Li Tong, Wang Yuzhao, Qu Yang, Dong Rongpeng, Kang Mingyang, Zhao Jianwu
The Second Hospital of Jilin University, Jilin University, Changchun, 130000, China.
College of Computer Science and Technology, Jilin University, Changchun, 130000, China.
Skeletal Radiol. 2022 Jun;51(6):1235-1247. doi: 10.1007/s00256-021-03939-w. Epub 2021 Nov 8.
To develop a deep learning algorithm based on automatic detection of landmarks that can be used to automatically calculate forefoot imaging parameters from radiographs and test its performance.
A total of 1023 weight-bearing dorsoplantar (DP) radiographs were included. A total of 776 radiographs were used for training and verification of the model, and 247 radiographs were used for testing the performance of the model. The radiologists manually marked 18 landmarks on each image. By training our model to automatically label these landmarks, 4 imaging parameters commonly used for the diagnosis of hallux valgus could be measured, including the first-second intermetatarsal angle (IMA), hallux valgus angle (HVA), hallux interphalangeal angle (HIA), and distal metatarsal articular angle (DMAA). The reference standard was determined by the radiologists' measurements. The percentage of correct key points (PCK), intragroup correlation coefficient (ICC), Pearson correlation coefficient (r), root mean square error (RMSE), and mean absolute error (MAE) between the predicted value of the model and the reference standard were calculated. The Bland-Altman plot shows the mean difference and 95% LoA.
The PCK was 84-99% at the 3-mm threshold. The correlation between the observed and predicted values of the four angles was high (ICC: 0.89-0.96, r: 0.81-0.97, RMSE: 3.76-6.77, MAE: 3.22-5.52). However, there was a systematic error between the model predicted value and the reference standard (the mean difference ranged from - 3.00 to - 5.08°, and the standard deviation ranged from 2.25 to 4.47°).
Our model can accurately identify landmarks, but there is a certain amount of error in the angle measurement, which needs further improvement.
开发一种基于自动检测地标点的深度学习算法，该算法可用于从X线片自动计算前足成像参数并测试其性能。
共纳入1023张负重背跖位（DP）X线片。其中776张X线片用于模型训练和验证，247张X线片用于测试模型性能。放射科医生在每张图像上手动标记18个地标点。通过训练我们的模型自动标记这些地标点，可测量4个常用于诊断拇外翻的成像参数，包括第一、二跖骨间角（IMA）、拇外翻角（HVA）、拇趾间角（HIA）和跖骨远端关节角（DMAA）。参考标准由放射科医生的测量结果确定。计算模型预测值与参考标准之间的正确关键点百分比（PCK）、组内相关系数（ICC）、皮尔逊相关系数（r）、均方根误差（RMSE）和平均绝对误差（MAE）。Bland-Altman图显示平均差异和95%一致性界限（LoA）。
在3毫米阈值下，PCK为84%-99%。四个角度的观察值与预测值之间相关性较高（ICC：0.89-0.96，r：0.81-0.97，RMSE：3.76-6.77，MAE：3.22-5.52）。然而，模型预测值与参考标准之间存在系统误差（平均差异范围为-3.00至-5.08°，标准差范围为2.25至4.47°）。
我们的模型能够准确识别地标点，但角度测量存在一定误差，需要进一步改进。
