Liu Yunpeng, Gan Kaifeng, Li Jin, Sun Dechao, Qiu Hong, Liu Dongquan
Information and Computing Science Department, International Exchange College, Ningbo University of Technology, Ningbo, Zhejiang 315000, P. R. China.
Orthopedics, Lihuili Hospital Affiliated to Ningbo University, Ningbo, Zhejiang 3151000, P. R. China.
Sheng Wu Yi Xue Gong Cheng Xue Za Zhi. 2024 Aug 25;41(4):798-806. doi: 10.7507/1001-5515.202309050.
This article aims to combine deep learning with image analysis technology and propose an effective classification method for distal radius fracture types. Firstly, an extended U-Net three-layer cascaded segmentation network was used to accurately segment the most important joint surface and non joint surface areas for identifying fractures. Then, the images of the joint surface area and non joint surface area separately were classified and trained to distinguish fractures. Finally, based on the classification results of the two images, the normal or ABC fracture classification results could be comprehensively determined. The accuracy rates of normal, A-type, B-type, and C-type fracture on the test set were 0.99, 0.92, 0.91, and 0.82, respectively. For orthopedic medical experts, the average recognition accuracy rates were 0.98, 0.90, 0.87, and 0.81, respectively. The proposed automatic recognition method is generally better than experts, and can be used for preliminary auxiliary diagnosis of distal radius fractures in scenarios without expert participation.
本文旨在将深度学习与图像分析技术相结合，提出一种有效的桡骨远端骨折类型分类方法。首先，使用扩展的U-Net三层级联分割网络准确分割用于识别骨折的最重要的关节面和非关节面区域。然后，分别对关节面区域和非关节面区域的图像进行分类和训练以区分骨折。最后，基于这两张图像的分类结果，可以综合确定正常或ABC骨折分类结果。测试集上正常、A型、B型和C型骨折的准确率分别为0.99、0.92、0.91和0.82。对于骨科医学专家，平均识别准确率分别为0.98、0.90、0.87和0.81。所提出的自动识别方法总体上优于专家，可用于在没有专家参与的情况下对桡骨远端骨折进行初步辅助诊断。
