Abstract：
The surgical management of complications after total hip arthroplasty (THA) necessitates accurate identification of the femoral implant manufacturer and model. Automated image processing using deep learning has been previously developed and internally validated; however, external validation is necessary prior to responsible application of artificial intelligence (AI)-based technologies.
We trained, validated, and externally tested a deep learning system to classify femoral-sided THA implants as one of the 8 models from 2 manufacturers derived from 2,954 original, deidentified, retrospectively collected anteroposterior plain radiographs across 3 academic referral centers and 13 surgeons. From these radiographs, 2,117 were used for training, 249 for validation, and 588 for external testing. Augmentation was applied to the training set (n = 2,117,000) to increase model robustness. Performance was evaluated by 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 8 implant models with a mean area under the receiver operating characteristic curve of 0.991, accuracy of 97.9%, sensitivity of 88.6%, and specificity of 98.9% in the external testing dataset of 588 anteroposterior radiographs. The software classified implants at a mean speed of 0.02 seconds per image.
An AI-based software demonstrated excellent internal and external validation. Although continued surveillance is necessary with implant library expansion, this software represents responsible and meaningful clinical application of AI with immediate potential to globally scale and assist in preoperative planning prior to revision THA.
We trained, validated, and externally tested a deep learning system to classify femoral-sided THA implants as one of the 8 models from 2 manufacturers derived from 2,954 original, deidentified, retrospectively collected anteroposterior plain radiographs across 3 academic referral centers and 13 surgeons. From these radiographs, 2,117 were used for training, 249 for validation, and 588 for external testing. Augmentation was applied to the training set (n = 2,117,000) to increase model robustness. Performance was evaluated by 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 8 implant models with a mean area under the receiver operating characteristic curve of 0.991, accuracy of 97.9%, sensitivity of 88.6%, and specificity of 98.9% in the external testing dataset of 588 anteroposterior radiographs. The software classified implants at a mean speed of 0.02 seconds per image.
An AI-based software demonstrated excellent internal and external validation. Although continued surveillance is necessary with implant library expansion, this software represents responsible and meaningful clinical application of AI with immediate potential to globally scale and assist in preoperative planning prior to revision THA.
摘要：
背景：全髋关节置换术（THA）后并发症的外科处理需要准确识别股骨植入物制造商和模型。使用深度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，在负责任地应用基于人工智能(AI)的技术之前，外部验证是必要的。
方法：我们训练，已验证，并在外部测试了一个深度学习系统，将股骨侧THA植入物分类为2个制造商的8个模型之一，该模型来自2,954个原始产品，被取消身份，回顾性收集了3个学术转诊中心和13名外科医生的前后位平片.从这些射线照片来看，2,117人被用于培训，249用于验证，和588用于外部测试。将增强应用于训练集(n=2,117,000)以增加模型鲁棒性。通过接收器工作特性曲线下的面积来评估性能，灵敏度,特异性，和准确性。计算了种植体识别处理速度。
结果：训练和测试集来自统计学上不同的植入物群体（P<.001）。在深度学习系统进行了1000次培训之后，系统判别了8个植入物模型，接收器工作特性曲线下的平均面积为0.991，准确率为97.9％，灵敏度为88.6%，在588张前后位X线照片的外部测试数据集中，特异性为98.9%。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AI的软件表现出出色的内部和外部验证。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,并在修订THA之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，将股骨侧THA植入物分类为2个制造商的8个模型之一，该模型来自2,954个原始产品，被取消身份，回顾性收集了3个学术转诊中心和13名外科医生的前后位平片.从这些射线照片来看，2,117人被用于培训，249用于验证，和588用于外部测试。将增强应用于训练集(n=2,117,000)以增加模型鲁棒性。通过接收器工作特性曲线下的面积来评估性能，灵敏度,特异性，和准确性。计算了种植体识别处理速度。
结果：训练和测试集来自统计学上不同的植入物群体（P<.001）。在深度学习系统进行了1000次培训之后，系统判别了8个植入物模型，接收器工作特性曲线下的平均面积为0.991，准确率为97.9％，灵敏度为88.6%，在588张前后位X线照片的外部测试数据集中，特异性为98.9%。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AI的软件表现出出色的内部和外部验证。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,并在修订THA之前协助进行术前规划.
