文献速递骨肌儿科影像DR

AI在儿童至青年脊柱侧弯EOS影像纵向监测中的准确性研究

AI-Based Longitudinal Scoliosis Monitoring on EOS Whole-Spine Radiographs in a Pediatric to Young Adult Cohort.
PubMed 文献 · Acad Radiol · 2026-07-07

本研究回顾性纳入29例5-25岁确诊脊柱侧弯患者共144张EOS全脊柱正位片,比较AI软件与两名专家手动测量Cobb角及冠状面平衡的一致性。结果显示AI与人工测量ICC为0.969-0.993,平均差异0.2°-0.7°及0.7 mm,识别侧弯进展准确率为90.9%。

要点

  • AI自动测量Cobb角与专家手动测量一致性极佳,可用于日常侧弯随访初筛。
  • AI识别侧弯进展(两次测量增大≥5°)准确率为90.9%,但仍有漏判可能需人工复核。
  • AI测量误差随时间无显著漂移,适合多时间点纵向监测。

核心结论

  • AI对Cobb角及冠状面平衡的测量与专家人工测量具有极佳的绝对一致性和纵向一致性。
  • AI识别脊柱侧弯进展(两次测量增大≥5°)的准确率为90.9%。
  • AI测量误差在连续随访检查中无显著时间漂移。

研究设计与样本

  • 回顾性单中心研究,纳入29例5-25岁确诊脊柱侧弯且有多 次随访检查的患者。
  • 共纳入144张前后位EOS全脊柱正位片。
  • 设备为EOS Imaging(法国巴黎)EOS成像系统。
  • 参考标准为两名专家读者手动测量Cobb角及冠状面平衡。
  • AI软件为IB Lab SQUIRREL(IB Lab GmbH,奥地利维也纳)商业软件。

关键影像表现/征象

  • 在冠状面EOS全脊柱正位片上自动识别并测量Cobb角。
  • 冠状面平衡测量平均差异为0.7 mm。

诊断标准与关键数值

  • AI与人工测量所有指标的组内相关系数为0.969-0.993。
  • AI与人工测量Cobb角平均差异为0.2°-0.7°。
  • AI与人工测量冠状面平衡平均差异为0.7 mm。
  • 侧弯进展定义为两次测量间Cobb角增大量≥5°。
  • AI识别侧弯进展的准确率为90.9%。

临床应用与阅片要点

  • AI自动Cobb角测量可用于脊柱侧弯随访中减少人工测量重复劳动。
  • 冠状面平衡自动测量差异仅0.7 mm,可作为报告中的常规参考指标。

局限性

  • 回顾性单中心研究,样本量较小,仅29例患者144张图像。
  • 仅纳入5-25岁确诊脊柱侧弯患者,结果外推到其他年龄段需谨慎。

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: Manual Cobb angle measurement can exhibit high interrater variability, potentially affecting scoliosis management decisions. This study aimed to examine the accuracy of an artificial intelligence (AI) software for automated Cobb angle measurement compared to manual assessments on coronal EOS (EOS Imaging, Paris, France) radiographs of the spine in a pediatric to young adult cohort.

MATERIALS & METHODS: In this retrospective single-center study we selected patients from 5-25 years with confirmed scoliosis and multiple follow-up exams. Cobb angles and coronal balance were measured on EOS radiographs: manually by two expert readers, representing the reference standard, and an AI-driven commercial software (IB Lab SQUIRREL, IB Lab GmbH, Vienna, Austria). Performance among readers and the AI was compared using mean differences, intraclass correlation coefficients (ICC), Pearson's correlation coefficients, Skillings-Mack and Bland-Altman analyses.

RESULTS: A total of 144 anteroposterior whole-spine EOS radiographs from 29 patients were included (median age 13 years, 8 male). The AI demonstrated excellent agreement with human readers for all measurements (ICCs 0.969-0.993). Mean differences were minimal: (0.2°-0.7°) for Cobb angles and 0.7 mm for coronal balance. Skillings-Mack analysis confirmed no significant temporal drift in AI measurement errors across sequential examinations (all p > 0.05). The AI identified scoliosis progression (increase of or over 5° between measurements) with 90.9% accuracy.

CONCLUSION: AI measurements demonstrated excellent absolute and longitudinal agreement with expert human readers for longitudinal Cobb angle measurement across multiple follow-ups, offering potential for improved diagnostic consistency and efficiency in scoliosis assessment.

来源:Acad Radiol,查看原文。版权归原作者所有。

引用

  1. Enters, Zoubi, Dascalescu, et al. AI-Based Longitudinal Scoliosis Monitoring on EOS Whole-Spine Radiographs in a Pediatric to Young Adult Cohort. Acad Radiol. 2026. PMID: 42414133. doi:10.1016/j.acra.2026.06.019

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。