Department of Biomedical Engineering, Johns Hopkins University, Baltimore, MD, USA.
Faculty of Medicine, University of Ottawa, Ottawa, ON, Canada.
Emerg Radiol. 2022 Oct;29(5):801-808. doi: 10.1007/s10140-022-02060-2. Epub 2022 May 24.
Periprosthetic dislocations of total hip arthroplasty (THA) are time-sensitive injuries, as the longer diagnosis and treatment are delayed, the more difficult they are to reduce. Automated triage of radiographs with dislocations could help reduce these delays. We trained convolutional neural networks (CNNs) for the detection of THA dislocations, and evaluated their generalizability by evaluating them on external datasets.
We used 357 THA radiographs from a single hospital (185 with dislocation [51.8%]) to develop and internally test a variety of CNNs to identify THA dislocation. We performed external testing of these CNNs on two datasets to evaluate generalizability. CNN performance was evaluated using area under the receiving operating characteristic curve (AUROC). Class activation mapping (CAM) was used to create heatmaps of test images for visualization of regions emphasized by the CNNs.
Multiple CNNs achieved AUCs of 1 for both internal and external test sets, indicating good generalizability. Heatmaps showed that CNNs consistently emphasized the THA for both dislocated and located THAs.
CNNs can be trained to recognize THA dislocation with high diagnostic performance, which supports their potential use for triage in the emergency department. Importantly, our CNNs generalized well to external data from two sources, further supporting their potential clinical utility.
全髋关节置换术后假体周围脱位是一种与时间相关的损伤，因为诊断和治疗的延迟时间越长，复位就越困难。对伴有脱位的 X 光片进行自动分类有助于减少这些延迟。我们使用卷积神经网络（CNN）来检测全髋关节置换术后脱位，并通过在外部数据集上进行评估来评估其泛化能力。
我们使用来自一家医院的 357 张全髋关节置换术 X 光片（185 张有脱位[51.8%]）来开发和内部测试各种用于识别全髋关节置换术后脱位的 CNN。我们在两个数据集上对这些 CNN 进行了外部测试，以评估其泛化能力。使用接收者操作特征曲线下的面积（AUROC）评估 CNN 性能。使用类激活映射（CAM）为测试图像创建热图，以可视化 CNN 强调的区域。
多个 CNN 在内部和外部测试集上的 AUC 均为 1，表明具有良好的泛化能力。热图显示，CNN 始终强调有脱位和无脱位的全髋关节置换术。
可以训练 CNN 以高诊断性能识别全髋关节置换术后脱位，支持它们在急诊科分诊中的潜在用途。重要的是，我们的 CNN 很好地泛化到来自两个来源的外部数据，进一步支持了它们在临床上的潜在应用。
