使用人工智能在胸部CT上机会性筛查骨质疏松症
本研究利用人工智能在非增强胸部CT上测量所有胸椎和第一腰椎的衰减值,以双能X线吸收法(DXA)结果为分组依据,发现CT衰减值随年龄增长而下降,对骨质减少或骨质疏松风险具有预测和诊断效能,可机会性筛查高危人群。
要点
- CT衰减值每增加10 HU,骨质减少或骨质疏松风险分别降低32~44%和61~80%。
- 所有胸椎联合诊断效能高于单个椎体,鉴别正常与骨质减少或骨质疏松的AUC分别为0.831和0.972。
- 常规胸部CT结合人工智能可用于机会性筛查骨质减少或骨质疏松,不增加辐射剂量。
核心结论
- 常规胸部CT结合人工智能在机会性筛查骨质减少或骨质疏松方面具有重要价值,可快速筛查骨质疏松高危人群而不增加辐射剂量,从而减少骨质疏松性骨折的发生。
研究设计与样本
- 基于胸部CT图像,使用人工智能测量同期接受肺癌筛查CT和双能X线吸收法(DXA)检查患者的所有胸椎和第一腰椎的衰减值(HU),根据DXA结果分为正常组、骨质减少组和骨质疏松组,比较三组临床基线数据和衰减值,分析衰减值与骨密度值的相关性,并评估胸椎和第一腰椎衰减值对骨质减少或骨质疏松风险的预测能力和诊断效能。
主要发现
- 各胸椎和第一腰椎的CT值随年龄增长而下降,尤其在绝经后女性中。
- 经临床数据校正后,CT值每增加10 HU,骨质减少或骨质疏松的风险分别降低32~44%和61~80%。
- 所有胸椎联合诊断效能高于单个椎体,从正常组中识别骨质减少或骨质疏松的AUC分别为0.831和0.972。
关键数值与推荐
- CT值每增加10 HU,骨质减少风险降低32~44%,骨质疏松风险降低61~80%。
- 从正常组中识别骨质减少的AUC为0.831,识别骨质疏松的AUC为0.972。
临床怎么用
- 原文未据此给出推荐。
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
UNLABELLED: Osteoporosis has a high incidence and a low detection rate. If it is not detected in time, it will cause osteoporotic fracture and other serious consequences. This study showed that the attenuation values of vertebrae on chest CT could be used for opportunistic screening of osteoporosis. This will be beneficial to improve the detection rate of osteoporosis and reduce the incidence of adverse events caused by osteoporosis. INTRODUCTION: To explore the value of the attenuation values of all thoracic vertebrae and the first lumbar vertebra measured by artificial intelligence on non-enhanced chest CT to do osteoporosis screening. METHODS: On base of images of chest CT, using artificial intelligence (AI) to measure the attenuation values (HU) of all thoracic and the first vertebrae of patients who underwent CT examination for lung cancer screening and dual-energy X-ray absorptiometry (DXA) examination during the same period. The patients were divided into three groups: normal group, osteopenia group, and osteoporosis group according to the results of DXA. Clinical baseline data and attenuation values were compared among the three groups. The correlation between attenuation values and BMD values was analyzed, and the predictive ability and diagnostic efficacy of attenuation values of thoracic and first lumbar vertebrae on osteopenia or osteoporosis risk were further evaluated. RESULTS: CT values of each thoracic vertebrae and the first lumbar vertebrae decreased with age, especially in menopausal women and presented high predictive ability and diagnostic efficacy for osteopenia or osteoporosis. After clinical data correction, with every 10 HU increase of CT values, the risk of osteopenia or osteoporosis decreased by 32 ~ 44% and 61 ~ 80%, respectively. And the combined diagnostic efficacy of all thoracic vertebrae was higher than that of a single vertebra. The AUC of recognizing osteopenia or osteoporosis from normal group was 0.831and 0.972, respectively. CONCLUSIONS: The routine chest CT with AI is of great value in opportunistic screening for osteopenia or osteoporosis, which can quickly screen the population at high risk of osteoporosis without increasing radiation dose, thus reducing the incidence of osteoporotic fracture.
引用
- Yang J, Liao M, Wang Y, et al. Opportunistic osteoporosis screening using chest CT with artificial intelligence. Osteoporos Int. 2022. PMID: 35931902. doi:10.1007/s00198-022-06491-y
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。