基于深度学习利用胸部低剂量CT与腰椎CT自动机会性骨质疏松筛查:多中心队列研究
本回顾性多中心队列研究纳入5家医院4305例接受胸部低剂量CT和腰椎CT扫描的患者,采用4种卷积神经网络自动分割椎体、提取感兴趣区并计算骨密度,以定量CT为参考标准。深度学习法测得的骨密度与定量CT高度相关(R²=0.970-0.997),诊断骨质疏松和低骨密度的AUC达0.993-1.000,在不同厂商CT设备上表现良好。
要点
- 深度学习法自动测量T12-L2椎体骨密度,与定量CT高度相关(R²=0.970-0.997)。
- 诊断骨质疏松AUC为0.993-1.000,敏感度96.55-100.00%,特异度92.75-100.00%。
- 诊断低骨密度( vs 正常骨密度)AUC为0.994-1.000,敏感度92.11-100.00%,特异度93.83-100.00%。
核心结论
- 该深度学习方法利用胸部低剂量CT和腰椎CT实现自动骨质疏松筛查,诊断性能高,且在不同厂商和不同医院的CT设备上表现良好。
研究设计与样本
- 回顾性多中心队列研究,纳入5家医院4305例接受胸部低剂量CT和腰椎CT扫描的患者,数据来自9台CT设备,分为训练集、验证集和测试集1-5(样本量分别为1891、806、229、418、508、229和224例)。采用4种卷积神经网络(3D VB-Net和SCN用于椎体分割,3D VB-Net用于感兴趣区提取,DenseNet和ResNet用于骨密度计算)对目标椎体T12-L2进行分析,以定量CT测得的骨密度值为参考标准。
诊断标准与关键数值
- 以定量CT为参考标准,120 kV卷积神经网络测得的骨密度与120 kV定量CT高度相关(R²=0.970-0.997,P<0.001),平均误差0.57-2.45 mg/cm³,95%一致性界限-3.70-5.68 mg/cm³。诊断骨质疏松的AUC为0.993-1.000,敏感度96.55-100.00%,特异度92.75-100.00%;诊断低骨密度( vs 正常骨密度)的AUC为0.994-1.000,敏感度92.11-100.00%,特异度93.83-100.00%。
临床应用与阅片要点
- 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)。
英文原文(摘要)· 点击展开
RATIONALE AND OBJECTIVES: To propose a deep learning (DL) method for automatically measuring bone mineral density (BMD) and validating its diagnostic performance for opportunistic osteoporosis screening using low-dose chest computed tomography (LDCT) and lumbar CT scans across CT scanners from different manufacturers and hospitals.
MATERIALS AND METHODS: This retrospective study involved 4305 patients who underwent chest LDCT and lumbar CT scans at five hospitals. Patient data were collected from nine CT scanners and divided into training, validation, and test sets 1-5 (1891, 806, 229, 418, 508, 229, and 224). Four convolutional neural networks (CNNs) were employed for automated vertebral body (VB) segmentation (3D VB-Net and SCN), region of interest extraction (3D VB-Net), and BMD calculation (DenseNet and ResNet) of the target VBs (T12-L2). The BMD values derived from quantitative CT (QCT) were identified as the reference standard. Linear regression and Bland-Altman analyses were used to compare BMD values between 120 kV QCT and 120 kV CNNs. Receiver operating characteristic curve analysis was performed to assess the diagnostic accuracy of the 120 kV CNNs in detecting osteoporosis and low BMD from normal BMD.
RESULTS: The BMD values of 120 kV CNNs showed an excellent correlation (R² = 0.970-0.997, P < 0.001) and good agreement (mean error, 0.57-2.45 mg/cm³; 95% limits of agreement, -3.70-5.68 mg/cm³) with 120 kV QCT. The areas under the curve of the 120 kV CNNs in diagnosing osteoporosis and low BMD from normal BMD were 0.993-1.000 and 0.994-1.000, with a sensitivity of 96.55-100.00% and 92.11-100.00%, and a specificity of 92.75-100.00% and 93.83-100.00%, respectively.
CONCLUSION: This DL method achieved high diagnostic performance for automatic osteoporosis screening using chest LDCT and lumbar CT scans and performed well across CT scanners from different manufacturers and hospitals.
引用
- Li Y, Zhu Y, Zhang Y, et al. Deep Learning-based Automated Opportunistic Osteoporosis Screening Using Chest LDCT and Lumbar CT: A Multicenter Cohort Study. Acad Radiol. 2025. PMID: 41188157. doi:10.1016/j.acra.2025.09.015
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。