Sevinç Hüseyin Fatih, Üreten Kemal, Karadeniz Talha, Gültekin Gökhan Koray
Department Of Orthopedics And Traumatology, Versa Hospital, Kapadokya University, Nevşehir, Turkey.
Department Of Computer Engineering, Çankaya University, Ankara, Turkey.
Ulus Travma Acil Cerrahi Derg. 2025 Aug;31(8):783-788. doi: 10.14744/tjtes.2025.75806.
Femoral neck fractures are a serious health concern, particularly among the elderly. The aim of this study is to diagnose and classify femoral neck fractures from plain pelvic X-rays using deep learning and machine learning algorithms, and to compare the performance of these methods.
The study was conducted on a total of 598 plain pelvic X-ray images, including 296 patients with femoral neck fractures and 302 individuals without femoral neck fractures. Initially, transfer learning was applied using pre-trained deep learning models: VGG-16, ResNet-50, and MobileNetv2.
The pre-trained VGG-16 network demonstrated slightly better performance than ResNet-50 and MobileNetV2 for de-tecting and classifying femoral neck fractures. Using the VGG-16 model, the following results were obtained: 95.6% accuracy, 95.5% sensitivity, 93.3% specificity, 95.7% precision, 95.5% F1 Score, a Cohen's kappa of 0.91, and the Receiver Operating Characteristic (ROC) curve of 0.99. Subsequently, features extracted from the convolution layers of VGG-16 were classified using common machine learning algorithms. Among these, the k-nearest neighbor (k-NN) algorithm outperformed the others and exceeded the accuracy of the VGG-16 model by 1%.
Successful results were obtained using deep learning and machine learning methods for the detection and clas-sification of femoral neck fractures. The model can be further improved through multi-center studies. The proposed model may be especially useful for physicians working in emergency departments and for those not having sufficient experience in evaluating plain pelvic radiographs.
股骨颈骨折是一个严重的健康问题，在老年人中尤为突出。本研究的目的是使用深度学习和机器学习算法从骨盆X线平片中诊断和分类股骨颈骨折，并比较这些方法的性能。
本研究共对598张骨盆X线平片图像进行了分析，其中包括296例股骨颈骨折患者和302例无股骨颈骨折的个体。最初，使用预训练的深度学习模型：VGG-16、ResNet-50和MobileNetv2进行迁移学习。
预训练的VGG-16网络在检测和分类股骨颈骨折方面表现略优于ResNet-50和MobileNetV2。使用VGG-16模型，获得了以下结果：准确率95.6%，灵敏度95.5%，特异度93.3%，精确率95.7%，F1分数95.5%，科恩kappa系数0.91，以及受试者工作特征（ROC）曲线0.99。随后，使用常见的机器学习算法对从VGG-16卷积层提取的特征进行分类。其中，k近邻（k-NN）算法表现优于其他算法，并且准确率比VGG-16模型高出1%。
使用深度学习和机器学习方法对股骨颈骨折进行检测和分类取得了成功的结果。该模型可通过多中心研究进一步改进。所提出的模型可能对急诊科医生以及那些在评估骨盆X线平片方面经验不足的医生特别有用。
