Uemura Keisuke, Otake Yoshito, Takashima Kazuma, Hamada Hidetoshi, Imagama Takashi, Takao Masaki, Sakai Takashi, Sato Yoshinobu, Okada Seiji, Sugano Nobuhiko
Department of Orthopaedic Medical Engineering, Graduate School of Medicine, Osaka University, Suita, Japan.
Division of Information Science, Graduate School of Science and Technology, Nara Institute of Science and Technology, Ikoma, Japan.
Bone Joint Res. 2023 Sep 20;12(9):590-597. doi: 10.1302/2046-3758.129.BJR-2023-0115.R1.
This study aimed to develop and validate a fully automated system that quantifies proximal femoral bone mineral density (BMD) from CT images.
The study analyzed 978 pairs of hip CT and dual-energy X-ray absorptiometry (DXA) measurements of the proximal femur (DXA-BMD) collected from three institutions. From the CT images, the femur and a calibration phantom were automatically segmented using previously trained deep-learning models. The Hounsfield units of each voxel were converted into density (mg/cm). Then, a deep-learning model trained by manual landmark selection of 315 cases was developed to select the landmarks at the proximal femur to rotate the CT volume to the neutral position. Finally, the CT volume of the femur was projected onto the coronal plane, and the areal BMD of the proximal femur (CT-aBMD) was quantified. CT-aBMD correlated to DXA-BMD, and a receiver operating characteristic (ROC) analysis quantified the accuracy in diagnosing osteoporosis.
CT-aBMD was successfully measured in 976/978 hips (99.8%). A significant correlation was found between CT-aBMD and DXA-BMD (r = 0.941; p < 0.001). In the ROC analysis, the area under the curve to diagnose osteoporosis was 0.976. The diagnostic sensitivity and specificity were 88.9% and 96%, respectively, with the cutoff set at 0.625 g/cm.
Accurate DXA-BMD measurements and diagnosis of osteoporosis were performed from CT images using the system developed herein. As the models are open-source, clinicians can use the proposed system to screen osteoporosis and determine the surgical strategy for hip surgery.
本研究旨在开发并验证一种能从CT图像定量分析股骨近端骨密度（BMD）的全自动系统。
本研究分析了从三个机构收集的978对近端股骨的髋部CT和双能X线吸收法（DXA）测量值（DXA-BMD）。利用先前训练的深度学习模型，从CT图像中自动分割出股骨和校准体模。将每个体素的亨氏单位转换为密度（mg/cm）。然后，开发了一个通过对315例病例进行手动地标选择训练的深度学习模型，以选择股骨近端的地标，将CT容积旋转到中立位置。最后，将股骨的CT容积投影到冠状面上，定量分析近端股骨的面积骨密度（CT-aBMD）。CT-aBMD与DXA-BMD相关，并通过受试者操作特征（ROC）分析来量化诊断骨质疏松症的准确性。
978例髋部中有976例（99.8%）成功测量了CT-aBMD。CT-aBMD与DXA-BMD之间存在显著相关性（r = 0.941；p < 0.001）。在ROC分析中，诊断骨质疏松症的曲线下面积为0.976。诊断敏感性和特异性分别为88.9%和96%，临界值设定为0.625 g/cm。
使用本文开发的系统从CT图像中进行了准确的DXA-BMD测量和骨质疏松症诊断。由于这些模型是开源的，临床医生可以使用所提出的系统来筛查骨质疏松症并确定髋关节手术的手术策略。
