Machine Learning for Opportunistic Screening for Osteoporosis from CT Scans of the Wrist and Forearm.
Machine Learning for Opportunistic Screening for Osteoporosis from CT Scans of the Wrist and Forearm.
复制标题
DOI：
10.3390/diagnostics12030691
复制
发表时间：
2022-03-11
期刊：
影响因子：
--
通讯作者：
De la Garza-Ramos C
中科院分区：
文献类型：
--
作者：
Sebro R;De la Garza-Ramos C
背景：我们研究了是否可以使用机器学习通过手腕/前臂的计算机断层扫描 (CT) 扫描来进行骨质疏松症的机会性筛查。方法：对 196 名 50 岁或以上的患者进行回顾性研究，这些患者在 12 个月内接受了腕部/前臂 CT 扫描和双能 X 射线骨密度测定 (DEXA) 扫描。对前臂、腕骨和掌骨进行体积分割，以获得每个骨骼的平均 CT 衰减。计算了每个腕/前臂骨的 CT 衰减的相关性及其与 DEXA 测量值的相关性。该研究分为训练/验证 (n = 96) 和测试 (n = 100) 数据集。在测试数据集中评估多变量支持向量机 (SVM) 的性能，并与桡骨轴远端三分之一（半径 33%）的 CT 衰减进行比较。结果：手腕/前臂骨的每个 CT 衰减与 DEXA 测量值之间存在正相关。 170.2 Hounsfield 单位的阈值钩骨 CT 衰减对于识别骨质疏松症患者的敏感性为 69.2%，特异性为 77.1%。径向基函数 (RBF) 核 SVM (AUC = 0.818) 是预测骨质疏松症的最佳方法，其 AUC 高于其他模型，并且优于半径 33% (AUC = 0.576) (p = 0.020)。结论：可以使用手腕/前臂 CT 扫描对骨质疏松症进行机会性筛查。多变量机器学习技术（例如带有 RBF 内核的 SVM）使用来自多个骨骼的数据比使用单个骨骼的 CT 衰减更准确。
Background: We investigated whether opportunistic screening for osteoporosis can be done from computed tomography (CT) scans of the wrist/forearm using machine learning. Methods: A retrospective study of 196 patients aged 50 years or greater who underwent CT scans of the wrist/forearm and dual-energy X-ray absorptiometry (DEXA) scans within 12 months of each other was performed. Volumetric segmentation of the forearm, carpal, and metacarpal bones was performed to obtain the mean CT attenuation of each bone. The correlations of the CT attenuations of each of the wrist/forearm bones and their correlations to the DEXA measurements were calculated. The study was divided into training/validation (n = 96) and test (n = 100) datasets. The performance of multivariable support vector machines (SVMs) was evaluated in the test dataset and compared to the CT attenuation of the distal third of the radial shaft (radius 33%). Results: There were positive correlations between each of the CT attenuations of the wrist/forearm bones, and with DEXA measurements. A threshold hamate CT attenuation of 170.2 Hounsfield units had a sensitivity of 69.2% and a specificity of 77.1% for identifying patients with osteoporosis. The radial-basis-function (RBF) kernel SVM (AUC = 0.818) was the best for predicting osteoporosis with a higher AUC than other models and better than the radius 33% (AUC = 0.576) (p = 0.020). Conclusions: Opportunistic screening for osteoporosis could be performed using CT scans of the wrist/forearm. Multivariable machine learning techniques, such as SVM with RBF kernels, that use data from multiple bones were more accurate than using the CT attenuation of a single bone.
登录
查看更多内容
影响因子：
6.2
作者：
O'Neill, TW;Lunt, M;Reeve, J
通讯作者：
Reeve, J
影响因子：
1.9
作者：
Markolf, KL;Dunbar, AM;Hannani, K
通讯作者：
Hannani, K
DOI：
10.1007/s11548-019-01933-1
发表时间：
2019-05-01
影响因子：
3
作者：
Mehta, Samir D.;Sebro, Ronnie
通讯作者：
Sebro, Ronnie
影响因子：
2.5
作者：
Fedorov, Andriy;Beichel, Reinhard;Kalpathy-Cramer, Jayashree;Finet, Julien;Fillion-Robin, Jean-Christophe;Pujol, Sonia;Bauer, Christian;Jennings, Dominique;Fennessy, Fiona;Sonka, Milan;Buatti, John;Aylward, Stephen;Miller, James V.;Pieper, Steve;Kikinis, Ron
通讯作者：
Kikinis, Ron
DOI：
10.1002/jbmr.3383
发表时间：
2018-05
期刊：
Journal of bone and mineral research : the official journal of the American Society for Bone and Mineral Research
影响因子：
--
作者：
Lee SJ;Graffy PM;Zea RD;Ziemlewicz TJ;Pickhardt PJ
通讯作者：
Pickhardt PJ