Department of Radiology, Mayo Clinic, Radiology Informatics Laboratory, Rochester, MN.
Department of Health Sciences Research, Mayo Clinic, Rochester, MN; Department of Orthopedic Surgery, Mayo Clinic, Rochester, MN.
J Arthroplasty. 2021 Jul;36(7):2510-2517.e6. doi: 10.1016/j.arth.2021.02.026. Epub 2021 Feb 16.
Inappropriate acetabular component angular position is believed to increase the risk of hip dislocation after total hip arthroplasty. However, manual measurement of these angles is time consuming and prone to interobserver variability. The purpose of this study was to develop a deep learning tool to automate the measurement of acetabular component angles on postoperative radiographs.
Two cohorts of 600 anteroposterior (AP) pelvis and 600 cross-table lateral hip postoperative radiographs were used to develop deep learning models to segment the acetabular component and the ischial tuberosities. Cohorts were manually annotated, augmented, and randomly split to train-validation-test data sets on an 8:1:1 basis. Two U-Net convolutional neural network models (one for AP and one for cross-table lateral radiographs) were trained for 50 epochs. Image processing was then deployed to measure the acetabular component angles on the predicted masks for anatomical landmarks. Performance of the tool was tested on 80 AP and 80 cross-table lateral radiographs.
The convolutional neural network models achieved a mean Dice similarity coefficient of 0.878 and 0.903 on AP and cross-table lateral test data sets, respectively. The mean difference between human-level and machine-level measurements was 1.35° (σ = 1.07°) and 1.39° (σ = 1.27°) for the inclination and anteversion angles, respectively. Differences of 5⁰ or more between human-level and machine-level measurements were observed in less than 2.5% of cases.
We developed a highly accurate deep learning tool to automate the measurement of angular position of acetabular components for use in both clinical and research settings.
III.
髋臼假体角度不当被认为会增加全髋关节置换术后髋关节脱位的风险。然而，这些角度的手动测量既耗时又容易受到观察者间的变异性影响。本研究的目的是开发一种深度学习工具，以实现术后 X 光片髋臼假体角度的自动测量。
使用两组共 600 张前后位（AP）骨盆和 600 张交叉位侧位髋关节术后 X 光片来开发深度学习模型，以分割髋臼假体和坐骨结节。使用手动标注、增强和随机分割的方法，将数据按照 8:1:1 的比例分为训练-验证-测试数据集。使用两个 U-Net 卷积神经网络模型（一个用于 AP 图像，一个用于交叉位侧位图像）进行 50 个周期的训练。然后，对预测掩模中的解剖学标志进行图像处理，以测量髋臼假体的角度。在 80 张 AP 和 80 张交叉位侧位 X 光片上测试了该工具的性能。
卷积神经网络模型在 AP 和交叉位侧位测试数据集上的平均 Dice 相似系数分别为 0.878 和 0.903。在倾斜角和前倾角方面，人工和机器测量之间的平均差值分别为 1.35°（σ=1.07°）和 1.39°（σ=1.27°）。在不到 2.5%的情况下，人工和机器测量之间的差值大于 5°。
我们开发了一种高度精确的深度学习工具，用于自动测量髋臼假体的角度位置，可用于临床和研究环境。
III 级。
