文献速递骨肌DR

基于人工智能的软件在负重足部X线片自动测量中的应用

Automated weight-bearing foot measurements using an artificial intelligence-based software.
PubMed 文献 · Skeletal Radiol · 2024-06-17

回顾性收集三家影像机构的连续负重前足及足侧位X线片,由两名资深肌骨放射科医师独立标注关键点测量前足及侧位足角度,以两人测量均值为参考标准,评估人工智能软件BoneMetrics的自动测量准确性。结果显示各角度平均绝对误差较低,除距骨-第一跖骨角外组间ICC均优秀。

要点

  • AI软件在前足及足侧位X线片上的自动角度测量与人工参考标准间平均绝对误差较低。
  • 前足各角度ICC为0.91~0.98,侧位足除距骨-第一跖骨角(ICC=0.88)外ICC均优秀。
  • 距骨-第一跖骨角的平均绝对误差最大(3.9°),人工测量间一致性亦相对较低。

核心结论

  • AI在负重前足及足侧位X线片上展现出准确自动测量的潜力。

研究设计与样本

  • 回顾性研究,从三家影像机构连续收集负重前足及足侧位X线片,前足片纳入80例(53±17岁,50名女性)、排除26例,侧位足片纳入97例(51±20岁,46名女性)、排除21例;由两名资深肌骨放射科医师独立标注关键点测量,以两人测量均值为参考标准。

诊断标准与关键数值

  • 前足X线片:拇外翻角平均绝对误差1.2°(95%CI [1; 1.4]),偏倚-0.04°,ICC=0.98。
  • 前足X线片:第一至第二跖骨角平均绝对误差0.7°(95%CI [0.6; 0.9]),偏倚-0.19°,ICC=0.91。
  • 前足X线片:第一至第五跖骨角平均绝对误差0.9°(95%CI [0.7; 1.1]),偏倚0.44°,ICC=0.96。
  • 足侧位X线片:距骨-第一跖骨角平均绝对误差3.9°(95%CI [3.4; 4.5]),偏倚0.61°,ICC=0.88。
  • 足侧位X线片:内侧足弓角平均绝对误差1.5°(95%CI [1.2; 1.8]),偏倚-0.18°,ICC=0.95;跟骨倾斜角平均绝对误差1°(95%CI [0.8; 1.2]),偏倚0.74°,ICC=0.99。

临床应用与阅片要点

  • AI软件可自动测量负重前足及足侧位X线片上的拇外翻角、第一至第二跖骨角、第一至第五跖骨角及距骨-第一跖骨角、内侧足弓角、跟骨倾斜角。
  • 距骨-第一跖骨角的平均绝对误差为3.9°,人工测量间ICC=0.88,为该组中一致性相对较低的角度。

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: To assess the accuracy of an artificial intelligence (AI) software (BoneMetrics, Gleamer) in performing automated measurements on weight-bearing forefoot and lateral foot radiographs.

METHODS: Consecutive forefoot and lateral foot radiographs were retrospectively collected from three imaging institutions. Two senior musculoskeletal radiologists independently annotated key points to measure the hallux valgus, first-second metatarsal, and first-fifth metatarsal angles on forefoot radiographs and the talus-first metatarsal, medial arch, and calcaneus inclination angles on lateral foot radiographs. The ground truth was defined as the mean of their measurements. Statistical analysis included mean absolute error (MAE), bias assessed with Bland-Altman analysis between the ground truth and AI prediction, and intraclass coefficient (ICC) between the manual ratings.

RESULTS: Eighty forefoot radiographs were included (53 ± 17 years, 50 women), and 26 were excluded. Ninety-seven lateral foot radiographs were included (51 ± 20 years, 46 women), and 21 were excluded. MAE for the hallux valgus, first-second metatarsal, and first-fifth metatarsal angles on forefoot radiographs were respectively 1.2° (95% CI [1; 1.4], bias = - 0.04°, ICC = 0.98), 0.7° (95% CI [0.6; 0.9], bias = - 0.19°, ICC = 0.91) and 0.9° (95% CI [0.7; 1.1], bias = 0.44°, ICC = 0.96). MAE for the talus-first, medial arch, and calcaneal inclination angles on the lateral foot radiographs were respectively 3.9° (95% CI [3.4; 4.5], bias = 0.61° ICC = 0.88), 1.5° (95% CI [1.2; 1.8], bias = - 0.18°, ICC = 0.95) and 1° (95% CI [0.8; 1.2], bias = 0.74°, ICC = 0.99). Bias and MAE between the ground truth and the AI prediction were low across all measurements. ICC between the two manual ratings was excellent, except for the talus-first metatarsal angle.

CONCLUSION: AI demonstrated potential for accurate and automated measurements on weight-bearing forefoot and lateral foot radiographs.

来源:Skeletal Radiol,查看原文。版权归原作者所有。

引用

  1. Lassalle L, Regnard NE, Ventre J, et al. Automated weight-bearing foot measurements using an artificial intelligence-based software. Skeletal Radiol. 2024. PMID: 38880791. doi:10.1007/s00256-024-04726-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。