{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,25]],"date-time":"2026-09-25T06:35:16Z","timestamp":1790318116857,"version":"4.1.0"},"reference-count":53,"publisher":"Public Library of Science (PLoS)","issue":"10","license":[{"start":{"date-parts":[[2025,10,16]],"date-time":"2025-10-16T00:00:00Z","timestamp":1760572800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"NRFK","award":["RS-2023-00217471"],"award-info":[{"award-number":["RS-2023-00217471"]}]}],"content-domain":{"domain":["www.plosone.org"],"crossmark-restriction":false},"short-container-title":["PLoS One"],"abstract":"<jats:p>Osteoporosis is a prevalent bone disease characterized by reduced bone density and an elevated risk of fractures, especially in older adults and postmenopausal women. The clinical consequences of osteoporotic fractures extend beyond pain and disability, contributing substantially to morbidity, mortality, and healthcare costs. Early intervention and accurate detection is therefore essential to improve patient outcomes. This paper introduces an advanced deep-learning methodology to enhance the accuracy and efficiency of osteoporosis detection through knee X-ray analysis. The proposed approach integrates features from two pre-trained models, DenseNet169 and Vision Transformer (ViT), with a custom-designed Attention Model (AM) to capture detailed spatial and channel-specific information from the input images. These fused features are then fed into a fully connected neural network to classify the images as osteoporotic or normal. The results indicate significant improvements in classification accuracy, achieving a high accuracy rate on previously unseen test data. The proposed model achieves superior performance over existing methods and other recent models for osteoporosis detection, with an accuracy of 0.8611, specificity of 0.9474, and precision of 0.9286. Our approach effectively combines convolutional and transformer-based representations, enabling extraction of both local and global features for comprehensive bone characterization. These findings highlight the model\u2019s potential to support early diagnosis, timely intervention, and improved patient care in osteoporosis management.<\/jats:p>","DOI":"10.1371\/journal.pone.0334664","type":"journal-article","created":{"date-parts":[[2025,10,16]],"date-time":"2025-10-16T17:35:56Z","timestamp":1760636156000},"page":"e0334664","update-policy":"https:\/\/doi.org\/10.1371\/journal.pone.corrections_policy","source":"Crossref","is-referenced-by-count":9,"title":["BONE-Net: A novel hybrid deep-learning model for effective osteoporosis detection"],"prefix":"10.1371","volume":"20","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-2408-162X","authenticated-orcid":true,"given":"Ishaq","family":"Muhammad","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5588-0218","authenticated-orcid":true,"given":"Routhu Srinivasa","family":"Rao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2482-1869","authenticated-orcid":true,"given":"Bumshik","family":"Lee","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2025,10,16]]},"reference":[{"issue":"5","key":"pone.0334664.ref001","doi-asserted-by":"crossref","first-page":"1388","DOI":"10.1111\/jgs.17043","article-title":"The prevention of osteoporosis and sarcopenia in older adults","volume":"69","author":"PP Coll","year":"2021","journal-title":"J Am Geriatr Soc"},{"issue":"12","key":"pone.0334664.ref002","doi-asserted-by":"crossref","first-page":"2271","DOI":"10.1007\/s00198-020-05497-8","article-title":"Is there a role for menopausal hormone therapy in the management of postmenopausal osteoporosis?","volume":"31","author":"S Rozenberg","year":"2020","journal-title":"Osteoporos Int"},{"key":"pone.0334664.ref003","article-title":"Interventions for improving mobility after hip fracture surgery in adults","author":"NJ Fairhall","year":"2022","journal-title":"Cochrane database of systematic reviews"},{"issue":"7","key":"pone.0334664.ref004","doi-asserted-by":"crossref","first-page":"1225","DOI":"10.1002\/jbmr.4284","article-title":"Incidence of Hip and Subtrochanteric\/Femoral Shaft Fractures in Postmenopausal Women With Osteoporosis in the Phase 3 Long-Term Odanacatib Fracture Trial","volume":"36","author":"S Papapoulos","year":"2021","journal-title":"J Bone Miner Res"},{"issue":"11","key":"pone.0334664.ref005","doi-asserted-by":"crossref","first-page":"8019","DOI":"10.1007\/s00330-022-08805-4","article-title":"Radiomics analysis based on lumbar spine CT to detect osteoporosis","volume":"32","author":"Y-W Jiang","year":"2022","journal-title":"Eur Radiol"},{"issue":"10","key":"pone.0334664.ref006","doi-asserted-by":"crossref","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":"DP Ahern","year":"2021","journal-title":"Spine J"},{"issue":"4","key":"pone.0334664.ref007","doi-asserted-by":"crossref","first-page":"2199","DOI":"10.1007\/s00330-019-06573-2","article-title":"Imaging of sarcopenia: old evidence and new insights","volume":"30","author":"D Albano","year":"2020","journal-title":"Eur Radiol"},{"issue":"1","key":"pone.0334664.ref008","doi-asserted-by":"crossref","first-page":"46","DOI":"10.5152\/eurjrheum.2016.048","article-title":"An overview and management of osteoporosis","volume":"4","author":"T S\u00f6zen","year":"2017","journal-title":"Eur J Rheumatol"},{"key":"pone.0334664.ref009","article-title":"Healthcare policy changes in osteoporosis can improve outcomes and reduce costs in the United States","volume":"3","author":"EM Lewiecki","year":"2019","journal-title":"Journal of Bone and Mineral Research Plus"},{"issue":"1","key":"pone.0334664.ref010","doi-asserted-by":"crossref","first-page":"21","DOI":"10.1007\/s11548-018-1883-7","article-title":"Automatic bone segmentation in whole-body CT images","volume":"14","author":"A Klein","year":"2019","journal-title":"Int J Comput Assist Radiol Surg"},{"key":"pone.0334664.ref011","doi-asserted-by":"crossref","first-page":"596","DOI":"10.1016\/S2213-8587(24)00153-0","article-title":"The potential role for artificial intelligence in fracture risk prediction","volume":"12","author":"N Hong","year":"2024","journal-title":"Lancet Diabetes Endocrinol"},{"key":"pone.0334664.ref012","unstructured":"Python S. Osteoporosis Knee X-ray Dataset. Available from: https:\/\/www.kaggle.com\/datasets\/stevepython\/osteoporosis-knee-xray-dataset. 2021."},{"key":"pone.0334664.ref013","first-page":"4700","article-title":"Densely connected convolutional networks.","author":"G Huang","year":"2017","journal-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition"},{"key":"pone.0334664.ref014","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"A Dosovitskiy","year":"2020","journal-title":"arXiv preprint"},{"key":"pone.0334664.ref015","first-page":"1043","article-title":"hybrid attention-driven deep learning model for osteoporosis detection in knees.","author":"I Muhammad","year":"2025","journal-title":"2025 International Conference on Artificial Intelligence in Information and Communication (ICAIIC)"},{"key":"pone.0334664.ref016","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1109\/ACCESS.2024.3384496","article-title":"Evaluation and Analysis of Large Language Models for Clinical Text Augmentation and Generation","author":"A Latif","year":"2024","journal-title":"IEEE Access"},{"key":"pone.0334664.ref017","doi-asserted-by":"crossref","first-page":"123891","DOI":"10.1109\/ACCESS.2023.3329364","article-title":"Multiclass segmentation using teeth attention modules for dental x-ray images","volume":"11","author":"A Ghafoor","year":"2023","journal-title":"IEEE Access"},{"issue":"24","key":"pone.0334664.ref018","doi-asserted-by":"crossref","first-page":"2877","DOI":"10.3390\/diagnostics14242877","article-title":"Computer-Aided Diagnosis in Spontaneous Abortion: A Histopathology Dataset and Benchmark for Products of Conception","volume":"14","author":"T Mahmood","year":"2024","journal-title":"Diagnostics (Basel)"},{"key":"pone.0334664.ref019","doi-asserted-by":"crossref","first-page":"898","DOI":"10.1016\/S2213-8587(17)30188-2","article-title":"Osteoporosis treatment: recent developments and ongoing challenges","volume":"5","author":"S Khosla","year":"2017","journal-title":"Lancet Diabetes Endocrinol"},{"issue":"3","key":"pone.0334664.ref020","doi-asserted-by":"crossref","first-page":"108","DOI":"10.22271\/ortho.2021.v7.i3b.2736","article-title":"A comparative study on detection of osteoporosis using deep learning methods: A review","volume":"7","author":"KA Patil","year":"2021","journal-title":"Int J Orthop Sci"},{"issue":"4","key":"pone.0334664.ref021","doi-asserted-by":"crossref","first-page":"3000605241244754","DOI":"10.1177\/03000605241244754","article-title":"Deep learning in the radiologic diagnosis of osteoporosis: a literature review","volume":"52","author":"Y He","year":"2024","journal-title":"J Int Med Res"},{"issue":"6","key":"pone.0334664.ref022","doi-asserted-by":"crossref","first-page":"3045","DOI":"10.1007\/s00590-024-04032-3","article-title":"Deep learning for osteoporosis screening using an anteroposterior hip radiograph image","volume":"34","author":"A Boonrod","year":"2024","journal-title":"Eur J Orthop Surg Traumatol"},{"issue":"4","key":"pone.0334664.ref023","doi-asserted-by":"crossref","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":"S Wang","year":"2024","journal-title":"Quant Imaging Med Surg"},{"key":"pone.0334664.ref024","doi-asserted-by":"crossref","first-page":"770","DOI":"10.1109\/CVPR.2016.90","article-title":"Deep Residual Learning for Image Recognition.","author":"K He","year":"2016","journal-title":"2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)"},{"issue":"1","key":"pone.0334664.ref025","doi-asserted-by":"crossref","first-page":"5245","DOI":"10.1038\/s41598-024-56114-1","article-title":"Using machine learning techniques to predict the risk of osteoporosis based on nationwide chronic disease data","volume":"14","author":"J-B Tu","year":"2024","journal-title":"Sci Rep"},{"key":"pone.0334664.ref026","doi-asserted-by":"crossref","first-page":"243","DOI":"10.1007\/978-1-4842-4470-8_20","article-title":"Logistic regression","volume-title":"Building machine learning and deep learning models on google cloud platform: A comprehensive guide for beginners","author":"E Bisong","year":"2019"},{"key":"pone.0334664.ref027","first-page":"2825","article-title":"Scikit\u2010learn: Machine learning in python Fabian","volume":"12","author":"F Pedregosa","year":"2011","journal-title":"Journal of Machine Learning Research"},{"key":"pone.0334664.ref028","doi-asserted-by":"crossref","first-page":"1937","DOI":"10.1007\/s10462-020-09896-5","article-title":"A comparative analysis of gradient boosting algorithms","volume":"54","author":"C Bent\u00e9jac","year":"2021","journal-title":"Artif Intell Rev"},{"key":"pone.0334664.ref029","doi-asserted-by":"crossref","first-page":"340","DOI":"10.1109\/SIBGRAPI51738.2020.00053","article-title":"From explanations to feature selection: assessing SHAP values as feature selection mechanism.","author":"WE Marcilio","year":"2020","journal-title":"2020 33rd SIBGRAPI Conference on Graphics, Patterns and Images (SIBGRAPI)"},{"issue":"1","key":"pone.0334664.ref030","doi-asserted-by":"crossref","first-page":"19997","DOI":"10.1038\/s41598-021-99549-6","article-title":"Prediction of osteoporosis from simple hip radiography using deep learning algorithm","volume":"11","author":"R Jang","year":"2021","journal-title":"Sci Rep"},{"issue":"12","key":"pone.0334664.ref031","doi-asserted-by":"crossref","first-page":"6999","DOI":"10.1109\/TNNLS.2021.3084827","article-title":"A Survey of Convolutional Neural Networks: Analysis, Applications, and Prospects","volume":"33","author":"Z Li","year":"2022","journal-title":"IEEE Trans Neural Netw Learn Syst"},{"key":"pone.0334664.ref032","doi-asserted-by":"crossref","first-page":"244","DOI":"10.1109\/COSITE60233.2023.10249479","article-title":"Impact of Image Enhancement for Osteoporosis Detection Based on Deep Learning Algorithm","author":"RD Iman","year":"2023","journal-title":"2023 2nd International Conference on Computer System, Information Technology, and Electrical Engineering (COSITE)"},{"key":"pone.0334664.ref033","first-page":"1","article-title":"A Comparative Analysis of Deep Learning Models and Conventional Approaches for Osteoporosis Detection in Hip X-Ray Images.","author":"V Kawade","year":"2023","journal-title":"2023 World Conference on Communication & Computing (WCONF)"},{"key":"pone.0334664.ref034","first-page":"788","article-title":"An advanced deep learning approach for primary osteoporosis prediction using radiographs with clinical covariates.","author":"R Umamaheswari","year":"2023","journal-title":"2023 7th International Conference on Electronics, Communication and Aerospace Technology (ICECA)"},{"issue":"12","key":"pone.0334664.ref035","article-title":"Predictive value of machine learning on fracture risk in osteoporosis: a systematic review and meta-analysis","volume":"13","author":"Y Wu","year":"2023","journal-title":"BMJ Open"},{"issue":"6","key":"pone.0334664.ref036","doi-asserted-by":"crossref","first-page":"887","DOI":"10.1002\/jbmr.4814","article-title":"Deep-Learning-Based Detection of Vertebral Fracture and Osteoporosis Using Lateral Spine X-Ray Radiography","volume":"38","author":"N Hong","year":"2023","journal-title":"J Bone Miner Res"},{"key":"pone.0334664.ref037","doi-asserted-by":"crossref","first-page":"91","DOI":"10.1109\/TSP55681.2022.9851342","article-title":"Osteo-Net: A Robust Deep Learning-Based Diagnosis of Osteoporosis Using X-ray images.","author":"A Kumar","year":"2022","journal-title":"2022 45th International Conference on Telecommunications and Signal Processing (TSP)"},{"key":"pone.0334664.ref038","doi-asserted-by":"crossref","first-page":"131069","DOI":"10.1016\/j.neucom.2025.131069","article-title":"Multi-level feature enhancement and dual attention mechanisms for improved osteoporosis diagnosis","volume":"652","author":"RS Rao","year":"2025","journal-title":"Neurocomputing"},{"issue":"5","key":"pone.0334664.ref039","doi-asserted-by":"crossref","DOI":"10.1148\/ryai.220042","article-title":"Improved CT-based Osteoporosis Assessment with a Fully Automated Deep Learning Tool","volume":"4","author":"PJ Pickhardt","year":"2022","journal-title":"Radiol Artif Intell"},{"key":"pone.0334664.ref040","first-page":"234","article-title":"U-net: Convolutional networks for biomedical image segmentation.","author":"O Ronneberger","year":"2015","journal-title":"Medical image computing and computer-assisted intervention\u2013MICCAI 2015: 18th international conference, Munich, Germany, October 5-9, 2015, proceedings, part III"},{"key":"pone.0334664.ref041","doi-asserted-by":"crossref","first-page":"1061911","DOI":"10.3389\/fphys.2022.1061911","article-title":"Prediction of bone mineral density in CT using deep learning with explainability","volume":"13","author":"JW Kang","year":"2023","journal-title":"Front Physiol"},{"key":"pone.0334664.ref042","doi-asserted-by":"crossref","first-page":"94","DOI":"10.1016\/j.isprsjprs.2020.01.013","article-title":"ResUNet-a: A deep learning framework for semantic segmentation of remotely sensed data","volume":"162","author":"FI Diakogiannis","year":"2020","journal-title":"ISPRS Journal of Photogrammetry and Remote Sensing"},{"key":"pone.0334664.ref043","doi-asserted-by":"crossref","first-page":"102639","DOI":"10.1016\/j.artmed.2023.102639","article-title":"Osteoporosis prediction in lumbar spine X-ray images using the multi-scale weighted fusion contextual transformer network","volume":"143","author":"L Xue","year":"2023","journal-title":"Artif Intell Med"},{"issue":"2","key":"pone.0334664.ref044","doi-asserted-by":"crossref","first-page":"1489","DOI":"10.1109\/TPAMI.2022.3164083","article-title":"Contextual Transformer Networks for Visual Recognition","volume":"45","author":"Y Li","year":"2023","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"pone.0334664.ref045","doi-asserted-by":"crossref","first-page":"5731","DOI":"10.1109\/ACCESS.2023.3348817","article-title":"KONet: Toward a Weighted Ensemble Learning Model for Knee Osteoporosis Classification","volume":"12","author":"MJA Rasool","year":"2024","journal-title":"IEEE Access"},{"key":"pone.0334664.ref046","article-title":"Efficientnet: Rethinking model scaling for convolutional neural networks","author":"M Tan","year":"2019","journal-title":"arXiv preprint"},{"key":"pone.0334664.ref047","doi-asserted-by":"crossref","first-page":"184119","DOI":"10.1109\/ACCESS.2024.3503413","article-title":"Hybrid Deep Learning EfficientNetV2 and Vision Transformer (EffNetV2-ViT) Model for Breast Cancer Histopathological Image Classification","volume":"12","author":"M Hayat","year":"2024","journal-title":"IEEE Access"},{"issue":"1","key":"pone.0334664.ref048","first-page":"1","article-title":"Deep feature extraction and classification of Alzheimer\u2019s disease: A novel fusion of vision transformer-densenet approach with visualization","volume":"48","author":"PA Menon","year":"2023","journal-title":"Journal of Alzheimer\u2019s Disease"},{"key":"pone.0334664.ref049","article-title":"Very deep convolutional networks for large-scale image recognition","author":"K Simonyan","year":"2014","journal-title":"arXiv preprint"},{"key":"pone.0334664.ref050","first-page":"2818","article-title":"Rethinking the inception architecture for computer vision.","author":"C Szegedy","year":"2016","journal-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition"},{"key":"pone.0334664.ref051","first-page":"16133","article-title":"Convnext v2: Co-designing and scaling convnets with masked autoencoders. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"S Woo","year":"2023"},{"key":"pone.0334664.ref052","author":"D Kim","year":"2024"},{"key":"pone.0334664.ref053","article-title":"Metaformer baselines for vision","author":"W Yu","year":"2023","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"}],"container-title":["PLOS One"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0334664","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,16]],"date-time":"2025-10-16T17:36:06Z","timestamp":1760636166000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0334664"}},"subtitle":[],"editor":[{"given":"Alessandra","family":"Aldieri","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2025,10,16]]},"references-count":53,"journal-issue":{"issue":"10","published-online":{"date-parts":[[2025,10,16]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pone.0334664","relation":{},"ISSN":["1932-6203"],"issn-type":[{"value":"1932-6203","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10,16]]}}}