A Deep Learning Tool for Automated Radiographic Measurement of Acetabular Component Inclination and Version After Total Hip Arthroplasty.
A Deep Learning Tool for Automated Radiographic Measurement of Acetabular Component Inclination and Version After Total Hip Arthroplasty.
复制标题
全髋关节置换术后髋臼组件倾斜度和版本的自动放射学测量的深度学习工具。
DOI：
10.1016/j.arth.2021.02.026
复制
发表时间：
2021-07
期刊：
影响因子：
--
通讯作者：
Maradit Kremers H
中科院分区：
文献类型：
--
作者：
Rouzrokh P;Wyles CC;Philbrick KA;Ramazanian T;Weston AD;Cai JC;Taunton MJ;Lewallen DG;Berry DJ;Erickson BJ;Maradit Kremers H
不适当的髋臼假体角度位置被认为会增加全髋关节置换术（THA）后髋关节脱位的风险。然而，这些角度的手动测量是耗时的，并且易于观察者之间的变化。本研究的目的是开发一种深度学习工具，以自动测量术后X线片上的髋臼组件角度。使用两个队列的600个前后位（AP）骨盆和600个交叉床髋关节外侧术后X线片来开发深度学习模型，以分割髋臼部件和坐骨结节。对队列进行手动注释、增强，并以8：1：1的比例随机分配到训练-验证-测试数据集。两个U-Net卷积神经网络（CNN）模型（一个用于AP，一个用于交叉床侧位X线片）被训练了50个时期。然后进行图像处理，以测量解剖标志上预测掩模上的髋臼部件角度。在80张前后位和80张交叉床侧位X线片上测试了工具的性能。CNN模型在AP和交叉表横向测试数据集上的平均骰子相似系数分别为0.878和0.903。对于倾斜角和前倾角，人体水平和机器水平测量值之间的平均差异分别为1.35°（σ=1.07°）和1.39°（σ=1.27°）。在不到2.5%的情况下观察到人类水平和机器水平测量值之间的差异为5或更多。我们开发了一种高度精确的深度学习工具，用于自动测量髋臼部件的角度位置，用于临床和研究环境。
Inappropriate acetabular component angular position is believed to increase the risk of hip dislocation following total hip arthroplasty (THA). However, manual measurement of these angles is time consuming and prone to inter-observer 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 datasets on an 8:1:1 basis. Two U-Net convolutional neural network (CNN) 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 on anatomical landmarks. Performance of the tool was tested on 80 AP and 80 cross-table lateral radiographs. The CNN models achieved a mean Dice Similarity Coefficient of 0.878 and 0.903 on AP and cross-table lateral test datasets, 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 5 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.
登录
查看更多内容
影响因子：
4.6
作者：
Murphy, M. P.;Killen, C. J.;Wu, K.
通讯作者：
Wu, K.
影响因子：
4.4
作者：
Eversman, WG;Pavlicek, W;Erickson, BJ
通讯作者：
Erickson, BJ
DOI：
10.1109/tpami.2018.2858826
发表时间：
2020-02-01
影响因子：
23.6
作者：
Lin, Tsung-Yi;Goyal, Priya;Dollar, Piotr
通讯作者：
Dollar, Piotr
影响因子：
5.3
作者：
Bozic, Kevin J.;Kurtz, Steven M.;Berry, Daniel J.
通讯作者：
Berry, Daniel J.
影响因子：
4.6
作者：
Stilling M;Kold S;de Raedt S;Andersen NT;Rahbek O;Søballe K
通讯作者：
Søballe K