文献速递儿科影像骨肌DR

基于开源平台部署并前瞻性验证用于肢体长度差异测量的AI模型

Clinical deployment and prospective validation of an AI model for limb-length discrepancy measurements using an open-source platform.
PubMed 文献 · Eur Radiol · 2025-09-24

本研究将肢体长度差异(LLD)AI模型封装为Docker容器并集成至临床计算平台,开展影子试验(2024年7月至9月)和临床试验(2024年11月至2025年1月)两项前瞻性验证。影子试验纳入84例儿童的84份EOS扫描图,临床试验纳入114例儿童的114份EOS扫描图,AI模型估算股骨和胫骨长度的中位绝对差为0.2-0.3 cm。作者认为该模型性能与放射科医生相当,可作为第二读者提高LLD测量的信心和准确性。

要点

  • AI模型估算股骨和胫骨长度的中位绝对差为0.2-0.3 cm。
  • 影子试验中股骨和胫骨长度的中位绝对差均为0.2 cm。
  • 临床试验中股骨长度中位绝对差0.3 cm,胫骨长度0.2 cm。

核心结论

  • 成功利用计算平台将LLD AI模型无缝集成并部署至临床工作流程,并前瞻性验证了其性能。

研究设计与样本

  • 研究将LLD AI模型推理编码为Docker容器并集成至临床部署计算平台,开展影子试验(2024年7月至9月)和临床试验(2024年11月至2025年1月)两项前瞻性验证研究;影子试验纳入84例儿童的84份EOS扫描图(168个股骨和胫骨长度),临床试验纳入114例儿童的114份EOS扫描图(228个股骨和胫骨长度),以放射学报告中的双侧股骨和胫骨长度为参考进行比较。

诊断标准与关键数值

  • 影子试验中,AI模型估算股骨和胫骨长度的中位绝对差(IQR)分别为0.2 cm(0.3 cm)和0.2 cm(0.3 cm)。
  • 临床试验中,AI模型估算股骨和胫骨长度的中位绝对差(IQR)分别为0.3 cm(0.4 cm)和0.2 cm(0.3 cm)。

临床应用与阅片要点

  • 作者认为,性能与放射科医生相当的LLD AI模型可作为第二读者,提高LLD测量的信心和准确性。
  • 影子试验中AI标注输出对放射科医生隐藏,临床试验中在解读研究时向放射科医生显示AI标注输出。

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

OBJECTIVES: To deploy an AI model to measure limb-length discrepancy (LLD) and prospectively validate its performance.

MATERIALS AND METHODS: We encoded the inference of an LLD AI model into a docker container, incorporated it into a computational platform for clinical deployment, and conducted two prospective validation studies: a shadow trial (07/2024-9/2024) and a clinical trial (11/2024-01/2025). During each trial period, we queried for LLD EOS scanograms to serve as inputs to our model. For the shadow trial, we hid the AI-annotated outputs from the radiologists, and for the clinical trial, we displayed the AI-annotated output to the radiologists at the time of study interpretation. Afterward, we collected the bilateral femoral and tibial lengths from the radiology reports and compared them against those generated by the AI model. We used median absolute difference (MAD) and interquartile range (IQR) as summary statistics to assess the performance of our model.

RESULTS: Our shadow trial consisted of 84 EOS scanograms from 84 children, with 168 femoral and tibial lengths. The MAD (IQR) of the femoral and tibial lengths were 0.2 cm (0.3 cm) and 0.2 cm (0.3 cm), respectively. Our clinical trial consisted of 114 EOS scanograms from 114 children, with 228 femoral and tibial lengths. The MAD (IQR) of the femoral and tibial lengths were 0.3 cm (0.4 cm) and 0.2 cm (0.3 cm), respectively.

CONCLUSION: We successfully employed a computational platform for seamless integration and deployment of an LLD AI model into our clinical workflow, and prospectively validated its performance.

KEY POINTS: Question No AI models have been clinically deployed for limb-length discrepancy (LLD) assessment in children, and the prospective validation of these models is unknown. Findings We deployed an LLD AI model using a homegrown platform, with prospective trials showing a median absolute difference of 0.2-0.3 cm in estimating bone lengths. Clinical relevance An LLD AI model with performance comparable to that of radiologists can serve as a secondary reader in increasing the confidence and accuracy of LLD measurements.

来源:Eur Radiol,查看原文。版权归原作者所有。

引用

  1. Tsai A, Samal S, Lamonica P, et al. Clinical deployment and prospective validation of an AI model for limb-length discrepancy measurements using an open-source platform. Eur Radiol. 2025. PMID: 40990984. doi:10.1007/s00330-025-12022-0

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。