Pickhardt Perry J, Nguyen Thang, Perez Alberto A, Graffy Peter M, Jang Samuel, Summers Ronald M, Garrett John W
Department of Radiology, University of Wisconsin School of Medicine & Public Health, E3/311 Clinical Science Center, 600 Highland Ave, Madison, WI 53792-3252 (P.J.P., T.N., A.A.P., P.M.G., S.J., J.W.G.); and Imaging Biomarkers and Computer-Aided Diagnosis Laboratory, Department of Radiology and Imaging Sciences, National Institutes of Health Clinical Center, Bethesda, Md (R.M.S.).
Radiol Artif Intell. 2022 Aug 31;4(5):e220042. doi: 10.1148/ryai.220042. eCollection 2022 Sep.
To develop, test, and validate a deep learning (DL) tool that improves upon a previous feature-based CT image processing bone mineral density (BMD) algorithm and compare it against the manual reference standard.
This single-center, retrospective, Health Insurance Portability and Accountability Act-compliant study included manual L1 trabecular Hounsfield unit measurements from abdominal CT scans in 11 035 patients (mean age, 58 years ± 12 [SD]; 6311 women) as the reference standard. Automated level selection and L1 trabecular region of interest (ROI) placement were then performed in this CT cohort with both a previously validated feature-based image processing tool and a new DL tool. Overall technical success rates and agreement with the manual reference standard were assessed.
The overall success rate of the DL tool in this heterogeneous patient cohort was significantly higher than that of the older image processing BMD algorithm (99.3% vs 89.4%, < .001). Using this DL tool, the closest median Hounsfield unit values for single-, three-, and seven-slice vertebral ROIs were within 5% of the manual reference standard Hounsfield unit values in 35.1%, 56.9%, and 85.8% of scans; within 10% in 56.6%, 75.6%, and 92.9% of scans; and within 25% in 76.5%, 89.3%, and 97.1% of scans, respectively. Trade-offs in sensitivity and specificity for osteoporosis assessment were observed from the single-slice approach (sensitivity, 39.4%; specificity, 98.3%) to the minimum value of the multislice approach (for seven contiguous slices; sensitivity, 71.3% and specificity, 94.6%).
The new DL BMD tool demonstrated a higher success rate than the older feature-based image processing tool, and its outputs can be targeted for higher specificity or sensitivity for osteoporosis assessment. CT, CT-Quantitative, Abdomen/GI, Skeletal-Axial, Spine, Deep Learning, Machine Learning © RSNA, 2022.
开发、测试并验证一种深度学习（DL）工具，该工具改进了先前基于特征的CT图像处理骨密度（BMD）算法，并将其与手动参考标准进行比较。
这项单中心、回顾性、符合《健康保险流通与责任法案》的研究纳入了11035例患者（平均年龄58岁±12[标准差]；6311例女性）腹部CT扫描的手动L1小梁Hounsfield单位测量值作为参考标准。然后，在这个CT队列中，使用先前验证的基于特征的图像处理工具和新的DL工具进行自动水平选择和L1小梁感兴趣区（ROI）放置。评估总体技术成功率以及与手动参考标准的一致性。
在这个异质性患者队列中，DL工具的总体成功率显著高于旧的图像处理BMD算法（99.3%对89.4%，<0.001）。使用该DL工具，单层面、三层面和七层面椎体ROI最接近的中位数Hounsfield单位值在35.1%、56.9%和85.8%的扫描中分别在手动参考标准Hounsfield单位值的5%以内；在56.6%、75.6%和92.9%的扫描中在10%以内；在76.5%、89.3%和97.1%的扫描中分别在25%以内。从单层面方法（敏感性39.4%；特异性98.3%）到多层面方法的最小值（七个连续层面；敏感性71.3%，特异性94.6%），观察到骨质疏松评估在敏感性和特异性方面的权衡。
新的DL BMD工具显示出比旧的基于特征的图像处理工具更高的成功率，其输出可针对骨质疏松评估的更高特异性或敏感性。CT、CT定量、腹部/胃肠道、骨骼-轴位、脊柱、深度学习、机器学习 © RSNA，2022年
