文献速递骨肌胸部腹部CT

深度学习在常规胸腹部CT上机会性检出椎体骨折的系统综述与Meta分析

Deep Learning for Opportunistic Vertebral Fracture Detection on Routine Thoraco-abdominal Computed Tomography: A Systematic Review and Hierarchical Summary Receiver Operating Characteristic Meta-analysis of Patient-level Diagnostic Test Accuracy.
PubMed 文献 · Acad Radiol · 2026-06-29

该系统综述纳入7项回顾性研究、11615例患者,评估深度学习在常规胸腹部CT上检出≥1个Genant半定量2–3级椎体骨折的效能。汇总敏感度为0.83,特异度为0.92,阳性似然比10.44,阴性似然比0.19,诊断比值比55.98。证据仍属早期、小样本、回顾性且异质性较大,支持开展前瞻性评估而非常规部署。

要点

  • 深度学习特异度较高,适合作为读片提醒或规则内辅助,不宜单独排除椎体骨折
  • 目标病变为≥1个Genant半定量2–3级椎体骨折,报告时可关注该分级病例
  • 敏感度异质性大于特异度,不同中心病例构成或阈值差异可能影响表现

核心结论

  • 深度学习对常规CT患者层面椎体骨折检出具有高特异度和中高敏感度
  • 当前证据支持将其作为读片提醒、分诊或规则内辅助工具进行前瞻性评估,而非常规部署或单独排除

研究设计与样本

  • 系统综述与Meta分析,遵循PRISMA-DTA,检索MEDLINE、Embase和Web of Science
  • 纳入7项回顾性研究,样本量合计11615例,发表时间为2020至2025年
  • 多数队列为机会性筛查或骨质疏松相关人群,7项中5项使用了外部验证
  • 采用QUADAS-2评估偏倚风险,并对人工智能相关报告完整性进行描述性评估
  • 采用双变量随机效应/层次汇总受试者工作特征模型,并进行基于限制条件的敏感性分析

关键影像表现/征象

  • 所有研究均评估独立运行的深度学习检测≥1个Genant半定量2–3级骨折的椎体

诊断标准与关键数值

  • 汇总敏感度为0.83,95%置信区间为0.73–0.90
  • 汇总特异度为0.92,95%置信区间为0.90–0.94
  • 阳性似然比为10.44,阴性似然比为0.19,诊断比值比为55.98
  • HSROC不对称提示病例构成或阈值存在差异,敏感度变异大于特异度

临床应用与阅片要点

  • 可用于常规胸腹部CT的椎体骨折机会性筛查辅助,帮助识别可能漏诊的骨折病例
  • 适合作为读片提醒或分诊工具,阳性结果应结合常规影像判读确认
  • 不适合单独用于排除椎体骨折,阴性结果不能完全排除病变
  • 偏倚风险为低至中等,但人工智能相关报告完整性不足,临床应用需关注研究报告质量

局限性

  • 证据仍属早期、样本量较小、均为回顾性研究且异质性较大
  • 人工智能相关报告完整性不完整,可能影响研究可比性和可重复性

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)。

英文原文(摘要)· 点击展开

RATIONALE AND OBJECTIVES: Vertebral fractures (VFs) are common, clinically important, and often missed on routine chest or abdominal computed tomography (CT). Deep learning (DL) may support opportunistic case-finding.

MATERIALS AND METHODS: Following the Preferred Reporting Items for Systematic Reviews and Meta-Analyses of Diagnostic Test Accuracy Studies (PRISMA-DTA), we searched MEDLINE, Embase, and Web of Science. Risk of bias was assessed using Quality Assessment of Diagnostic Accuracy Studies 2 (QUADAS-2), and artificial intelligence (AI)-specific reporting was assessed descriptively. We fitted bivariate random-effects/hierarchical summary receiver operating characteristic (HSROC) models and conducted restriction-based sensitivity analyses.

RESULTS: Seven retrospective studies (2020-2025; N = 11,615) were included. Most cohorts were opportunistic or osteoporosis-related; 5/7 used external validation. All evaluated stand-alone DL for detecting ≥1 vertebra with Genant semiquantitative (SQ) grade 2-3 fracture. Pooled sensitivity was 0.83 (95% confidence interval [CI]: 0.73-0.90) and specificity was 0.92 (95% CI: 0.90-0.94). The positive likelihood ratio was 10.44, negative likelihood ratio was 0.19, and diagnostic odds ratio was 55.98. Sensitivity varied more than specificity, and HSROC asymmetry suggested differences in case mix or thresholds. Risk of bias was low to moderate, and AI-specific reporting was incomplete.

CONCLUSION: DL showed high specificity and moderate-to-high sensitivity for patient-level VF detection on routine CT. However, evidence remains early, small, retrospective, and heterogeneous. Current findings support prospective evaluation of DL as a reader-alert, triage, or rule-in aid, rather than routine deployment or stand-alone exclusion of VF.

来源:Acad Radiol,查看原文。版权归原作者所有。

引用

  1. Gete, Idris, Ayele, et al. Deep Learning for Opportunistic Vertebral Fracture Detection on Routine Thoraco-abdominal Computed Tomography: A Systematic Review and Hierarchical Summary Receiver Operating Characteristic Meta-analysis of Patient-level Diagnostic Test Accuracy. Acad Radiol. 2026. PMID: 42373383. doi:10.1016/j.acra.2026.06.007

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。