Ma Shuang, Wang Haifeng, Zhao Wei, Yu Zhihao, Wei Baofu, Zhu Shufeng, Zhai Yongqing
School of Information Science and Engineering, Linyi University, Linyi University, Linyi City, Shandong Province, Linyi, 276000, Linyi, China; Linyi People's Hospital Health and Medical Big Data Center, Linyi City, Shandong Province, Linyi, 276034, Linyi, China.
Linyi People's Hospital Health and Medical Big Data Center, Linyi City, Shandong Province, Linyi, 276034, Linyi, China; Linyi City People's Hospital, Linyi People's Hospital of Shandong Province, Linyi, 276034, Linyi, China.
Comput Biol Med. 2025 Feb;185:109468. doi: 10.1016/j.compbiomed.2024.109468. Epub 2024 Dec 10.
This work developed an interpretable deep learning model to automatically annotate landmarks and calculate the hallux valgus angle (HVA) and the intermetatarsal angle (IMA), reducing the time and error of manual calculations by medical experts and improving the efficiency and accuracy of hallux valgus (HV) diagnosis.
A total of 2,000 foot X-ray images were manually labeled with 12 landmarks by two surgical specialists as training data for the deep learning model. The important parts of the foot X-ray images centered on the proximal phalanx of the bunion (PH1), the first metatarsal (MT1), and the second metatarsal (MT2) were segmented using the proposed AG-UNet in the study. The SE-DNN network model was used for automatic identification of landmarks and calculation of the HVA angle between PH1 and MT1, and the IMA angle between MT1 and MT2. Finally, the accuracy of the model was assessed using a comparison of two methods, the interpretability of deep learning and manual measurements by a foot and ankle surgeon.
In the test set, the average error distance between the 12 landmarks predicted by the model and the manually annotated landmarks ranged from 1.9 mm to 5.6 mm, and the average error of all landmarks was less than 3.1 mm. In addition, for the measurement of HVA and IMA angles, the inter-rater agreement between the proposed model and the experts performed well, and the ICC results were all greater than or equal to 0.9.
This work proposed an interpretable deep learning model for hallux valgus prediction, which can automatically identify 12 landmarks and calculate HVA and IMA. Compared with the subjective judgment of medical experts, the model showed significant advantages in reliability and accuracy. The method has been applied in hospitals and achieved significant detection results.
本研究开发了一种可解释的深度学习模型，用于自动标注地标并计算拇外翻角（HVA）和跖间角（IMA），减少医学专家手动计算的时间和误差，提高拇外翻（HV）诊断的效率和准确性。
两名外科专家对2000张足部X线图像进行了12个地标点的手动标注，作为深度学习模型的训练数据。使用本研究中提出的AG-UNet对以拇囊炎近端趾骨（PH1）、第一跖骨（MT1）和第二跖骨（MT2）为中心的足部X线图像的重要部分进行分割。采用SE-DNN网络模型自动识别地标点，并计算PH1与MT1之间的HVA角以及MT1与MT2之间的IMA角。最后，通过两种方法的比较评估模型的准确性，即深度学习的可解释性和足踝外科医生的手动测量。
在测试集中，模型预测的12个地标点与手动标注的地标点之间的平均误差距离在1.9毫米至5.6毫米之间，所有地标点的平均误差小于3.1毫米。此外，对于HVA和IMA角的测量，所提出的模型与专家之间的评分者间一致性良好，ICC结果均大于或等于0.9。
本研究提出了一种用于拇外翻预测的可解释深度学习模型，该模型可以自动识别12个地标点并计算HVA和IMA。与医学专家的主观判断相比，该模型在可靠性和准确性方面具有显著优势。该方法已在医院应用并取得了显著的检测效果。
