Department of Physical Medicine and Rehabilitation, Taoyuan Chang Gung Memorial Hospital, Taoyuan, Taiwan; Comprehensive Sports Medicine Center, Taoyuan Chang Gung Memorial Hospital, Taoyuan, Taiwan; Master of Science Degree Program in Innovation for Smart Medicine, Chang Gung University, Taoyuan, Taiwan; College of Management, Chang Gung University, Taoyuan, Taiwan.
Department of Research and Development, Chang Gung Medical Technology Co., Ltd., No. 11-5, Wenhua 2nd Road., Ltd., Guishan District., Taoyuan City 333, Taiwan.
Bone. 2025 Jan;190:117317. doi: 10.1016/j.bone.2024.117317. Epub 2024 Nov 3.
Osteoporosis, affecting over 200 million individuals, often remains unrecognized and untreated, increasing the risk of fractures in older adults. Osteoporosis is typically diagnosed with bone mineral density (BMD) measured by dual-energy X-ray absorptiometry (DXA). This study aims to develop DeepDXA-Hand, a deep learning model using the efficient CNN-based deep learning architecture, for opportunistic osteoporosis screening from hand radiographs.
DeepDXA-Hand utilizes a CNN-based, HarDNet, approach to predict BMD non-invasively. A total of 10,351 hand radiographs and DXA pairs were used for model training and validation. The model's interpretability was enhanced using GradCAM for hotspot analysis to determine the model's attention areas.
The predicted and ground truth BMD were significantly correlated with a correlation coefficient of 0.745. For binary classification of osteoporosis, DeepDXA-Hand demonstrated a sensitivity of 0.73, specificity of 0.83, and accuracy of 0.80, indicating its clinical potential. The model mainly focused on the carpal bones, such as the capitate, trapezoid, hamate, triquetrum, and the head of the second metacarpal bone, suggesting these areas provide radiological features for inferring BMD.
DeepDXA-Hand shows potential for the early detection of osteoporosis with high sensitivity and specificity. Further studies should explore its utility in predicting fracture risks.
Osteoporosis affects millions and often goes undetected and untreated. DeepDXA-Hand, a HarDNet-based deep learning model, predicted bone mineral density with a correlation of 0.745 and classified osteoporosis with 0.80 accuracy. This model enhances early detection and has significant clinical potential as osteoporosis opportunistic screening tool.
骨质疏松症影响着超过 2 亿人，常被漏诊和未治疗，增加了老年人骨折的风险。骨质疏松症通常通过双能 X 射线吸收法（DXA）测量骨密度（BMD）来诊断。本研究旨在开发一种基于深度学习的模型 DeepDXA-Hand，该模型使用高效的基于卷积神经网络（CNN）的深度学习架构，从手部 X 光片中进行骨质疏松症的机会性筛查。
DeepDXA-Hand 使用基于 CNN 的 HarDNet 方法进行 BMD 的无创预测。共使用了 10351 张手部 X 光片和 DXA 对进行模型训练和验证。使用 GradCAM 进行热点分析来增强模型的可解释性，以确定模型的关注区域。
预测的和真实的 BMD 具有显著相关性，相关系数为 0.745。对于骨质疏松症的二分类，DeepDXA-Hand 表现出 0.73 的敏感性、0.83 的特异性和 0.80 的准确性，表明其具有临床潜力。该模型主要关注腕骨，如头状骨、梯形骨、钩骨、三角骨和第二掌骨的头部，表明这些区域提供了用于推断 BMD 的放射学特征。
DeepDXA-Hand 具有高敏感性和特异性，有望用于骨质疏松症的早期检测。进一步的研究应该探索其在预测骨折风险方面的应用。
