人工智能自动识别膝关节置换假体:一项超过350万张平片的的多中心外部验证研究
该研究在3个学术转诊中心回顾性收集4724张膝关节正位平片,训练并外部测试深度学习系统以分类4个制造商的9种膝关节置换假体模型。外部测试集744张平片显示平均AUC为0.989、准确率97.4%、敏感度89.2%、特异度99.0%,平均分类速度0.02秒/图像。作者认为该软件在内部和外部验证中表现优异,但随假体库扩展仍需持续监测。
要点
- 外部测试集744张平片:平均AUC 0.989,准确率97.4%,敏感度89.2%,特异度99.0%。
- 软件平均分类速度为每张图像0.02秒。
- 训练集与测试集来自统计学上不同的假体人群(P < .001)。
核心结论
- 基于人工智能的膝关节置换假体识别软件在内部和外部验证中均表现出色。
- 作者认为,随着假体库扩展仍需持续监测,但该软件代表了负责任且有意义的临床人工智能应用,具有立即在全球推广并辅助翻修膝关节置换术前规划的潜力。
研究设计与样本
- 研究从3个学术转诊中心回顾性收集4724张原始膝关节正位平片,用于训练、验证和外部测试深度学习系统,以分类4个制造商的9种膝关节置换假体模型。
- 其中3568张用于训练,412张用于验证,744张用于外部测试;训练集经增强后达3568000张图像以增加模型稳健性。
- 性能通过受试者工作特征曲线下面积、敏感度、特异度和准确率评估,并计算假体识别处理速度。
主要发现
- 深度学习系统经1000个训练轮次后,在744张正位平片的外部测试数据集中区分9种假体模型,平均受试者工作特征曲线下面积为0.989。
- 外部测试集准确率为97.4%,敏感度为89.2%,特异度为99.0%。
- 软件平均分类速度为每张图像0.02秒。
- 训练集和测试集取自统计学上不同的假体人群(P < .001)。
关键数值与推荐
- 外部测试集744张正位平片:平均AUC 0.989,准确率97.4%,敏感度89.2%,特异度99.0%。
- 软件平均分类速度0.02秒/图像。
- 训练集与测试集假体人群存在统计学差异(P < .001)。
临床怎么用
- 原文未据此给出推荐。
局限性
- 随着假体库扩展,仍需持续监测。
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)。
原文
BACKGROUND: Surgical management of complications following knee arthroplasty demands accurate and timely identification of implant manufacturer and model. Automated image processing using deep machine learning has been previously developed and internally validated; however, external validation is essential prior to scaling clinical implementation for generalizability. METHODS: We trained, validated, and externally tested a deep learning system to classify knee arthroplasty systems as one of the 9 models from 4 manufacturers derived from 4,724 original, retrospectively collected anteroposterior plain knee radiographs across 3 academic referral centers. From these radiographs, 3,568 were used for training, 412 for validation, and 744 for external testing. Augmentation was applied to the training set (n = 3,568,000) to increase model robustness. Performance was determined by the area under the receiver operating characteristic curve, sensitivity, specificity, and accuracy. Implant identification processing speed was calculated. The training and testing sets were drawn from statistically different populations of implants (P < .001). RESULTS: After 1,000 training epochs by the deep learning system, the system discriminated 9 implant models with a mean area under the receiver operating characteristic curve of 0.989, accuracy of 97.4%, sensitivity of 89.2%, and specificity of 99.0% in the external testing dataset of 744 anteroposterior radiographs. The software classified implants at a mean speed of 0.02 seconds per image. CONCLUSION: An artificial intelligence-based software for identifying knee arthroplasty implants demonstrated excellent internal and external validation. Although continued surveillance is necessary with implant library expansion, this software represents a responsible and meaningful clinical application of artificial intelligence with immediate potential to globally scale and assist in preoperative planning prior to revision knee arthroplasty.
引用
- Karnuta JM, Shaikh HJF, Murphy MP, et al. Artificial Intelligence for Automated Implant Identification in Knee Arthroplasty: A Multicenter External Validation Study Exceeding 3.5 Million Plain Radiographs. J Arthroplasty. 2023. PMID: 36940755. doi:10.1016/j.arth.2023.03.039
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。