机器学习利用胸部CT多骨骼部位CT值预测骨量减少/骨质疏松
本研究回顾性纳入364例有胸部CT和6个月内DXA的患者,对肋骨、胸椎、胸骨、锁骨进行三维分割获取平均CT值,采用LASSO、弹性网络、岭回归和SVM(RBF核)预测骨量减少/骨质疏松。SVM的AUC最高(0.864),优于LASSO、弹性网络和岭回归(P=0.011),但不优于T12 CT值阈值(P=0.060)。
要点
- 胸部CT上肋骨、胸椎、胸骨和锁骨的平均CT值可单独或联合预测骨密度和骨量减少/骨质疏松。
- T12 CT值阈值170.2 HU诊断骨量减少/骨质疏松的AUC为0.702,T4阈值192.1 HU的AUC为0.757。
- SVM(RBF核)模型AUC最高(0.864),但未显著优于T12 CT值阈值(P=0.060)。
关键影像表现/征象
- 所有骨骼之间的CT值呈正相关(r>0.6,P<0.001)。
- 骨骼CT值与L1-L4 BMD T评分、全髋T评分和股骨颈T评分呈正相关(r>0.4,P<0.001)。
诊断标准与关键数值
- T12 CT值阈值170.2 HU诊断骨量减少/骨质疏松的AUC为0.702。
- T4 CT值阈值192.1 HU诊断骨量减少/骨质疏松的AUC为0.757。
- SVM(RBF核)模型AUC为0.864,优于LASSO(P=0.011)、弹性网络(P=0.011)和岭回归(P=0.011),但不优于T12 CT值阈值(P=0.060)。
临床应用与阅片要点
- 胸部CT上可机会性评估肋骨、胸椎、胸骨和锁骨CT值,辅助预测骨量减少/骨质疏松。
- T12和T4 CT值阈值可作为简单筛查指标,但SVM模型未显著优于T12阈值,需结合临床综合判断。
局限性
- 回顾性研究设计。
- 单中心研究。
- 样本量有限(共364例,测试集73例)。
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
PURPOSE: To use machine learning and the CT attenuation of all bones visible on chest CT scans to predict osteopenia/osteoporosis.
METHOD: We retrospectively evaluated 364 patients with CT scans of the chest, and Dual-energy X-ray absorptiometry (DXA) scans within 6 months of each other. Studies were performed between 01/01/2015 and 08/01/2021. Volumetric segmentation of the ribs, thoracic vertebrae, sternum, and clavicle was performed using 3D Slicer to obtain the mean CT attenuation of each bone. The study sample was randomly split into training/validation (80 %, n = 291 patients) and test (20 %, n = 73 patients) datasets. Univariate analyses were used to identify the optimal CT attenuation thresholds to diagnose osteopenia/osteoporosis. We used penalized multivariable logistic regression models including Least Absolute Shrinkage and Selection Operator (LASSO), Elastic Net, and Ridge regression, and Support Vector Machines (SVM) with radial basis functions (RBF) to predict osteopenia/osteoporosis and compared these results to the CT attenuation threshold at T12.
RESULTS: There were positive correlations between the CT attenuation between all bones (r > 0.6, P < 0.001 for all). There were positive correlations between CT attenuation of the bones and the L1-L4 BMD T-score, total hip T-score, and femoral neck T-scores (r > 0.4, P < 0.001 for all). A CT attenuation threshold of 170.2 Hounsfield units (HU) at T12 had an AUC of 0.702, while a threshold of 192.1 HU at T4 had an AUC of 0.757. The SVM with RBF had the highest AUC (AUC = 0.864) and was better than the LASSO (P = 0.011), Elastic Net (P = 0.011), Ridge regression (P = 0.011) but was not better than using the CT attenuation at T12 (P = 0.060).
CONCLUSIONS: The CT attenuation of the ribs, thoracic vertebra, sternum, and clavicle can be used individually and collectively to predict BMD and to predict osteopenia/osteoporosis.
引用
- Sebro, De la Garza-Ramos. Machine learning for the prediction of osteopenia/osteoporosis using the CT attenuation of multiple osseous sites from chest CT. Eur J Radiol. 2022. PMID: 35988394. doi:10.1016/j.ejrad.2022.110474
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。