文献速递关节外科

深度学习人工智能模型基于术后X线评估初次全髋关节置换后脱位风险

Deep Learning Artificial Intelligence Model for Assessment of Hip Dislocation Risk Following Primary Total Hip Arthroplasty From Postoperative Radiographs.
PubMed 文献 · J Arthroplasty · 2021-02-16

本研究回顾性分析13,970例初次全髋关节置换(THA)的术后骨盆正位X线片,其中374例发生脱位,共纳入1,490张脱位者和91,094张非脱位者的X线片。采用YOLO-V3裁剪以股骨头为中心的图像,并用ResNet18分类器预测后续髋关节脱位。模型平均敏感度89.0%、阴性预测值99.5%、AUC 76.7%,结论认为该影像分类器可结合临床危险因素快速评估THA后脱位风险。

要点

  • 模型基于术后骨盆正位X线片预测THA后脱位,平均敏感度89.0%、阴性预测值99.5%。
  • 模型平均准确率49.5%、特异度48.8%、阳性预测值3.3%、AUC 76.7%。
  • 显著性图显示模型最关注股骨头和髋臼假体区域。

核心结论

  • 现有预测方法无法识别THA后脱位高危患者,而该影像分类器模型具有高敏感度和高阴性预测值,可结合临床危险因素快速评估脱位风险。

研究设计与样本

  • 回顾性队列研究,纳入13,970例初次THA、随访5年,其中374例脱位,分析1,490张脱位者与91,094张非脱位者的X线片。
  • 使用YOLO-V3目标检测模型以股骨头为中心裁剪图像,ResNet18分类器以ImageNet权重初始化,经FastAI(V1.0)在PyTorch上训练15个epoch,采用10折交叉验证、过采样和数据增强。

主要发现

  • 髋脱位分类器平均(标准差)准确率49.5(4.1%)、敏感度89.0(2.2%)、特异度48.8(4.2%)。
  • 阳性预测值3.3(0.3%)、阴性预测值99.5(0.1%)、受试者工作特征曲线下面积76.7(3.6%)。
  • 显著性图显示模型最关注股骨头和髋臼假体区域。

临床怎么用

  • 该模型高敏感度和高阴性预测值可用于快速评估THA后脱位风险,并建议与临床危险因素信息结合使用。
  • 模型提示的影像学位置(股骨头和髋臼假体)可能有助于理解假体脱位的病因。

局限性

  • 证据等级为Level III。

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: Dislocation is a common complication following total hip arthroplasty (THA), and accounts for a high percentage of subsequent revisions. The purpose of this study is to illustrate the potential of a convolutional neural network model to assess the risk of hip dislocation based on postoperative anteroposterior pelvis radiographs. METHODS: We retrospectively evaluated radiographs for a cohort of 13,970 primary THAs with 374 dislocations over 5 years of follow-up. Overall, 1490 radiographs from dislocated and 91,094 from non-dislocated THAs were included in the analysis. A convolutional neural network object detection model (YOLO-V3) was trained to crop the images by centering on the femoral head. A ResNet18 classifier was trained to predict subsequent hip dislocation from the cropped imaging. The ResNet18 classifier was initialized with ImageNet weights and trained using FastAI (V1.0) running on PyTorch. The training was run for 15 epochs using 10-fold cross validation, data oversampling, and augmentation. RESULTS: The hip dislocation classifier achieved the following mean performance (standard deviation): accuracy = 49.5 (4.1%), sensitivity = 89.0 (2.2%), specificity = 48.8 (4.2%), positive predictive value = 3.3 (0.3%), negative predictive value = 99.5 (0.1%), and area under the receiver operating characteristic curve = 76.7 (3.6%). Saliency maps demonstrated that the model placed the greatest emphasis on the femoral head and acetabular component. CONCLUSION: Existing prediction methods fail to identify patients at high risk of dislocation following THA. Our radiographic classifier model has high sensitivity and negative predictive value, and can be combined with clinical risk factor information for rapid assessment of risk for dislocation following THA. The model further suggests radiographic locations which may be important in understanding the etiology of prosthesis dislocation. Importantly, our model is an illustration of the potential of automated imaging artificial intelligence models in orthopedics. LEVEL OF EVIDENCE: Level III.

来源:J Arthroplasty,查看原文。版权归原作者所有。

引用

  1. Rouzrokh P, Ramazanian T, Wyles CC, et al. Deep Learning Artificial Intelligence Model for Assessment of Hip Dislocation Risk Following Primary Total Hip Arthroplasty From Postoperative Radiographs. J Arthroplasty. 2021. PMID: 33663890. doi:10.1016/j.arth.2021.02.028

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。