文献速递骨质疏松与代谢性骨病

从平片X线预测面积骨密度的人工智能系统

Artificial intelligence system for predicting areal bone mineral density from plain X-rays.
PubMed 文献 · Osteoporos Int · 2025-08-27

该研究基于越南骨质疏松研究(3783名≥18岁参与者)的7060张数字X线片,开发了七模型集成深度学习系统从骨盆正位和脊柱侧位X线预测面积骨密度(xBMD)。xBMD与DXA测得的aBMD在股骨颈(r=0.90;95%CI 0.88-0.91)和腰椎(r=0.87;95%CI 0.85-0.88)均强相关,识别髋部骨折高风险者的AUC在股骨颈为0.96(95%CI 0.95-0.98)、腰椎为0.97(95%CI 0.96-0.99)。作者认为该AI系统可在资源有限地区作为DXA的替代方案用于骨质疏松筛查。

要点

  • xBMD与DXA测得的aBMD在股骨颈(r=0.90;95%CI 0.88-0.91)和腰椎(r=0.87;95%CI 0.85-0.88)均呈强相关。
  • AI系统识别髋部骨折高风险者的AUC在股骨颈为0.96(95%CI 0.95-0.98)、腰椎为0.97(95%CI 0.96-0.99)。
  • 作者认为该AI系统可在资源有限且患者需求高的场景中作为DXA的替代方案用于骨质疏松筛查。

核心结论

  • AI能准确预测aBMD并识别骨折高风险个体,该系统可在资源有限地区作为DXA的替代方案用于骨质疏松筛查。

研究设计与样本

  • 研究为越南骨质疏松研究(前瞻性人群研究)的一部分,纳入3783名18岁及以上参与者,采集7060张骨盆正位和脊柱侧位数字X线片(FCR Capsula XLII系统)。
  • 采用七种深度学习模型的集成分析X线片并预测骨密度(称为xBMD),以DXA(Hologic Horizon)测量的股骨颈和腰椎aBMD为参照。

主要发现

  • xBMD与股骨颈aBMD的Pearson相关系数r=0.90(95%CI 0.88-0.91),与腰椎aBMD的r=0.87(95%CI 0.85-0.88)。
  • 该相关性在不同年龄组和性别间保持一致。
  • AI系统识别髋部骨折高风险者的AUC在股骨颈为0.96(95%CI 0.95-0.98)、腰椎为0.97(95%CI 0.96-0.99)。

关键数值与推荐

  • xBMD与股骨颈aBMD的相关系数r=0.90(95%CI 0.88-0.91)。
  • xBMD与腰椎aBMD的相关系数r=0.87(95%CI 0.85-0.88)。
  • 识别髋部骨折高风险者的AUC:股骨颈0.96(95%CI 0.95-0.98),腰椎0.97(95%CI 0.96-0.99)。

临床怎么用

  • 作者认为该AI系统可在资源有限且患者需求高的场景中作为DXA的替代方案用于骨质疏松筛查。

局限性

  • 原文未报告局限性。

以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。

原文

INTRODUCTION: Dual-energy X-ray absorptiometry (DXA) is the standard method for assessing areal bone mineral density (aBMD), diagnosing osteoporosis, and predicting fracture risk. However, DXA's availability is limited in resource-poor areas. This study aimed to develop an artificial intelligence (AI) system capable of estimating aBMD from standard radiographs. METHODS: The study was part of the Vietnam Osteoporosis Study, a prospective population-based research involving 3783 participants aged 18 years and older. A total of 7060 digital radiographs of the frontal pelvis and lateral spine were taken using the FCR Capsula XLII system (Fujifilm Corp., Tokyo, Japan). aBMD at the femoral neck and lumbar spine was measured with DXA (Hologic Horizon, Hologic Corp., Bedford, MA, USA). An ensemble of seven deep-learning models was used to analyze the X-rays and predict bone mineral density, termed "xBMD". RESULTS: The correlation between xBMD and aBMD was evaluated using Pearson's correlation coefficients. The correlation between xBMD and aBMD at the femoral neck was strong ( r = 0.90; 95% CI, 0.88-0.91), and similarly high at the lumbar spine ( r = 0.87; 95% CI, 0.85-0.88). This correlation remained consistent across different age groups and genders. The AI system demonstrated excellent performance in identifying individuals at high risk for hip fractures, with area under the ROC curve (AUC) values of 0.96 (95% CI, 0.95-0.98) at the femoral neck and 0.97 (95% CI, 0.96-0.99) at the lumbar spine. CONCLUSIONS: These findings indicate that AI can accurately predict aBMD and identify individuals at high risk of fractures. This AI system could provide an efficient alternative to DXA for osteoporosis screening in settings with limited resources and high patient demand. An AI system developed to predict aBMD from X-rays showed strong correlations with DXA ( r = 0.90 at femoral neck; = r 0.87 at lumbar spine) and high accuracy in identifying individuals at high risk for fractures (AUC = 0.96 at femoral neck; AUC = 0.97 at lumbar spine).

来源:Osteoporos Int,查看原文。版权归原作者所有。

引用

  1. Nguyen HG, Nguyen DT, Tran TS, et al. Artificial intelligence system for predicting areal bone mineral density from plain X-rays. Osteoporos Int. 2025. PMID: 40864252. doi:10.1007/s00198-025-07634-7

供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。