Utilizing artificial intelligence to determine bone mineral density using spectral CT

• DOI: 10.1016/j.bone.2024.117321
• Publication Date: 2024-11-06T08:32:05Z
• Authors: Yali Li; Dan Jin; Yan Zhang; Wenhuan Li; Chenyu Jiang; Ming Ni; Nianxi Liao; Huishu Yuan
• Keywords: Dual layer; Dual purpose

Dual-energy computed tomography (DECT) has demonstrated the feasibility of using HAP-water to respond BMD changes without requiring dedicated software or calibration. Artificial intelligence (AI) been utilized for diagnosising osteoporosis in routine CT scans but rarely used DECT. This study investigated diagnostic performance an AI system screening DECT images with reference quantitative (QCT). prospective included 120 patients who underwent and QCT from August December 2023. Two convolutional neural networks, 3D RetinaNet U-Net, were employed automated vertebral body segmentation. The accuracy bone mineral density (BMD) measurement was assessed relative error (RME%). Linear regression Bland-Altman analyses performed compare values between manual systems those QCT. low evaluated receiver operating characteristic curve analysis. overall mean RME% - 15.93 ± 12.05 % 25.47 14.83 %, respectively. measurements achieved greater agreement results than (R2 = 0.973, 0.948, p < 0.001; errors, 23.27, 35.71 mg/cm3; 95 LoA, -9.72 56.26, -11.45 82.87 mg/cm3). areas under 0.979 0.933 detecting 0.980 0.991 BMD. could achieve relatively high on scans, providing great potential follow-up screening.