{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,20]],"date-time":"2026-07-20T09:06:25Z","timestamp":1784538385832,"version":"3.55.0"},"reference-count":36,"publisher":"Oxford University Press (OUP)","issue":"8","license":[{"start":{"date-parts":[[2026,6,19]],"date-time":"2026-06-19T00:00:00Z","timestamp":1781827200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"funder":[{"DOI":"10.13039\/100010875","name":"Amgen Canada","doi-asserted-by":"publisher","award":["2347804"],"award-info":[{"award-number":["2347804"]}],"id":[{"id":"10.13039\/100010875","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100000024","name":"Canadian Institutes of Health Research","doi-asserted-by":"publisher","award":["PJT 180543"],"award-info":[{"award-number":["PJT 180543"]}],"id":[{"id":"10.13039\/501100000024","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,7,3]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Osteoporosis is a skeletal disease that significantly increases fracture risk and imposes a growing public health and economic burden. Notably, hip fractures are associated with high mortality, long-term disability, and loss of independence. When evaluating osteoporosis and estimating fracture risk, DXA is commonly used to determine the BMD. To capture geometrical morphology from these DXA scans as factors in fracture risk prediction, landmarking around the femur is conducted manually around the ROI. However, this process is labor-intensive and prone to variability. This study presents the development of a fully automated femoral landmarking tool that integrates a U-Net convolutional neural network for femur contour segmentation with a geometric algorithm for consistent landmark placement. A heterogeneous dataset of 555 DXA scans was used to train and evaluate the U-Net model, achieving a pixel-wise accuracy of 97.55%, an Intersection over Union of 91.55%, and a Dice coefficient of 95.56% on the test set. When incorporated into a statistical shape and appearance modeling (SSAM) framework for fracture risk prediction, predictions using the automatically generated landmarks achieved a test AUC of 0.831 (95% CI: 0.698-0.965), compared with 0.780 (95% CI: 0.635-0.925) for manual landmarks; a paired DeLong test showed no significant difference (p\u2009=\u2009.53), indicating a comparable performance. The proposed pipeline produces anatomically relevant, reproducible landmarks, and supports fracture prediction performance similar to manual methods. It presents a scalable and objective solution for morphometric analysis in DXA imaging.<\/jats:p>","DOI":"10.1093\/jbmrpl\/ziag103","type":"journal-article","created":{"date-parts":[[2026,6,18]],"date-time":"2026-06-18T11:46:29Z","timestamp":1781783189000},"source":"Crossref","is-referenced-by-count":0,"title":["Development of an automated landmarking tool for the femur in dual-energy X-ray absorptiometry scans using contour-based image analysis"],"prefix":"10.1093","volume":"10","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-2360-1090","authenticated-orcid":false,"given":"Edward M","family":"Chu","sequence":"first","affiliation":[{"name":"School of Biomedical Engineering, McMaster University , Hamilton, L8S 4L8, ON ,","place":["Canada"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9142-2767","authenticated-orcid":false,"given":"Jonathan D","family":"Adachi","sequence":"additional","affiliation":[{"name":"Department of Medicine, McMaster University , Hamilton, L8S 4L8, ON ,","place":["Canada"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1636-2631","authenticated-orcid":false,"given":"Cheryl E","family":"Quenneville","sequence":"additional","affiliation":[{"name":"School of Biomedical Engineering, McMaster University , Hamilton, L8S 4L8, ON ,","place":["Canada"]},{"name":"Department of Mechanical Engineering, McMaster University , Hamilton, L8S 4L8, ON ,","place":["Canada"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2026,6,19]]},"reference":[{"key":"2026072004370026800_ref1","volume-title":"StatPearls","author":"Krugh","year":"2025"},{"issue":"3","key":"2026072004370026800_ref2","doi-asserted-by":"publisher","first-page":"480","DOI":"10.1002\/jbmr.4212","article-title":"Increased mortality in hip fracture patients living alone: a NOREPOS study","volume":"36","author":"Dahl","year":"2021","journal-title":"J Bone Miner Res"},{"issue":"1","key":"2026072004370026800_ref3","doi-asserted-by":"publisher","first-page":"158","DOI":"10.1186\/s12877-016-0332-0","article-title":"A critical review of the long-term disability outcomes following hip fracture","volume":"16","author":"Dyer","year":"2016","journal-title":"BMC Geriatr"},{"issue":"6","key":"2026072004370026800_ref4","doi-asserted-by":"publisher","first-page":"681","DOI":"10.1109\/34.927467","article-title":"Active appearance models","volume":"23","author":"Cootes","year":"2001","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"issue":"4","key":"2026072004370026800_ref5","doi-asserted-by":"publisher","first-page":"396","DOI":"10.1093\/jbmr\/zjaf171","article-title":"DXA-derived hip shape is associated with hip fracture: a longitudinal study of 38 123 UK Biobank participants","volume":"41","author":"Scott","year":"2025","journal-title":"J Bone Miner Res"},{"issue":"4","key":"2026072004370026800_ref6","doi-asserted-by":"publisher","first-page":"543","DOI":"10.1016\/j.media.2009.05.004","article-title":"Statistical shape models for 3D medical image segmentation: a review","volume":"13","author":"Heimann","year":"2009","journal-title":"Med Image Anal"},{"issue":"1","key":"2026072004370026800_ref7","doi-asserted-by":"publisher","first-page":"14","DOI":"10.1016\/j.medengphy.2020.01.015","article-title":"Enhancing hip fracture risk prediction by statistical modeling and texture analysis on DXA images","volume":"78","author":"Jazinizadeh","year":"2020","journal-title":"Med Eng Phys"},{"key":"2026072004370026800_ref8","doi-asserted-by":"publisher","first-page":"129","DOI":"10.1016\/j.bone.2013.12.006","article-title":"Statistical shape and appearance models of bones","volume":"60","author":"Sarkalkan","year":"2014","journal-title":"Bone"},{"issue":"6","key":"2026072004370026800_ref9","doi-asserted-by":"publisher","first-page":"917","DOI":"10.1111\/joa.12973","article-title":"The effect of automated landmark identification on morphometric analyses","volume":"234","author":"Percival","year":"2019","journal-title":"J Anat"},{"issue":"1","key":"2026072004370026800_ref10","doi-asserted-by":"publisher","first-page":"33","DOI":"10.1186\/s12983-015-0127-8","article-title":"Performance of single and multi-atlas based automated landmarking methods compared to expert annotations in volumetric microCT datasets of mouse mandibles","volume":"12","author":"Young","year":"2015","journal-title":"Front Zool"},{"issue":"5","key":"2026072004370026800_ref11","doi-asserted-by":"publisher","first-page":"3501","DOI":"10.21037\/qims-23-1600","article-title":"Application of convolutional neural networks in medical images: a bibliometric analysis","volume":"14","author":"Jia","year":"2024","journal-title":"Quant Imaging Med Surg"},{"key":"2026072004370026800_ref12","doi-asserted-by":"publisher","first-page":"234","DOI":"10.1007\/978-3-319-24574-4_28","volume-title":"Medical Image Computing and Computer-Assisted Intervention \u2013 MICCAI","author":"Ronneberger","year":"2015"},{"key":"2026072004370026800_ref13","doi-asserted-by":"publisher","first-page":"82031","DOI":"10.1109\/ACCESS.2021.3086020","article-title":"U-Net and its variants for medical image segmentation: theory and applications","volume":"9","author":"Siddique","year":"2021","journal-title":"IEEE Access"},{"key":"2026072004370026800_ref14","doi-asserted-by":"publisher","first-page":"100098","DOI":"10.1016\/j.health.2022.100098","article-title":"Using U-Net network for efficient brain tumor segmentation in MRI images","volume":"2","author":"Walsh","year":"2022","journal-title":"Healthc Anal"},{"issue":"8","key":"2026072004370026800_ref15","doi-asserted-by":"publisher","first-page":"3029","DOI":"10.1109\/JBHI.2021.3066208","article-title":"Boundary aware U-Net for retinal layers segmentation in optical coherence tomography images","volume":"25","author":"Wang","year":"2021","journal-title":"IEEE J Biomed Health Inform"},{"issue":"1","key":"2026072004370026800_ref16","doi-asserted-by":"publisher","first-page":"401","DOI":"10.1016\/j.bone.2011.11.009","article-title":"Physical activity, body mass index and bone mineral density-associations in a prospective population-based cohort of women and men: the Canadian Multicentre Osteoporosis Study (CaMos)","volume":"50","author":"Langsetmo","year":"2012","journal-title":"Bone"},{"issue":"1","key":"2026072004370026800_ref17","doi-asserted-by":"publisher","first-page":"58","DOI":"10.1007\/s12325-021-01936-y","article-title":"Denosumab in the treatment of osteoporosis: 10 years later: a narrative review","volume":"39","author":"Kendler","year":"2022","journal-title":"Adv Ther"},{"issue":"1","key":"2026072004370026800_ref18","doi-asserted-by":"publisher","first-page":"90","DOI":"10.1177\/09544119231214651","article-title":"The effect of femur positioning on dual-energy X-ray absorptiometry (DXA) measures and statistical shape and appearance modeling (SSAM) fracture risk assessments","volume":"238","author":"Ammar","year":"2024","journal-title":"Proc Inst Mech Eng H"},{"issue":"2","key":"2026072004370026800_ref19","doi-asserted-by":"publisher","first-page":"125","DOI":"10.3390\/info11020125","article-title":"Albumentations: fast and flexible image augmentations","volume":"11","author":"Buslaev","year":"2020","journal-title":"Information"},{"key":"2026072004370026800_ref20","volume-title":"Advances in Neural Information Processing Systems","author":"Paszke","year":"2019"},{"key":"2026072004370026800_ref21","volume-title":"Open Source Computer Vision Library","author":"Itseez","year":"2015"},{"issue":"2","key":"2026072004370026800_ref22","doi-asserted-by":"publisher","first-page":"40","DOI":"10.1145\/1365490.1365500","article-title":"Scalable parallel programming with CUDA","volume":"6","author":"Nickolls","year":"2008","journal-title":"Queue"},{"issue":"4","key":"2026072004370026800_ref23","doi-asserted-by":"publisher","first-page":"1222","DOI":"10.1007\/s10439-020-02670-2","article-title":"3D analysis of the proximal femur compared to 2D analysis for hip fracture risk prediction in a clinical population","volume":"49","author":"Jazinizadeh","year":"2021","journal-title":"Ann Biomed Eng"},{"issue":"10","key":"2026072004370026800_ref24","doi-asserted-by":"publisher","first-page":"1925","DOI":"10.1007\/s00198-020-05444-7","article-title":"Advanced 2D image processing technique to predict hip fracture risk in an older population based on single DXA scans","volume":"31","author":"Jazinizadeh","year":"2020","journal-title":"Osteoporos Int"},{"key":"2026072004370026800_ref25","volume-title":"Experiment Tracking with Weights and Biases","author":"Biewald","year":"2020"},{"issue":"7","key":"2026072004370026800_ref26","doi-asserted-by":"publisher","first-page":"2296626","DOI":"10.1080\/21681163.2023.2296626","article-title":"A CNN-based strategy to automate contour detection of the hip and proximal femur using DXA hip images from longitudinal databases (CLSA and CaMos)","volume":"11","author":"Ammar","year":"2024","journal-title":"Comput Methods Biomech Biomed Eng Imaging Vis"},{"issue":"12","key":"2026072004370026800_ref27","doi-asserted-by":"publisher","first-page":"2101","DOI":"10.1109\/TMI.2011.2163074","article-title":"Reconstructing the 3D shape and bone mineral density distribution of the proximal femur from dual-energy X-ray absorptiometry","volume":"30","author":"Whitmarsh","year":"2011","journal-title":"IEEE Trans Med Imaging"},{"issue":"9","key":"2026072004370026800_ref28","doi-asserted-by":"publisher","first-page":"1862","DOI":"10.1109\/TPAMI.2014.2382106","article-title":"Robust and accurate shape model matching using random forest regression-voting","volume":"37","author":"Lindner","year":"2015","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"issue":"8","key":"2026072004370026800_ref29","doi-asserted-by":"publisher","first-page":"1462","DOI":"10.1109\/TMI.2013.2258030","article-title":"Fully automatic segmentation of the proximal femur using random forest regression voting","volume":"32","author":"Lindner","year":"2013","journal-title":"IEEE Trans Med Imaging"},{"key":"2026072004370026800_ref30","doi-asserted-by":"publisher","DOI":"10.1093\/jbmr\/zjaf171","article-title":"DXA-derived hip shape is associated with hip fracture: a longitudinal study of 38,123 UK Biobank participants","volume":"41","author":"Scott"},{"issue":"5","key":"2026072004370026800_ref31","doi-asserted-by":"publisher","first-page":"727","DOI":"10.3233\/XST-180399","article-title":"Femur segmentation in DXA imaging using a machine learning decision tree","volume":"26","author":"Hussain","year":"2018","journal-title":"J Xray Sci Technol"},{"issue":"12","key":"2026072004370026800_ref32","doi-asserted-by":"publisher","first-page":"1474","DOI":"10.1016\/j.medengphy.2016.09.019","article-title":"Fully automatic segmentation of femurs with medullary canal definition in high and in low resolution CT scans","volume":"38","author":"Almeida","year":"2016","journal-title":"Med Eng Phys"},{"issue":"6","key":"2026072004370026800_ref33","doi-asserted-by":"publisher","first-page":"644","DOI":"10.1080\/10255842.2019.1577828","article-title":"Cascaded statistical shape model based segmentation of the full lower limb in CT","volume":"22","author":"Audenaert","year":"2019","journal-title":"Comput Methods Biomech Biomed Engin"},{"issue":"1","key":"2026072004370026800_ref34","doi-asserted-by":"publisher","first-page":"16485","DOI":"10.1038\/s41598-018-34817-6","article-title":"Segmentation of the proximal femur from MR images using deep convolutional neural networks","volume":"8","author":"Deniz","year":"2018","journal-title":"Sci Rep"},{"issue":"21","key":"2026072004370026800_ref35","doi-asserted-by":"publisher","first-page":"2053","DOI":"10.1056\/NEJMcp1611090","article-title":"Management of acute hip fracture","volume":"377","author":"Bhandari","year":"2017","journal-title":"N Engl J Med"},{"issue":"6","key":"2026072004370026800_ref36","first-page":"675","article-title":"Hip fractures: diagnosis and management","volume":"106","author":"Schroeder","journal-title":"Am Fam Physician"}],"container-title":["JBMR Plus"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/jbmrplus\/advance-article-pdf\/doi\/10.1093\/jbmrpl\/ziag103\/68558711\/ziag103.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/jbmrplus\/article-pdf\/10\/8\/ziag103\/68558711\/ziag103.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/jbmrplus\/article-pdf\/10\/8\/ziag103\/68558711\/ziag103.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,20]],"date-time":"2026-07-20T08:37:09Z","timestamp":1784536629000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/jbmrplus\/article\/doi\/10.1093\/jbmrpl\/ziag103\/8711622"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,19]]},"references-count":36,"journal-issue":{"issue":"8","published-print":{"date-parts":[[2026,7,3]]}},"URL":"https:\/\/doi.org\/10.1093\/jbmrpl\/ziag103","relation":{},"ISSN":["2473-4039"],"issn-type":[{"value":"2473-4039","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2026,8]]},"published":{"date-parts":[[2026,6,19]]},"article-number":"ziag103"}}