Luan Anna, Maan Zeshaan, Lin Kun-Yi, Yao Jeffrey
Division of Plastic and Reconstructive Surgery, Department of Surgery, Stanford University School of Medicine, Stanford, CA.
Department of Orthopedics, Tri-Service General Hospital, National Defense Medical Center, Taipei, Taiwan, Republic of China.
J Hand Surg Am. 2025 Jan;50(1):43-50. doi: 10.1016/j.jhsa.2024.09.008. Epub 2024 Nov 16.
Fragility fractures associated with osteoporosis and osteopenia are a common cause of morbidity and mortality. Current methods of diagnosing low bone mineral density require specialized dual x-ray absorptiometry (DXA) scans. Plain hand radiographs may have utility as an alternative screening tool, although optimal diagnostic radiographic parameters are unknown, and measurement is prone to human error. The aim of the present study was to develop and validate an artificial intelligence algorithm to screen for osteoporosis and osteopenia using standard hand radiographs.
A cohort of patients with both a DXA scan and a plain hand radiograph within 12 months of one another was identified. Hand radiographs were labeled as normal, osteopenia, or osteoporosis based on corresponding DXA hip T-scores. A deep learning algorithm was developed using the ResNet-50 framework and trained to predict the presence of osteoporosis or osteopenia on hand radiographs using labeled images. The results from the algorithm were validated using a separate balanced validation set, with the calculation of sensitivity, specificity, accuracy, and receiver operating characteristic curve using definitions from corresponding DXA scans as the reference standard.
There was a total of 687 images in the normal category, 607 images in the osteopenia category, and 130 images in the osteoporosis category for a total of 1,424 images. When predicting low bone density (osteopenia or osteoporosis) versus normal bone density, sensitivity was 88.5%, specificity was 65.4%, overall accuracy was 80.8%, and the area under the curve was 0.891, at the standard threshold of 0.5. If optimizing for both sensitivity and specificity, at a threshold of 0.655, the model achieved a sensitivity of 84.6% at a specificity of 84.6%.
The findings represent a possible step toward more accessible, cost-effective, automated diagnosis and therefore earlier treatment of osteoporosis/osteopenia.
TYPE OF STUDY/LEVEL OF EVIDENCE: Diagnostic II.
与骨质疏松症和骨质减少相关的脆性骨折是发病和死亡的常见原因。目前诊断低骨密度的方法需要专门的双能X线吸收法（DXA）扫描。普通手部X线片可能作为一种替代筛查工具，尽管最佳诊断X线参数尚不清楚，且测量容易出现人为误差。本研究的目的是开发并验证一种人工智能算法，以使用标准手部X线片筛查骨质疏松症和骨质减少。
确定一组在12个月内同时进行了DXA扫描和普通手部X线片检查的患者。根据相应的DXA髋部T值，将手部X线片标记为正常、骨质减少或骨质疏松。使用ResNet-50框架开发了一种深度学习算法，并使用标记图像进行训练，以预测手部X线片上骨质疏松症或骨质减少的存在。算法结果使用单独的平衡验证集进行验证，以相应DXA扫描的定义作为参考标准计算敏感性、特异性、准确性和受试者工作特征曲线。
正常类别共有687张图像，骨质减少类别有607张图像，骨质疏松类别有130张图像，共计1424张图像。在预测低骨密度（骨质减少或骨质疏松）与正常骨密度时，在标准阈值0.5时，敏感性为88.5%，特异性为65.4%，总体准确性为80.8%，曲线下面积为0.891。如果同时优化敏感性和特异性，在阈值0.655时，模型的敏感性为84.6%，特异性为84.6%。
这些发现代表了朝着更易获得、更具成本效益的自动化诊断以及因此更早治疗骨质疏松症/骨质减少迈出的可能一步。
研究类型/证据水平：诊断性研究II级。
