基于深度学习分割模型经胸部CT评估肱骨近端体积骨密度的年龄与性别相关变化
本研究开发了基于nnU-Net的深度学习流程,在2675名成人胸部CT上自动分割肱骨近端并量化体积骨密度(vBMD),生成性别特异性百分位曲线。男性肱骨近端vBMD自成年早期近似线性下降;女性在约40-45岁出现明显拐点后各百分位同步陡降。肱骨近端与腰椎vBMD相关性低至中等且50岁后减弱,腰椎测量不能可靠替代肱骨BMD。
要点
- 深度学习分割肱骨近端精度高:DSC 98.42±0.20%、IoU 96.89±0.42%。
- 男性肱骨近端vBMD自成年早期近似线性下降;女性约40-45岁后加速下降。
- 女性腰椎vBMD下降早于肱骨近端,两者相关性低至中等且50岁后减弱。
核心结论
- 研究提出一种从胸部CT自动量化肱骨近端vBMD的新方法,揭示性别特异性衰老模式。
- 男性肱骨vBMD线性下降,女性则经历更早的加速丢失。
- 女性肱骨vBMD峰值出现晚于腰椎,脊柱测量不能可靠替代肱骨BMD。
研究设计与样本
- 开发基于nnU-Net的深度学习流程,自动分割2675名成人胸部CT上的肱骨近端。
- 用Dice相似系数(DSC)、交并比(IoU)、95百分位Hausdorff距离(95HD)和平均对称表面距离(ASSD)评估分割性能。
- 对每名受试者量化体模校准的vBMD-总、小梁和BMAT校正小梁vBMD。
- 用广义加性模型(GAMLSS)建模年龄相关分布,生成性别特异性P3-P97百分位曲线。
- 在1460名个体中测量腰椎vBMD用于相关性分析。
主要发现
- 分割高度准确:DSC 98.42±0.20%、IoU 96.89±0.42%、95HD 1.12±0.37 mm、ASSD 0.94±0.31 mm。
- 男性总、小梁和BMAT校正小梁vBMD自成年早期近似线性下降。
- 女性在约40-45岁出现明显拐点:此前数值稳定或略升,之后所有百分位陡峭同步下降,提示绝经相关加速丢失。
- 女性腰椎vBMD下降早于肱骨近端。
- 肱骨近端与腰椎vBMD相关性总体低至中等,50岁后减弱。
局限性
- 原文未报告局限性
以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。
原文
UNLABELLED: Accurate assessment of proximal humeral volumetric bone mineral density (vBMD) is essential for surgical planning in shoulder pathology. However, age-related changes in proximal humeral vBMD remain poorly characterized. This study developed a deep learning-based method to assess proximal humeral vBMD and identified sex-specific age-related changes. It also demonstrated that lumbar spine vBMD is not a valid substitute. PURPOSE: This study aimed to develop a deep learning-based method for proximal humeral vBMD assessment and to investigate its age- and sex-related changes, as well as its correlation with lumbar spine vBMD. METHODS: An nnU-Net-based deep learning pipeline was developed to automatically segment the proximal humerus on chest CT scans from 2,675 adults. Segmentation performance was assessed using the Dice Similarity Coefficient (DSC), Intersection over Union (IoU), 95th-percentile Hausdorff Distance (95HD), and Average Symmetric Surface Distance (ASSD). Phantom-calibrated vBMD-total, trabecular, and BMAT-corrected trabecular-was quantified for each subject. Age-related distributions were modeled with generalized additive models for location, scale, and shape (GAMLSS) to generate sex-specific P3-P97 percentile curves. Lumbar spine vBMD was measured in 1460 individuals for correlation analysis. RESULTS: Segmentation was highly accurate (DSC 98.42 ± 0.20%; IoU 96.89 ± 0.42%; 95HD 1.12 ± 0.37 mm; ASSD 0.94 ± 0.31 mm). In males, total, trabecular, and BMAT-corrected trabecular vBMD declined approximately linearly from early adulthood. In females, a pronounced inflection occurred at ~ 40-45 years: values were stable or slightly rising beforehand, then all percentiles dropped steeply and synchronously, indicating accelerated menopause-related loss. In females, vBMD declined earlier in the lumbar spine than in the proximal humerus. Correlations between proximal humeral and lumbar spine vBMD were low to moderate overall and weakened after age 50. CONCLUSION: We present a novel, automated method for quantifying proximal humeral vBMD from chest CT, revealing distinct, sex-specific aging patterns. Males' humeral vBMD declines linearly, while females experience an earlier, accelerated loss. Moreover, the peak humeral vBMD in females occurs later than that of the lumbar spine, and spinal measurements cannot reliably substitute for humeral BMD in clinical assessment.
引用
- Li S, Tang C, Zhang H, et al. Age- and sex-related changes in proximal humeral volumetric BMD assessed via chest CT with a deep learning-based segmentation model. Osteoporos Int. 2025. PMID: 40879742. doi:10.1007/s00198-025-07671-2
供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。