دورية أكاديمية
أعرض في EDS

Classification of Fracture Risk in Fallers Using Dual-Energy X-Ray Absorptiometry (DXA) Images and Deep Learning-Based Feature Extraction.

التفاصيل البيبلوغرافية
العنوان: Classification of Fracture Risk in Fallers Using Dual-Energy X-Ray Absorptiometry (DXA) Images and Deep Learning-Based Feature Extraction.
المؤلفون: Senanayake D; Department of Biomedical Engineering University of Melbourne Parkville VIC Australia.; Department of Mechanical Engineering University of Melbourne Parkville VIC Australia., Seneviratne S; Department of Mechanical Engineering University of Melbourne Parkville VIC Australia.; Melbourne School of Design University of Melbourne Parkville VIC Australia., Imani M; Australian Institute for Musculoskeletal Science (AIMSS), Geroscience & Osteosarcopenia Research Program University of Melbourne and Western Health St Albans VIC Australia.; Department of Medicine-Western Health Melbourne Medical School St Albans VIC Australia., Harijanto C; Department of Medicine-Western Health Melbourne Medical School St Albans VIC Australia., Sales M; Australian Institute for Musculoskeletal Science (AIMSS), Geroscience & Osteosarcopenia Research Program University of Melbourne and Western Health St Albans VIC Australia.; Department of Medicine-Western Health Melbourne Medical School St Albans VIC Australia., Lee P; Department of Biomedical Engineering University of Melbourne Parkville VIC Australia., Duque G; Bone, Muscle & Geroscience Group, Research Institute of the McGill University Health Centre Montreal QC Canada.; Dr. Joseph Kaufmann Chair in Geriatric Medicine, Department of Medicine McGill University Montreal QC Canada., Ackland DC; Department of Biomedical Engineering University of Melbourne Parkville VIC Australia.
المصدر: JBMR plus [JBMR Plus] 2023 Oct 19; Vol. 7 (12), pp. e10828. Date of Electronic Publication: 2023 Oct 19 (Print Publication: 2023).
نوع المنشور: Journal Article
اللغة: English
بيانات الدورية: Publisher: Oxford University Press Country of Publication: England NLM ID: 101707013 Publication Model: eCollection Cited Medium: Internet ISSN: 2473-4039 (Electronic) Linking ISSN: 24734039 NLM ISO Abbreviation: JBMR Plus Subsets: PubMed not MEDLINE
أسماء مطبوعة: Publication: 2024- : Oxford : Oxford University Press
Original Publication: [Chichester, West Sussex, UK] : John Wiley & Sons, [2017]-
مستخلص: Dual-energy X-ray absorptiometry (DXA) scans are one of the most frequently used imaging techniques for calculating bone mineral density, yet calculating fracture risk using DXA image features is rarely performed. The objective of this study was to combine deep neural networks, together with DXA images and patient clinical information, to evaluate fracture risk in a cohort of adults with at least one known fall and age-matched healthy controls. DXA images of the entire body as, well as isolated images of the hip, forearm, and spine (1488 total), were obtained from 478 fallers and 48 non-faller controls. A modeling pipeline was developed for fracture risk prediction using the DXA images and clinical data. First, self-supervised pretraining of feature extractors was performed using a small vision transformer (ViT-S) and a convolutional neural network model (VGG-16 and Resnet-50). After pretraining, the feature extractors were then paired with a multilayer perceptron model, which was used for fracture risk classification. Classification was achieved with an average area under the receiver-operating characteristic curve (AUROC) score of 74.3%. This study demonstrates ViT-S as a promising neural network technique for fracture risk classification using DXA scans. The findings have future application as a fracture risk screening tool for older adults at risk of falls. © 2023 The Authors. JBMR Plus published by Wiley Periodicals LLC on behalf of American Society for Bone and Mineral Research.
(© 2023 The Authors. JBMR Plus published by Wiley Periodicals LLC on behalf of American Society for Bone and Mineral Research.)
References: Arch Osteoporos. 2020 Apr 19;15(1):59. (PMID: 32306163)
Osteoporos Int. 2022 Oct;33(10):2049-2102. (PMID: 35478046)
Osteoporos Int. 2018 Jan;29(1):191-200. (PMID: 29038836)
J Am Geriatr Soc. 2005 Sep;53(9):1618-22. (PMID: 16137297)
Maturitas. 2004 Jul 15;48(3):271-87. (PMID: 15207894)
Osteoporos Int. 2018 Mar;29(3):557-566. (PMID: 29230511)
J Bone Miner Res. 2022 Oct;37(10):2018-2024. (PMID: 36069122)
PLoS One. 2014 Sep 25;9(9):e107695. (PMID: 25255221)
J Orthop Surg Res. 2020 Feb 27;15(1):81. (PMID: 32103764)
Age Ageing. 2022 Jun 1;51(6):. (PMID: 35753766)
Chin J Traumatol. 2016 Oct 1;19(5):275-277. (PMID: 27780507)
J Bone Miner Res. 2016 Apr;31(4):725-31. (PMID: 26572496)
Osteoporos Int. 2022 Oct;33(10):2103-2136. (PMID: 35639106)
Bone. 2020 May;134:115286. (PMID: 32070789)
J Nucl Med. 2021 Apr;62(4):446-454. (PMID: 33310738)
Osteoporos Int. 2022 Sep;33(9):1895-1907. (PMID: 35701629)
Osteoporos Int. 2020 Sep;31(9):1779-1786. (PMID: 32377806)
J Bone Miner Res. 2021 Apr;36(4):654-661. (PMID: 33450071)
Expert Rev Endocrinol Metab. 2021 Jul;16(4):191-200. (PMID: 33982611)
J Am Med Dir Assoc. 2015 Apr;16(4):290-5. (PMID: 25512216)
J Nutr Health Aging. 2015 Apr;19(4):474-80. (PMID: 25809813)
AJR Am J Roentgenol. 2019 Sep;213(3):506-513. (PMID: 31166761)
فهرسة مساهمة: Keywords: AGING; ANALYSIS/QUANTITATION OF BONE; BIOENGINEERING; DXA; FRACTURE RISK ASSESSMENT; ORTHOPAEDICS; PRACTICE/POLICYRELATED ISSUES
تواريخ الأحداث: Date Created: 20231222 Latest Revision: 20231223
رمز التحديث: 20231223
مُعرف محوري في PubMed: PMC10731096
DOI: 10.1002/jbm4.10828
PMID: 38130762
قاعدة البيانات: MEDLINE
الوصف
تدمد:2473-4039
DOI:10.1002/jbm4.10828