EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Automatic opportunistic osteoporosis screening using chest X-ray images via deep neural networks

Jun Tang, Xiang Yin, Jiangyuan Lai, Keyu Luo, Dongdong Wu

Bone · 2025-12 · 201 · 117618

DOI: 10.1016/j.bone.2025.117618 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Bone, 2025-12. Verfasst von Jun Tang und 4 weiteren Autor:innen. Beteiligte Einrichtung: Department of Information, Daping Hospital, Army Medical University, Chongqing 400042, China. Hauptthemen laut MEDLINE: Osteoporosis, Neural Networks, Computer, Radiography, Thoracic, Mass Screening. Die Arbeit wurde bisher 11-mal zitiert (Crossref) und nennt 30 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

BACKGROUND: Osteoporosis is a bone disease characterized by reduced bone mineral density and quality, which increases the risk of fragility fractures. The current diagnostic gold standard, dual-energy X-ray absorptiometry (DXA), faces limitations such as low equipment penetration, high testing costs, and radiation exposure, restricting its feasibility as a screening tool. METHOD: To address these limitations, we retrospectively collected data from 1995 patients who visited Chongqing Daping Hospital between January 2019 and August 2024. We have developed an opportunistic screening method using chest X-rays and designed three innovative deep neural network models using transfer learning: Inception v3, VGG16, and ResNet50. These models were evaluated for their classification performance of osteoporosis using chest X-ray images and validated through an external dataset. RESULTS: The ResNet50 model demonstrated superior performance, achieving average accuracies of 87.85 % and 90.38 % in the internal test dataset across two experiments, with AUC values of 0.945 and 0.957, respectively. These results outperformed traditional convolutional neural networks. In the external validation, the ResNet50 model achieved an AUC of 0.904, accuracy of 89 %, sensitivity of 90 %, and specificity of 88.57 %, demonstrating strong generalization ability. And the model shows robust performance despite concurrent pulmonary pathologies. CONCLUSIONS: This study provides an automatic screening method for osteoporosis using chest X-rays, without additional radiation exposure or cost. The ResNet50 model's high performance supports clinicians in the early identification and treatment of osteoporosis patients.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

OsteoporosisNeural Networks, ComputerRadiography, ThoracicMass ScreeningHumansFemaleMiddle AgedAgedMaleRetrospective StudiesDeep LearningAbsorptiometry, Photon

Stichwörter der Autor:innen

Chest X-rayDeep neural networkOsteoporosisResNet50Transfer learning

Autor:innen und Institutionen

  • Department of Information, Daping Hospital, Army Medical University, Chongqing 400042, China.
  • Department of Orthopedics, Daping Hospital, Army Medical University, Chongqing 400042, China.
  • School of Basic Medicine, Army Medical University, Chongqing 400038, China.
  • Department of Orthopedics, Daping Hospital, Army Medical University, Chongqing 400042, China. Electronic address: keyuluo@tmmu.edu.cn.
  • Department of Information, Daping Hospital, Army Medical University, Chongqing 400042, China. Electronic address: 604269346@qq.com.

Förderung

  • National Natural Science Foundation of China

Zitieren

APA

Tang, J., Yin, X., Lai, J., Luo, K., & Wu, D. (2025). Automatic opportunistic osteoporosis screening using chest X-ray images via deep neural networks. Bone, 201, 117618. https://doi.org/10.1016/j.bone.2025.117618

Vancouver

Tang J, Yin X, Lai J, Luo K, Wu D. Automatic opportunistic osteoporosis screening using chest X-ray images via deep neural networks. Bone. 2025;201:117618. doi:10.1016/j.bone.2025.117618

BibTeX
@article{Tang2025,
  author = {Tang, Jun and Yin, Xiang and Lai, Jiangyuan and Luo, Keyu and Wu, Dongdong},
  title = {Automatic opportunistic osteoporosis screening using chest X-ray images via deep neural networks},
  journal = {Bone},
  year = {2025},
  volume = {201},
  pages = {117618},
  doi = {10.1016/j.bone.2025.117618}
}
Kostenlos starten →