Abstract：
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.
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).
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.
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.
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).
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.
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.
摘要：
背景：膝关节置换术后并发症的外科处理需要准确及时地识别植入物制造商和型号。使用深度机器学习的自动图像处理之前已经开发并进行了内部验证；然而，在扩大临床实施范围以实现普遍性之前,外部验证至关重要.
方法：我们训练，已验证，并在外部测试了一个深度学习系统，将膝关节置换术系统归类为4个制造商的9个模型之一，该模型来自4,724个原始产品，回顾性收集了三个学术转诊中心的膝关节前后位（AP）平片。从这些射线照片来看，3,568人用于培训，412用于验证，和744用于外部测试。将增强应用于训练集(n=3,568,000)以增加模型鲁棒性。通过接收器工作特性曲线下的面积来确定性能，灵敏度,特异性，和准确性。计算了种植体识别处理速度。训练和测试集来自统计学上不同的植入物群体(P<.001)。
结果：经过深度学习系统的1000个训练时期，系统判别了9种植入物模型，接收器工作特性曲线下平均面积为0.989，准确率为97.4%，灵敏度为89.2%，在744张APX光片的外部测试数据集中，特异性为99.0%。软件以每幅图像0.02秒的平均速度对植入物进行分类。
结论：基于人工智能的识别膝关节置换植入物的软件证明了良好的内部和外部验证。尽管随着植入物库的扩展，继续监测是必要的，该软件代表了AI的负责任和有意义的临床应用,具有可立即在全球范围内扩展的潜力,并在膝关节翻修术前协助进行术前规划.
方法：我们训练，已验证，并在外部测试了一个深度学习系统，将膝关节置换术系统归类为4个制造商的9个模型之一，该模型来自4,724个原始产品，回顾性收集了三个学术转诊中心的膝关节前后位（AP）平片。从这些射线照片来看，3,568人用于培训，412用于验证，和744用于外部测试。将增强应用于训练集(n=3,568,000)以增加模型鲁棒性。通过接收器工作特性曲线下的面积来确定性能，灵敏度,特异性，和准确性。计算了种植体识别处理速度。训练和测试集来自统计学上不同的植入物群体(P<.001)。
结果：经过深度学习系统的1000个训练时期，系统判别了9种植入物模型，接收器工作特性曲线下平均面积为0.989，准确率为97.4%，灵敏度为89.2%，在744张APX光片的外部测试数据集中，特异性为99.0%。软件以每幅图像0.02秒的平均速度对植入物进行分类。
结论：基于人工智能的识别膝关节置换植入物的软件证明了良好的内部和外部验证。尽管随着植入物库的扩展，继续监测是必要的，该软件代表了AI的负责任和有意义的临床应用,具有可立即在全球范围内扩展的潜力,并在膝关节翻修术前协助进行术前规划.
