Department of Orthopaedic Surgery and Rehabilitation, Loyola University Medical Center, Maywood, IL, USA.
Hip Int. 2022 Nov;32(6):766-770. doi: 10.1177/1120700020987526. Epub 2021 Jan 8.
A critical part in preoperative planning for revision arthroplasty surgery involves the identification of the failed implant. Using a predictive artificial neural network (ANN) model, the objectives of this study were: (1) to develop a machine-learning algorithm using operative big data to identify an implant from a radiograph; and (2) to compare algorithms that optimise accuracy in a timely fashion.
Using 2116 postoperative anteroposterior (AP) hip radiographs of total hip arthroplasties from 2002 to 2019, 10 artificial neural networks were modeled and trained to classify the radiograph according to the femoral stem implanted. Stem brand and model was confirmed with 1594 operative reports. Model performance was determined by classification accuracy toward a random 706 AP hip radiographs, and again on a consecutive series of 324 radiographs prospectively collected over 2019.
The Dense-Net 201 architecture outperformed all others with 100.00% accuracy in training data, 95.15% accuracy on validation data, and 91.16% accuracy in the unique prospective series of patients. This outperformed all other models on the validation ( < 0.0001) and novel series ( < 0.0001). The convolutional neural network also displayed the probability (confidence) of the femoral stem classification for any input radiograph. This neural network averaged a runtime of 0.96 (SD 0.02) seconds for an iPhone 6 to calculate from a given radiograph when converted to an application.
Neural networks offer a useful adjunct to the surgeon in preoperative identification of the prior implant.
翻修关节成形术术前规划的一个关键部分涉及到识别失败的植入物。本研究使用预测性人工神经网络（ANN）模型，目的是：（1）使用手术大数据开发一种机器学习算法来从 X 光片中识别植入物；（2）比较及时优化准确性的算法。
使用 2002 年至 2019 年的 2116 例全髋关节置换术术后前后位（AP）髋关节 X 光片，建立并训练了 10 个人工神经网络，以根据植入的股骨柄对 X 光片进行分类。通过 1594 份手术报告确认了柄的品牌和型号。通过对随机的 706 张 AP 髋关节 X 光片进行分类准确性来确定模型性能，并再次对 2019 年期间前瞻性收集的连续 324 张 X 光片进行分类准确性评估。
Dense-Net 201 架构在训练数据中的准确率为 100.00%，验证数据中的准确率为 95.15%，在 2019 年的独特前瞻性患者系列中准确率为 91.16%，优于其他所有模型。在验证（ < 0.0001）和新型系列（ < 0.0001）中，该模型均表现出色。卷积神经网络还显示了任何输入 X 光片的股骨柄分类的概率（置信度）。当将给定的 X 光片转换为应用程序时，该神经网络在 iPhone 6 上的平均运行时间为 0.96（SD 0.02）秒。
神经网络为外科医生在术前识别先前植入物提供了有用的辅助工具。
