Deparment of Orthopedics, The First Affiliated Hospital of Nanchang University, Nanchang, China.
Software Engineering Institute, East China Normal University, Shanghai, China.
Skeletal Radiol. 2023 Aug;52(8):1577-1583. doi: 10.1007/s00256-023-04324-5. Epub 2023 Mar 25.
The purpose of this study is to develop and validate a deep convolutional neural network (DCNN) model to automatically identify the manufacturer and model of hip internal fixation devices from anteroposterior (AP) radiographs.
In this retrospective study, 1721 hip AP radiographs, including six internal fixation devices from 1012 patients, were collected from an orthopedic center between June 2014 and June 2022 to establish a classification network. The images were divided into training set (1106 images), validation set (272 images), and test set (343 images). The model efficacy is evaluated by using the data on the test set. The overall TOP-1 accuracy, and the precision, sensitivity, specificity, and F1 score of each model are calculated, and receiver operating characteristic (ROC) curves are plotted to evaluate the model performance. Gradient-weighted class activation mapping (Grad-CAM) images are used to determine the image features that are most important for DCNN decisions.
A total of 1378 (80%) images were used for model development, and model efficacy was validated on a test set with 343 (20%) images. The overall TOP-1 accuracy was 98.5%. The area under the receiver operating characteristic curve (AUC) values for each internal fixation model were 1.000, 1.000, 0.980, 1.000, 0.999, and 1.000, respectively. Gradient-weighted class activation mapping showed the unique design of the internal fixation device.
We developed a deep convolutional neural network model that can identify the manufacturer and model of hip internal fixation devices from the hip AP radiographs.
本研究旨在开发和验证一种深度卷积神经网络（DCNN）模型，以自动从前后位（AP）X 光片中识别髋关节内固定装置的制造商和型号。
在这项回顾性研究中，从 2014 年 6 月至 2022 年 6 月，从一家骨科中心收集了 1721 张髋关节 AP 射线照片，包括 1012 名患者的 6 个内固定装置，用于建立分类网络。图像被分为训练集（1106 张图像）、验证集（272 张图像）和测试集（343 张图像）。使用测试集上的数据评估模型的功效。计算每个模型的总体 TOP-1 准确率，以及精度、灵敏度、特异性和 F1 评分，并绘制接收器工作特征（ROC）曲线以评估模型性能。使用梯度加权类激活映射（Grad-CAM）图像确定 DCNN 决策最重要的图像特征。
共使用 1378 张（80%）图像进行模型开发，并在 343 张（20%）图像的测试集上验证了模型的功效。总体 TOP-1 准确率为 98.5%。每个内固定模型的接收器工作特征曲线下面积（AUC）值分别为 1.000、1.000、0.980、1.000、0.999 和 1.000。梯度加权类激活映射显示了内固定装置的独特设计。
我们开发了一种深度卷积神经网络模型，可以从髋关节 AP X 光片中识别髋关节内固定装置的制造商和型号。
