"Conventional chest computed tomography-based radiomics for predicting the risk of thoracolumbar osteoporotic vertebral fractures","volume":"36","author":"Pan","year":"2025","journal-title":"Osteoporos Int"},{"key":"B50","doi-asserted-by":"publisher","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","year":"2024","journal-title":"Osteoporos Int"},{"key":"B51","doi-asserted-by":"publisher","DOI":"10.1007\/s10278-025-01547-x","article-title":"Deep learning for osteoporosis diagnosis using magnetic resonance images of lumbar vertebrae","volume":"39","author":"Mousavinasab","year":"2025","journal-title":"J Imaging Inform Med"},{"key":"B52","doi-asserted-by":"publisher","DOI":"10.5812\/iranjradiol-147913","article-title":"The use of radiomics data obtained from ADC map of lumbar MRI and machine learning in diagnosis of osteoporosis","volume":"21","author":"Erdem","year":"2024","journal-title":"I J Radiol"},{"key":"B53","doi-asserted-by":"publisher","first-page":"52","DOI":"10.4274\/tod.galenos.2024.03708","article-title":"Opportunistic prediction of osteoporosis with machine learning models based on clivus-radiomic features obtained from CT images","volume":"31","author":"G\u00fcng\u00f6r","year":"2025","journal-title":"Turk J Osteoporos"},{"key":"B54","doi-asserted-by":"publisher","DOI":"10.1109\/tkde.2008.239","article-title":"Learning from imbalanced data","volume":"21","author":"Haibo","year":"2009","journal-title":"IEEE"},{"key":"B55","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2006.01.009","article-title":"The effect of imbalanced data sets on lda: a theoretical and empirical analysis","volume":"40","author":"Xie","year":"2007","journal-title":"Pattern Recogn"},{"key":"B56","doi-asserted-by":"publisher","first-page":"1705.00607","DOI":"10.48550\/arXiv.1705.00607","article-title":"Stochastic learning on imbalanced data: determinantal point processes for mini-batch diversification","author":"Cheng","year":"2017","journal-title":"arXiv"},{"key":"B57","doi-asserted-by":"publisher","first-page":"e384","DOI":"10.1002\/sta4.384","article-title":"The effect of rebalancing on lda in imbalanced classification","volume":"10","author":"Kim","year":"2021","journal-title":"Stat"},{"key":"B58","doi-asserted-by":"publisher","DOI":"10.1016\/j.dss.2012.05.028","article-title":"On developing robust models for favorability analysis: model choice, feature sets and imbalanced data","volume":"53","author":"Lane","year":"2012","journal-title":"DSS"}],"container-title":["Frontiers in Endocrinology"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fendo.2026.1823826\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T01:10:21Z","timestamp":1777425021000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fendo.2026.1823826\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,29]]},"references-count":58,"alternative-id":["10.3389\/fendo.2026.1823826"],"URL":"https:\/\/doi.org\/10.3389\/fendo.2026.1823826","relation":{},"ISSN":["1664-2392"],"issn-type":[{"value":"1664-2392","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,4,29]]},"article-number":"1823826"}}