Department of Electronics, Information and Bioengineering, Politecnico di Milano, Via Golgi 39, 20131 Milan, MI, Italy.
Laboratory of Biological Structure Mechanics (LaBS), Department of Chemistry, Materials and Chemical Engineering "Giulio Natta", Politecnico di Milano, Milan, Italy.
Int J Med Inform. 2023 Aug;176:105095. doi: 10.1016/j.ijmedinf.2023.105095. Epub 2023 May 18.
Revision hip arthroplasty has a less favorable outcome than primary total hip arthroplasty and an understanding of the timing of total hip arthroplasty failure may be helpful. The aim of this study is to develop a combined deep learning (DL) and machine learning (ML) approach to automatically detect hip prosthetic failure from conventional plain radiographs.
Two cohorts of patients (of 280 and 352 patients) were included in the study, for model development and validation, respectively. The analysis was based on one antero-posterior and one lateral radiographic view obtained from each patient during routine post-surgery follow-up. After pre-processing, three images were obtained: the original image, the acetabulum image and the stem image. These images were analyzed through convolutional neural networks aiming to predict prosthesis failure. Deep features of the three images were extracted for each model and two feature-based pipelines were developed: one utilizing only the features of the original image (original image pipeline) and the other concatenating the features of the three images (3-image pipeline). The obtained features were either used directly or reduced through principal component analysis. Both support vector machine (SVM) and random forest (RF) classifiers were considered for each pipeline.
The SVM applied to the 3-image pipeline provided the best performance, with an accuracy of 0.958 ± 0.006 in the internal validation and an F1-score of 0.874 in the external validation set. The explainability analysis, besides identifying the features of the complete original images as the major contributor, highlighted the role of the acetabulum and stem images on the prediction.
This study demonstrated the potentialities of the developed DL-ML procedure based on plain radiographs in the detection of the failure of the hip prosthesis.
翻修髋关节置换术的结果不如初次全髋关节置换术理想，了解全髋关节置换术失败的时间可能会有所帮助。本研究旨在开发一种深度学习（DL）和机器学习（ML）相结合的方法，以便从常规的普通 X 光片中自动检测髋关节假体失效。
该研究纳入了 280 例和 352 例患者的两个队列，分别用于模型开发和验证。分析基于每位患者在常规术后随访期间获得的一张前后位和一张侧位 X 光片。经过预处理，获得了三张图像：原始图像、髋臼图像和柄图像。通过卷积神经网络分析这些图像，以预测假体失效。为每个模型提取了三张图像的深度特征，并开发了两种基于特征的管道：一种仅使用原始图像的特征（原始图像管道），另一种则串联三张图像的特征（三图像管道）。所获得的特征可以直接使用或通过主成分分析进行降维。每个管道都考虑了支持向量机（SVM）和随机森林（RF）分类器。
SVM 应用于三图像管道提供了最佳性能，内部验证的准确率为 0.958±0.006，外部验证集的 F1 得分为 0.874。可解释性分析除了确定完整原始图像的特征是主要贡献者外，还强调了髋臼和柄图像在预测中的作用。
本研究证明了基于普通 X 光片的开发的 DL-ML 程序在检测髋关节假体失效方面的潜力。
