Abstract：
BACKGROUND: Revision total hip arthroplasty (THA) requires preoperatively identifying in situ implants, a time-consuming and sometimes unachievable task. Although deep learning (DL) tools have been attempted to automate this process, existing approaches are limited by classifying few femoral and zero acetabular components, only classify on anterior-posterior (AP) radiographs, and do not report prediction uncertainty or flag outlier data.
METHODS: This study introduces Total Hip Arhtroplasty Automated Implant Detector (THA-AID), a DL tool trained on 241,419 radiographs that identifies common designs of 20 femoral and 8 acetabular components from AP, lateral, or oblique views and reports prediction uncertainty using conformal prediction and outlier detection using a custom framework. We evaluated THA-AID using internal, external, and out-of-domain test sets and compared its performance with human experts.
RESULTS: THA-AID achieved internal test set accuracies of 98.9% for both femoral and acetabular components with no significant differences based on radiographic view. The femoral classifier also achieved 97.0% accuracy on the external test set. Adding conformal prediction increased true label prediction by 0.1% for acetabular and 0.7 to 0.9% for femoral components. More than 99% of out-of-domain and >89% of in-domain outlier data were correctly identified by THA-AID.
CONCLUSIONS: The THA-AID is an automated tool for implant identification from radiographs with exceptional performance on internal and external test sets and no decrement in performance based on radiographic view. Importantly, this is the first study in orthopedics to our knowledge including uncertainty quantification and outlier detection of a DL model.
METHODS: This study introduces Total Hip Arhtroplasty Automated Implant Detector (THA-AID), a DL tool trained on 241,419 radiographs that identifies common designs of 20 femoral and 8 acetabular components from AP, lateral, or oblique views and reports prediction uncertainty using conformal prediction and outlier detection using a custom framework. We evaluated THA-AID using internal, external, and out-of-domain test sets and compared its performance with human experts.
RESULTS: THA-AID achieved internal test set accuracies of 98.9% for both femoral and acetabular components with no significant differences based on radiographic view. The femoral classifier also achieved 97.0% accuracy on the external test set. Adding conformal prediction increased true label prediction by 0.1% for acetabular and 0.7 to 0.9% for femoral components. More than 99% of out-of-domain and >89% of in-domain outlier data were correctly identified by THA-AID.
CONCLUSIONS: The THA-AID is an automated tool for implant identification from radiographs with exceptional performance on internal and external test sets and no decrement in performance based on radiographic view. Importantly, this is the first study in orthopedics to our knowledge including uncertainty quantification and outlier detection of a DL model.
摘要：
背景：翻修全髋关节置换术（THA）需要术前确定原位植入物，一项耗时且有时无法完成的任务。尽管已经尝试了深度学习(DL)工具来自动化这个过程，现有的方法是有限的分类股骨和零髋臼组件，仅在前后（AP）X光片上进行分类，并且不报告预测不确定性或标记离群数据。
方法：本研究介绍了THA-AID，在241,419张射线照片上训练的DL工具，可识别来自AP的20个股骨和8个髋臼组件的常见设计，横向,或斜视图，并使用共形预测和使用自定义框架的离群点检测报告预测不确定性。我们使用内部评估了THA-AID，外部,和域外测试集，并将其性能与人类专家进行比较。
结果：THA-AID对于股骨和髋臼组件均实现了98.9%的内部测试集准确度，根据影像学检查没有显著差异。股骨分类器在外部测试集上也实现了97.0%的准确度。添加适形预测将髋臼的真实标签预测增加了0.1％，股骨组件的真实标签预测增加了0.7％-0.9％。THA-AID正确识别了超过99％的域外和>89％的域内异常数据。
结论：THA-AID是一种用于从射线照片中识别植入物的自动化工具，在内部和外部测试集上具有出色的性能，并且基于射线照相视图的性能没有下降。重要的是,据我们所知,这是骨科领域的第一项研究,包括DL模型的不确定性量化和离群值检测.
方法：本研究介绍了THA-AID，在241,419张射线照片上训练的DL工具，可识别来自AP的20个股骨和8个髋臼组件的常见设计，横向,或斜视图，并使用共形预测和使用自定义框架的离群点检测报告预测不确定性。我们使用内部评估了THA-AID，外部,和域外测试集，并将其性能与人类专家进行比较。
结果：THA-AID对于股骨和髋臼组件均实现了98.9%的内部测试集准确度，根据影像学检查没有显著差异。股骨分类器在外部测试集上也实现了97.0%的准确度。添加适形预测将髋臼的真实标签预测增加了0.1％，股骨组件的真实标签预测增加了0.7％-0.9％。THA-AID正确识别了超过99％的域外和>89％的域内异常数据。
结论：THA-AID是一种用于从射线照片中识别植入物的自动化工具，在内部和外部测试集上具有出色的性能，并且基于射线照相视图的性能没有下降。重要的是,据我们所知,这是骨科领域的第一项研究,包括DL模型的不确定性量化和离群值检测.
