文献速递骨肌技术与安全CTDR

深度学习在椎体骨折检测中的应用:受试者水平与椎体水平方法的系统综述与荟萃分析

Deep Learning in Vertebral Fracture Detection: Systematic Review and Meta-analysis of Subject- vs. Vertebra-Level Approaches.
PubMed 文献 · Acad Radiol · 2025-12-06

本系统综述与荟萃分析纳入36项研究(96,956例患者、171,552幅图像),评估深度学习检测椎体骨折的准确性。受试者水平合并敏感度84%、特异度91%(AUC 0.94);椎体水平敏感度80%、特异度97%(AUC 0.96)。外部验证降低敏感度但保持高特异度,X线片偏好受试者水平筛查,CT支持椎体水平精准定位。

要点

  • 受试者水平模型敏感度较高(84%),适合筛查/分诊;椎体水平模型特异度更高(97%)且能精准定位。
  • 外部验证会降低敏感度但保持高特异度;X线片偏好受试者水平筛查,CT支持椎体水平精准诊断。
  • QUADAS-AI评估显示61%的研究存在患者选择偏倚高风险,为最常见的偏倚来源。

核心结论

  • 深度学习模型检测椎体骨折准确性高;受试者水平方法因敏感度较高适合筛查/分诊,椎体水平方法因特异度更高且能精准定位适合确诊和治疗规划;临床使用应根据任务和情境匹配模型粒度。

研究设计与样本

  • PRISMA合规的系统综述与荟萃分析(PROSPERO CRD42024523301),检索5个数据库至2025年2月,纳入36项英文研究(96,956例患者、171,552幅图像),其中28项提供113个列联表;采用QUADAS-AI评估偏倚风险,分层汇总ROC模型合并敏感度、特异度和AUC。

诊断标准与关键数值

  • 受试者水平合并敏感度84%、特异度91%、AUC 0.94;椎体水平合并敏感度80%、特异度97%、AUC 0.96。

临床应用与阅片要点

  • 作者认为受试者水平方法适合筛查/分诊,椎体水平方法适合确诊和治疗规划;临床使用应将模型粒度与预期任务和情境相匹配。

局限性

  • 方法学质量在各研究间存在差异;QUADAS-AI识别出患者选择偏倚为最常见的偏倚来源,见于61%的研究。
  • 外部验证降低敏感度但保持高特异度。
  • 性能因成像方式和数据来源而异。

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: To provide a context-aware evaluation of deep learning algorithms for vertebral fracture detection by disentangling subject-level from vertebra-level approaches, quantifying the influence of key technical and methodological factors, and generating evidence to guide task-specific clinical use and standardized reporting. MATERIALS AND METHODS: In this PRISMA‑compliant review (PROSPERO CRD42024523301), five databases were searched to February 2025 for English‑language studies reporting accuracy metrics. Risk of bias was assessed with QUADAS‑AI. Hierarchical summary ROC models pooled sensitivity, specificity, and AUC for each analytical level; subgroup analysis and meta‑regression explored heterogeneity by test‑set origin, imaging modality, and scanner vendor.

RESULTS: 36 studies (96,956 patients; 171,552 images) were eligible; 28 provided 113 contingency tables. Pooled subject‑level sensitivity/specificity was 84%/91% (AUC 0.94); vertebra‑level 80%/97% (AUC 0.96). Subject-level models prioritized sensitivity, whereas vertebra-level models achieved higher specificity with precise localization. External validation lowered sensitivity, yet retained high specificity. Radiographs favored subject‑level screening, whereas CT supported vertebra‑level precision. Multi‑vendor datasets improved subject‑level sensitivity, and single‑vendor datasets enhanced vertebra‑level specificity. Methodological quality varied across studies; QUADAS-AI identified high risk of patient selection bias-the most commonly identified bias source-in 61% of studies.

CONCLUSION: Deep learning models demonstrate high accuracy for vertebral fracture detection; subject-level approaches are suited to screening/triage due to higher sensitivity, whereas vertebra-level approaches offer higher specificity and precise localization for confirmatory diagnosis and treatment planning. Given performance variability across imaging modality and data sources, clinical use should align model granularity with the intended task and context.

来源:Acad Radiol,查看原文。版权归原作者所有。

引用

  1. Hosseini-Siyanaki MR, Ahmadi B, Sagdic HS, et al. Deep Learning in Vertebral Fracture Detection: Systematic Review and Meta-analysis of Subject- vs. Vertebra-Level Approaches. Acad Radiol. 2025. PMID: 41353070. doi:10.1016/j.acra.2025.11.023

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。