文献速递骨肌DR

人工智能生成的下肢X线测量在含植入物队列中是否准确

Are artificial intelligence generated lower extremity radiographic measurements accurate in a cohort with implants?
PubMed 文献 · Skeletal Radiol · 2025-04-28

本研究评估人工智能软件在含下肢金属植入物患者中行下肢全长正位片测量的准确性,并与两名放射科医生比较效率。AI 对 156 条腿中的 129 条生成输出,13 项变量中 11 项与阅片者一致性优良(ICC≥0.75),Bland-Altman 性能目标仅 5/13 项达标;AI 平均读片时间 38 秒,两名阅片者分别为 181 秒和 214 秒。结论为在该含植入物队列中,基于 AI 的下肢长度测量快速且准确,但多数角度测量不准确。

要点

  • 含下肢金属植入物时,AI 仅对 156 条腿中的 129 条生成测量输出。
  • 13 项测量变量中 11 项 AI 与阅片者一致性优良(ICC≥0.75)。
  • Bland-Altman 性能目标仅 5/13 项变量达标,多数角度测量不准确。

核心结论

  • 在含下肢金属植入物的队列中,基于 AI 的下肢长度测量快速且准确,但多数角度测量不准确。

研究设计与样本

  • 研究类型为针对含下肢金属植入物队列的 AI 测量准确性评估,样本为 156 条腿。
  • 由两名放射科医生与 AI 软件独立完成 8 个角度和 5 个长度的测量。
  • 测量变量包括髋膝角(HKA)、解剖胫股角(aTFA)、解剖机械轴角(AMA)、关节线汇聚角(JLCA)、机械股骨近端外侧角(mLPFA)、机械股骨远端外侧角(mLDFA)、机械胫骨近端内侧角(mMPTA)、机械胫骨远端外侧角(mLDTA)、股骨长度、胫骨长度、全腿长度、下肢长度差异(LLD)和机械轴偏差(MAD)。
  • 统计学方法为组内相关系数(ICC)和 Bland-Altman 分析。

诊断标准与关键数值

  • AI 与阅片者一致性以 ICC≥0.75 为优良,13 项变量中 11 项达到优良。
  • Bland-Altman 性能目标在 13 项变量中 5 项达标。
  • AI 对 156 条腿中的 129 条生成输出。
  • AI 平均(标准差)读片时间为 38(6)秒,两名阅片者分别为 181(41)秒和 214(77)秒。

临床应用与阅片要点

  • 在含下肢金属植入物的患者中,AI 生成的下肢长度测量快速且准确。
  • 原文结论指出多数角度测量不准确,阅片时对 AI 角度测量结果需谨慎。

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)。

英文原文(摘要)· 点击展开

OBJECTIVE: Leg length discrepancy (LLD) and malalignment of the lower extremity can lead to pain and increased risk of osteoarthritis. Radiographic measurements on anteroposterior (AP) full-length radiographs can be used to assess LLD and lower extremity alignment. The primary aim of this study was to evaluate the accuracy of AI software in performing lower extremity radiographic measurements in patients with implants. The secondary aim was to compare its efficiency to that of radiologists.

MATERIALS AND METHODS: This study used the following eight angles and five lengths: hip-knee-angle (HKA), anatomical-tibiofemoral angle (aTFA), anatomical-mechanical-axis angle (AMA), joint-line-convergence angle (JLCA), mechanical-lateral-proximal-femur-angle (mLPFA), mechanical-lateral-distal-femur-angle (mLDFA), mechanical-medial-proximal-tibia-angle (mMPTA), mechanical-lateral-distal-tibia- angle (mLDTA), femur length, tibia length, full leg length, leg-length-discrepancy (LLD), and mechanical-axis-deviation (MAD). Two radiologists and AI software independently performed these measurements on 156 legs. The statistical methods used to assess AI performance were intraclass correlation coefficient (ICC) and Bland-Altman analysis.

RESULTS: The AI generated output for 129/156 legs. 11/13 of the variables showed excellent agreement (ICC ≥ 0.75) between AI and the readers. Bland Altman performance targets were met for 5/13 variables. The mean (standard deviation) reading time for the AI and two readers, respectively, was 38 (6) seconds, 181 (41) seconds, and 214 (77) seconds.

CONCLUSION: In a cohort with lower extremity metal implants, AI-based leg length measurements were fast and accurate although most angular measurements were not.

来源:Skeletal Radiol,查看原文。版权归原作者所有。

引用

  1. Archer H, Xia S, Reine S, et al. Are artificial intelligence generated lower extremity radiographic measurements accurate in a cohort with implants? Skeletal Radiol. 2025. PMID: 40295351. doi:10.1007/s00256-025-04936-z

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。