Osteoarthritis (OA) means that the slippery cartilage tissue that covers the bone surfaces in the joints and allows the joint to move easily loses its properties and wears out. Knee OA is the wear and tear of the cartilage in the knee joint. Knee OA is a disease whose incidence increases especially after a certain age. Knee OA is difficult and costly to be detected by specialists using traditional methods and may lead to misdiagnosis. In this study, computer‐aided systems were used to prevent errors in traditional methods of detecting knee OA, shorten the diagnosis time, and accelerate the treatment process. In this study, a hybrid model was developed by using Darknet53, Histogram of Directional Gradients (HOG), Local Binary Model (LBP) methods for feature extraction, and Neighborhood Component Analysis (NCA) for feature selection. Our dataset used in experiments contains 1650 knee joint images and consists of five classes: Normal, Doubtful, Mild, Moderate, and Severe. In the experimental studies performed, the performance of the proposed method was compared with eight different Convolutional Neural Networks (CNN) Models. The developed model achieved better performance metrics than the eight different models used in the study and similar studies in the literature. The accuracy value of the developed model is 83.6%.

中文翻译：

---

使用基于人工智能的方法自动检测膝骨关节炎分级

骨关节炎 (OA) 是指覆盖关节骨表面并允许关节轻松移动的光滑软骨组织失去其性能并磨损。膝关节骨关节炎是指膝关节软骨的磨损。膝关节骨关节炎是一种发病率尤其在一定年龄后增加的疾病。专家使用传统方法检测膝骨关节炎非常困难且成本高昂，并且可能导致误诊。在本研究中，计算机辅助系统用于防止传统膝关节骨关节炎检测方法的错误，缩短诊断时间，加快治疗进程。在本研究中，使用 Darknet53、方向梯度直方图 (HOG)、局部二值模型 (LBP) 方法进行特征提取，以及邻域成分分析 (NCA) 进行特征选择，开发了一种混合模型。我们在实验中使用的数据集包含 1650 个膝关节图像，并由五个类别组成：正常、可疑、轻度、中度和严重。在进行的实验研究中，将所提出方法的性能与八种不同的卷积神经网络（CNN）模型进行了比较。所开发的模型比本研究中使用的八种不同模型以及文献中的类似研究取得了更好的性能指标。所开发模型的准确率为83.6%。