{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,8]],"date-time":"2026-09-08T18:07:37Z","timestamp":1788890857700,"version":"build-2803163510"},"reference-count":45,"publisher":"Oxford University Press (OUP)","issue":"10","license":[{"start":{"date-parts":[[2026,8,4]],"date-time":"2026-08-04T00:00:00Z","timestamp":1785801600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"publisher","award":["P30 AR072581"],"award-info":[{"award-number":["P30 AR072581"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"publisher","award":["NIH\/NHLBI R01 HL166747"],"award-info":[{"award-number":["NIH\/NHLBI R01 HL166747"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"publisher","award":["NCATS UM1TR004402"],"award-info":[{"award-number":["NCATS UM1TR004402"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"publisher","award":["NIH 5R01HL166747 (ROCK-D)"],"award-info":[{"award-number":["NIH 5R01HL166747 (ROCK-D)"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,8,30]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Chronic kidney disease (CKD) is associated with alterations in cortical bone structure and composition that contribute to increased fracture risk but are incompletely captured by standard clinical imaging, including DXA. This study evaluated whether radiomics combined with machine learning can enhance detection of CKD-related cortical bone characteristics using high-resolution peripheral quantitative computed tomography (HR-pQCT). HR-pQCT images (60.7\u00a0\u03bcm isotropic resolution; 168-slice stacks acquired at 7.3% and 30% proximal to the tibial endplate) were analyzed from 72 participants (38 non-CKD controls and 34 individuals with advanced CKD), yielding 24\u2009192 cortical bone image slices. Cortical bone was segmented using a pretrained neural network optimized through transfer learning. Radiomic features were extracted using gray-level co-occurrence matrix (GLCM), local binary pattern (LBP), and combined GLCM+LBP feature sets, and paired with 7 machine-learning classifiers to systematically evaluate 21 feature\u2013classifier combinations at distal and diaphyseal tibial sites. To address optimism associated with correlated slice-level data, radiomic features were aggregated per patient prior to model training and evaluated using patient-level splits (~7 test patients); this patient-level analysis constitutes the primary evaluation framework of this study. Under patient-level evaluation, classification performance was more variable across feature\u2013classifier combinations and tibial sites, with wide CIs reflecting the limited sample size. At the slice level, hybrid GLCM+LBP features combined with XGBoost demonstrated the strongest classification performance across both tibial regions (distal AUC\u2009=\u20090.999; diaphyseal AUC\u2009=\u20090.999), providing methodological context for the systematic evaluation of all 21 feature\u2013classifier combinations. Radiomics-derived texture features identified cortical heterogeneity that was not consistently reflected by conventional HR-pQCT metrics. These findings support radiomics as a promising methodological framework for characterizing CKD-associated cortical bone alterations while highlighting the importance of larger patient-level validation studies.<\/jats:p>","DOI":"10.1093\/jbmrpl\/ziag123","type":"journal-article","created":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T12:06:35Z","timestamp":1785585995000},"source":"Crossref","is-referenced-by-count":1,"title":["Radiomics and machine learning for characterizing CKD-associated cortical bone texture patterns in HR-pQCT tibia scans: a slice- and patient-level methodological framework"],"prefix":"10.1093","volume":"10","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2778-6085","authenticated-orcid":false,"given":"Youngjun","family":"Lee","sequence":"first","affiliation":[{"name":"Weldon School of Biomedical Engineering, Purdue University , West Lafayette, IN 47907 ,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8540-8854","authenticated-orcid":false,"given":"Andy Kin On","family":"Wong","sequence":"additional","affiliation":[{"name":"University Health Network, Toronto General Hospital , Toronto, ON M5G 2C4 ,","place":["Canada"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-6540-0389","authenticated-orcid":false,"given":"Seokkyoon","family":"Hong","sequence":"additional","affiliation":[{"name":"School of Polymer Science and Engineering, Chonnam National University , Gwangju, 61186 ,","place":["Republic of Korea"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-9270-9618","authenticated-orcid":false,"given":"Drake","family":"Dillman","sequence":"additional","affiliation":[{"name":"Division of Nephrology and Hypertension, Indiana University School of Medicine , Indianapolis, IN 46202 ,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7178-2183","authenticated-orcid":false,"given":"Kenneth","family":"Lim","sequence":"additional","affiliation":[{"name":"Division of Nephrology and Hypertension, Indiana University School of Medicine , Indianapolis, IN 46202 ,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3562-9725","authenticated-orcid":false,"given":"Sharon M","family":"Moe","sequence":"additional","affiliation":[{"name":"Division of Nephrology and Hypertension, Indiana University School of Medicine , Indianapolis, IN 46202 ,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6415-4936","authenticated-orcid":false,"given":"Stuart J","family":"Warden","sequence":"additional","affiliation":[{"name":"Department of Physical Therapy, School of Health and Human Sciences, Indiana University Indianapolis , Indianapolis, IN ,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5284-9239","authenticated-orcid":false,"given":"Ali","family":"Ghasem-Zadeh","sequence":"additional","affiliation":[{"name":"Departments of Endocrinology and Medicine, Austin Health, The University of Melbourne , Melbourne, VIC 3084 ,","place":["Australia"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7614-4412","authenticated-orcid":false,"given":"Rachel K","family":"Surowiec","sequence":"additional","affiliation":[{"name":"Weldon School of Biomedical Engineering, Purdue University , West Lafayette, IN 47907 ,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2026,8,4]]},"reference":[{"issue":"6","key":"2026090813221170200_ref1","doi-asserted-by":"publisher","first-page":"721","DOI":"10.1038\/ki.2008.264","article-title":"Chronic kidney disease and bone fracture: a growing concern","volume":"74","author":"Nickolas","year":"2008","journal-title":"Kidney Int"},{"key":"2026090813221170200_ref2","doi-asserted-by":"publisher","first-page":"117089","DOI":"10.1016\/j.bone.2024.117089","article-title":"Combining raloxifene and mechanical loading improves bone composition and mechanical properties in a murine model of chronic kidney disease (CKD)","volume":"183","author":"Surowiec","year":"2024","journal-title":"Bone."},{"issue":"5","key":"2026090813221170200_ref3","doi-asserted-by":"publisher","first-page":"413","DOI":"10.7326\/0003-4819-125-5-199609010-00009","article-title":"Hormonal influences on bone remodeling and bone loss: application to the management of primary hyperparathyroidism","volume":"125","author":"Parfitt","year":"1996","journal-title":"Ann Intern Med"},{"issue":"8","key":"2026090813221170200_ref4","doi-asserted-by":"publisher","first-page":"1371","DOI":"10.1681\/ASN.2009121208","article-title":"Bone mass and microarchitecture in CKD patients with fracture","volume":"21","author":"Nickolas","year":"2010","journal-title":"J Am Soc Nephrol"},{"issue":"6","key":"2026090813221170200_ref5","doi-asserted-by":"publisher","first-page":"e99262","DOI":"10.1371\/journal.pone.0099262","article-title":"Cortical bone mechanical properties are altered in an animal model of progressive chronic kidney disease","volume":"9","author":"Newman","year":"2014","journal-title":"PLoS One"},{"issue":"1","key":"2026090813221170200_ref6","first-page":"1","article-title":"KDIGO 2017 Clinical Practice Guideline Update for the Diagnosis, Evaluation, Prevention, and Treatment of Chronic Kidney Disease-Mineral and Bone Disorder (CKD-MBD) foreword","volume":"7","author":"Wheeler","year":"2017","journal-title":"Kidney Int Suppl"},{"issue":"4","key":"2026090813221170200_ref7","doi-asserted-by":"publisher","first-page":"861","DOI":"10.1136\/jim-2015-000043","article-title":"Bone mineral density and biochemical markers of bone metabolism in predialysis patients with chronic kidney disease","volume":"64","author":"Fidan","year":"2016","journal-title":"J Investig Med"},{"issue":"11","key":"2026090813221170200_ref8","doi-asserted-by":"publisher","first-page":"2325","DOI":"10.1093\/ndt\/gfg403","article-title":"Bone mineral density, biochemical markers and skeletal fractures in haemodialysis patients","volume":"18","author":"Urena","year":"2003","journal-title":"Nephrol Dial Transplant"},{"issue":"2","key":"2026090813221170200_ref9","first-page":"57","article-title":"Fractures and vertebral bone mineral density in patients with renal osteodystrophy","volume":"30","author":"Piraino","year":"1988","journal-title":"Clin Nephrol"},{"issue":"1","key":"2026090813221170200_ref10","doi-asserted-by":"crossref","first-page":"3107","DOI":"10.1038\/s41598-022-07178-4","article-title":"Characteristics of fracture in patients who firstly starts kidney replacement therapy in Korea: a retrospective population-based study","volume":"12","author":"Kim","year":"2022","journal-title":"Sci Rep"},{"issue":"9","key":"2026090813221170200_ref11","doi-asserted-by":"publisher","first-page":"1461","DOI":"10.1681\/ASN.2012090916","article-title":"Temporal trends in fracture rates and postdischarge outcomes among hemodialysis patients","volume":"24","author":"Beaubrun","year":"2013","journal-title":"J Am Soc Nephrol"},{"key":"2026090813221170200_ref12","doi-asserted-by":"publisher","first-page":"101633","DOI":"10.1016\/j.bonr.2022.101633","article-title":"Tracking changes of individual cortical pores over 1 year via HR-pQCT in a small cohort of 60-year-old females","volume":"17","author":"Surowiec","year":"2022","journal-title":"Bone Rep"},{"issue":"10","key":"2026090813221170200_ref13","doi-asserted-by":"publisher","first-page":"2955","DOI":"10.1007\/s00198-016-3621-8","article-title":"In vivo assessment of bone structure and estimated bone strength by first-and second-generation HR-pQCT","volume":"27","author":"Agarwal","year":"2016","journal-title":"Osteoporos Int"},{"issue":"9","key":"2026090813221170200_ref14","doi-asserted-by":"publisher","first-page":"1607","DOI":"10.1007\/s00198-020-05438-5","article-title":"Guidelines for the assessment of bone density and microarchitecture in vivo using high-resolution peripheral quantitative computed tomography","volume":"31","author":"Whittier","year":"2020","journal-title":"Osteoporos Int"},{"issue":"1","key":"2026090813221170200_ref15","doi-asserted-by":"publisher","first-page":"381","DOI":"10.1080\/0886022X.2022.2043375","article-title":"Comparison of bone microstructures via high-resolution peripheral quantitative computed tomography in patients with different stages of chronic kidney disease before and after starting hemodialysis","volume":"44","author":"Tsuji","year":"2022","journal-title":"Ren Fail"},{"issue":"4","key":"2026090813221170200_ref16","doi-asserted-by":"publisher","first-page":"539","DOI":"10.1007\/s00223-020-00779-z","article-title":"Bone fragility fractures in CKD patients","volume":"108","author":"Pimentel","year":"2021","journal-title":"Calcif Tissue Int"},{"issue":"1150","key":"2026090813221170200_ref17","doi-asserted-by":"crossref","first-page":"20221016","DOI":"10.1259\/bjr.20221016","article-title":"High-resolution peripheral quantitative computed tomography: research or clinical practice?","volume":"96","author":"Gazzotti","year":"2023","journal-title":"Br J Radiol"},{"key":"2026090813221170200_ref18","doi-asserted-by":"publisher","first-page":"116260","DOI":"10.1016\/j.bone.2021.116260","article-title":"Bone microarchitecture and estimated failure load are deteriorated whether patients with chronic kidney disease have normal bone mineral density, osteopenia or osteoporosis","volume":"154","author":"Ghasem-Zadeh","year":"2022","journal-title":"Bone."},{"issue":"8","key":"2026090813221170200_ref19","doi-asserted-by":"publisher","first-page":"1811","DOI":"10.1002\/jbmr.1916","article-title":"Rapid cortical bone loss in patients with chronic kidney disease","volume":"28","author":"Nickolas","year":"2013","journal-title":"J Bone Miner Res"},{"key":"2026090813221170200_ref20","doi-asserted-by":"publisher","first-page":"101821","DOI":"10.1016\/j.bonr.2024.101821","article-title":"Integrating deep learning and machine learning for improved CKD-related cortical bone assessment in HRpQCT images: a pilot study","volume":"24","author":"Lee","year":"2025","journal-title":"Bone Rep"},{"issue":"1","key":"2026090813221170200_ref21","doi-asserted-by":"crossref","first-page":"36","DOI":"10.1038\/s41413-026-00515-7","article-title":"Radiomics identifies distinct cortical bone texture alterations in patients with CKD using HR-pQCT: Radiomics identifies CKD-Related bone texture","volume":"14","author":"Lee","year":"2026","journal-title":"Bone Research"},{"issue":"2","key":"2026090813221170200_ref22","doi-asserted-by":"crossref","first-page":"563","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."},{"issue":"8","key":"2026090813221170200_ref23","doi-asserted-by":"crossref","first-page":"1079","DOI":"10.2215\/CJN.0000000749","article-title":"Abnormal cardiovascular functional responses after the long interdialytic interval: a quasi-experimental crossover study","volume":"20","author":"Arroyo","year":"2025","journal-title":"Clin J Am Soc Nephrol"},{"issue":"1","key":"2026090813221170200_ref24","doi-asserted-by":"crossref","first-page":"111","DOI":"10.1016\/j.bone.2011.10.003","article-title":"Visual grading of motion induced image degradation in high resolution peripheral computed tomography: impact of image quality on measures of bone density and micro-architecture","volume":"50","author":"Pialat","year":"2012","journal-title":"Bone."},{"issue":"4","key":"2026090813221170200_ref25","doi-asserted-by":"publisher","first-page":"791","DOI":"10.1007\/s00198-021-06164-2","article-title":"Reference data and calculators for second-generation HR-pQCT measures of the radius and tibia at anatomically standardized regions in White adults","volume":"33","author":"Warden","year":"2022","journal-title":"Osteoporos Int"},{"issue":"85","key":"2026090813221170200_ref26","first-page":"2825","article-title":"Scikit-learn: machine learning in python","volume":"12","author":"Pedregosa","year":"2011","journal-title":"J Mach Learn Res"},{"key":"2026090813221170200_ref27","volume-title":"pandas-dev\/pandas: Pandas 1.0. 5. Zenodo","author":"Reback","year":"2020"},{"issue":"5","key":"2026090813221170200_ref28","first-page":"1","article-title":"Image texture feature extraction using GLCM approach","volume":"3","author":"Mohanaiah","year":"2013","journal-title":"Int J Sci Res Publ"},{"issue":"7","key":"2026090813221170200_ref29","doi-asserted-by":"publisher","first-page":"971","DOI":"10.1109\/TPAMI.2002.1017623","article-title":"Multiresolution gray-scale and rotation invariant texture classification with local binary patterns","volume":"24","author":"Ojala","year":"2002","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"2026090813221170200_ref30","doi-asserted-by":"crossref","first-page":"116653","DOI":"10.1016\/j.bone.2022.116653","article-title":"Machine learning applied to HR-pQCT images improves fracture discrimination provided by DXA and clinical risk factors","volume":"168","author":"Lu","year":"2023","journal-title":"Bone."},{"issue":"4","key":"2026090813221170200_ref31","doi-asserted-by":"publisher","first-page":"1311","DOI":"10.1007\/s00521-020-05017-z","article-title":"A novel content-based image retrieval approach for classification using GLCM features and texture fused LBP variants","volume":"33","author":"Garg","year":"2021","journal-title":"Neural Comput Appl"},{"key":"2026090813221170200_ref32","doi-asserted-by":"crossref","first-page":"473","DOI":"10.17946\/JRST.2021.44.5.473","article-title":"Comparison of based on histogram equalization techniques by using normalization in thoracic computed tomography","author":"Lee","year":"2021","journal-title":"Radiological Science and Technology"},{"key":"2026090813221170200_ref33","first-page":"1","volume-title":"Xgboost: extreme gradient boosting. R package version 04-2","author":"Chen","year":"2015"},{"key":"2026090813221170200_ref34","doi-asserted-by":"crossref","first-page":"859","DOI":"10.1109\/BIBE50027.2020.00146","volume-title":"2020 IEEE 20th International Conference on Bioinformatics and Bioengineering (BIBE)","author":"Athanasiou","year":"2020"},{"issue":"1","key":"2026090813221170200_ref35","doi-asserted-by":"crossref","first-page":"836","DOI":"10.1186\/s12967-023-04720-4","article-title":"Classification of tumor types using XGBoost machine learning model: a vector space transformation of genomic alterations","volume":"21","author":"Zelli","year":"2023","journal-title":"J Transl Med"},{"issue":"7","key":"2026090813221170200_ref36","doi-asserted-by":"publisher","first-page":"072098","DOI":"10.1088\/1757-899X\/928\/7\/072098","article-title":"Texture analysis of breast cancer via LBP, HOG, and GLCM techniques","volume":"928","author":"Farhan","year":"2020","journal-title":"IOP Conf Ser: Mater Sci Eng"},{"issue":"12","key":"2026090813221170200_ref37","doi-asserted-by":"publisher","first-page":"2537","DOI":"10.1002\/jbmr.2309","article-title":"Structural and mechanical repair of diffuse damage in cortical bone in vivo","volume":"29","author":"Seref-Ferlengez","year":"2014","journal-title":"J Bone Miner Res"},{"issue":"7553","key":"2026090813221170200_ref38","doi-asserted-by":"crossref","first-page":"436","DOI":"10.1038\/nature14539","article-title":"Deep learning","volume":"521","author":"LeCun","year":"2015","journal-title":"Nature"},{"issue":"12","key":"2026090813221170200_ref39","doi-asserted-by":"publisher","first-page":"6858","DOI":"10.1007\/s00330-020-07011-4","article-title":"Machine learning\u2013based CT texture analysis to predict HPV status in oropharyngeal squamous cell carcinoma: comparison of 2D and 3D segmentation","volume":"30","author":"Ren","year":"2020","journal-title":"Eur Radiol"},{"issue":"3","key":"2026090813221170200_ref40","doi-asserted-by":"publisher","first-page":"1146","DOI":"10.1007\/s00330-024-11331-0","article-title":"Overlooked and underpowered: a meta-research addressing sample size in radiomics prediction models for binary outcomes","volume":"35","author":"Zhong","year":"2025","journal-title":"Eur Radiol"},{"issue":"1","key":"2026090813221170200_ref41","doi-asserted-by":"publisher","first-page":"84","DOI":"10.1504\/IJGUC.2024.136708","article-title":"Performance comparison of various machine learning classifiers using fusion of LBP, intensity and GLCM feature extraction techniques for thyroid nodules classification","volume":"15","author":"Srivastava","year":"2024","journal-title":"Int J Grid Util Comput"},{"issue":"30","key":"2026090813221170200_ref42","doi-asserted-by":"crossref","first-page":"1248452","DOI":"10.3389\/fonc.2023.1248452","article-title":"Brain tumor classification: a novel approach integrating GLCM, LBP and composite features","volume":"13","author":"Dheepak","year":"2024","journal-title":"Front Oncol"},{"issue":"17","key":"2026090813221170200_ref43","doi-asserted-by":"crossref","first-page":"2787","DOI":"10.3390\/math13172787","article-title":"Hierarchical deep feature fusion and ensemble learning for enhanced brain tumor MRI classification","volume":"13","author":"Ullah","year":"2025","journal-title":"Mathematics."},{"key":"2026090813221170200_ref44","doi-asserted-by":"crossref","first-page":"1674343","DOI":"10.3389\/fmedt.2025.1674343","article-title":"More than just a heatmap: elevating XAI with rigorous evaluation metrics","volume":"7","author":"Muhammad","year":"2025","journal-title":"Front Med Technol"},{"issue":"3","key":"2026090813221170200_ref45","doi-asserted-by":"publisher","first-page":"1374","DOI":"10.1007\/s10278-024-01277-6","article-title":"Deep learning classification of ischemic stroke territory on diffusion-weighted MRI: added value of augmenting the input with image transformations","volume":"38","author":"Koska","year":"2025","journal-title":"J Imaging Inform Med"}],"container-title":["JBMR Plus"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/jbmrplus\/advance-article-pdf\/doi\/10.1093\/jbmrpl\/ziag123\/70480946\/ziag123.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/jbmrplus\/article-pdf\/10\/10\/ziag123\/70480946\/ziag123.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/jbmrplus\/article-pdf\/10\/10\/ziag123\/70480946\/ziag123.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,8]],"date-time":"2026-09-08T17:22:35Z","timestamp":1788888155000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/jbmrplus\/article\/doi\/10.1093\/jbmrpl\/ziag123\/8751162"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,4]]},"references-count":45,"journal-issue":{"issue":"10","published-print":{"date-parts":[[2026,8,30]]}},"URL":"https:\/\/doi.org\/10.1093\/jbmrpl\/ziag123","relation":{},"ISSN":["2473-4039"],"issn-type":[{"value":"2473-4039","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2026,10]]},"published":{"date-parts":[[2026,8,4]]},"article-number":"ziag123"}}