Gan Kaifeng, Liu Yunpeng, Zhang Ting, Xu Dingli, Lian Leidong, Luo Zhe, Li Jin, Lu Liangjie
Department of Orthopaedics, the Affiliated LiHuiLi Hospital of Ningbo University, No. 57 Xingning Road, Yinzhou District, Ningbo, 315211, Zhejiang, China.
Ningbo University of Technology, Ningbo, 315100, Zhejiang, China.
J Imaging Inform Med. 2024 Dec;37(6):2874-2882. doi: 10.1007/s10278-024-01144-4. Epub 2024 Jun 11.
Distal radius fracture (DRF) is one of the most common types of wrist fractures. We aimed to construct a model for the automatic segmentation of wrist radiographs using a deep learning approach and further perform automatic identification and classification of DRF. A total of 2240 participants with anteroposterior wrist radiographs from one hospital between January 2015 and October 2021 were included. The outcomes were automatic segmentation of wrist radiographs, identification of DRF, and classification of DRF (type A, type B, type C). The Unet model and Fast-RCNN model were used for automatic segmentation. The DenseNet121 model and ResNet50 model were applied to DRF identification of DRF. The DenseNet121 model, ResNet50 model, VGG-19 model, and InceptionV3 model were used for DRF classification. The area under the curve (AUC) with 95% confidence interval (CI), accuracy, precision, and F1-score was utilized to assess the effectiveness of the identification and classification models. Of these 2240 participants, 1440 (64.3%) had DRF, of which 701 (48.7%) were type A, 278 (19.3%) were type B, and 461 (32.0%) were type C. Both the Unet model and the Fast-RCNN model showed good segmentation of wrist radiographs. For DRF identification, the AUCs of the DenseNet121 model and the ResNet50 model in the testing set were 0.941 (95%CI: 0.926-0.965) and 0.936 (95%CI: 0.913-0.955), respectively. The AUCs of the DenseNet121 model (testing set) for classification type A, type B, and type C were 0.96, 0.96, and 0.96, respectively. The DenseNet121 model may provide clinicians with a tool for interpreting wrist radiographs.
桡骨远端骨折（DRF）是最常见的腕部骨折类型之一。我们旨在构建一个使用深度学习方法对腕部X光片进行自动分割的模型，并进一步对DRF进行自动识别和分类。纳入了2015年1月至2021年10月期间来自一家医院的2240名有腕部前后位X光片的参与者。结果包括腕部X光片的自动分割、DRF的识别以及DRF的分类（A型、B型、C型）。使用Unet模型和Fast-RCNN模型进行自动分割。将DenseNet121模型和ResNet50模型应用于DRF的识别。使用DenseNet121模型、ResNet50模型、VGG-19模型和InceptionV3模型进行DRF分类。利用曲线下面积（AUC）及其95%置信区间（CI）、准确率、精确率和F1分数来评估识别和分类模型的有效性。在这2240名参与者中，1440名（64.3%）患有DRF，其中701名（48.7%）为A型，278名（19.3%）为B型，461名（32.0%）为C型。Unet模型和Fast-RCNN模型在腕部X光片分割方面均表现良好。对于DRF识别，测试集中DenseNet121模型和ResNet50模型的AUC分别为0.941（95%CI：0.926 - 0.965）和0.936（95%CI：0.913 - 0.955）。DenseNet121模型（测试集）对A型、B型和C型分类的AUC分别为0.96、0.96和0.96。DenseNet121模型可为临床医生提供一种解读腕部X光片的工具。
