Background and Objective

We present a fully automated method for the quantification of knee alignment from full-leg radiographs.

Methods

A state-of-the-art object detector, YOLOv4, was trained to locate regions of interests in full-leg radiographs for the hip joint, knee, and ankle. Residual neural networks were trained to regress landmark coordinates for each region of interest. Based on the detected landmarks the knee alignment, i.e., the hip-knee-ankle (HKA) angle was computed. The accuracy of landmark detection was evaluated by a comparison to manually placed ones for 180 radiographs. The accuracy of HKA angle computations was assessed on the basis of 2,943 radiographs by a comparison to results of two independent image reading studies (Cooke; Duryea) both publicly accessible via the Osteoarthritis Initiative. The agreement was evaluated using Spearman’s Rho, weighted kappa, and regarding the correspondence of the class assignment.

Results

The average deviation of landmarks manually placed by experts and automatically detected ones by our proposed “YOLOv4 And Resnet Landmark regression Algorithm” (YARLA) was less than 2.0 $\pm$ 1.5 mm for all structures. The average mismatch between HKA angle determinations of Cooke and Duryea was 0.09 $\pm$ 0.63°; YARLA resulted in a mismatch of 0.09 $\pm$ 0.73° compared to Cooke and of 0.18 $\pm$ 0.67° compared to Duryea. Cooke and Duryea agreed almost perfectly with respect to a weighted kappa value of 0.86, and showed an excellent reliability as measured by a Spearman’s Rho value of 0.98. Similar values were achieved by YARLA, i.e., a weighted kappa value of 0.83 and 0.87 and a Spearman’s Rho value of 0.98 and 0.98 compared to Cooke and Duryea, respectively. Cooke and Duryea agreed in 91% of all class assignments and YARLA did so in 90% against Cooke and 92% against Duryea.

Conclusions

YARLA yields HKA angles similar to those of human experts and provides a basis for an automated assessment of knee alignment in full-leg radiographs.

中文翻译：

---

使用“ YOLOv4和Resnet Landmark回归算法”（YARLA），从全腿X射线对膝关节对准进行全自动评估：来自骨关节炎计划的数据

背景与目的

我们提出了一种用于从全腿X射线照片量化膝盖对齐方式的全自动方法。

方法

训练有素的最新物体检测器YOLOv4可以在全腿X射线照片中找到髋关节，膝盖和脚踝的感兴趣区域。训练残差神经网络以回归每个感兴趣区域的界标坐标。基于检测到的界标，计算出膝盖的对齐方式，即髋-膝-踝（HKA）角度。地标检测的准确性通过与180张X射线照片的手动放置位置的比较进行评估。通过比较2项独立的图像阅读研究（Cooke； Duryea）的结果，通过2943幅X射线照片评估了HKA角度的准确性，这两项研究均可通过骨关节炎计划公开获得。使用Spearman的Rho（加权kappa）评估该协议，并评估班级分配的对应关系。

结果

由专家手动放置并由我们提出的“ YOLOv4和Resnet地标回归算法”（YARLA）自动检测到的地标的平均偏差小于2.0 $\pm$所有结构1.5毫米。Cooke和Duryea的HKA角度测定之间的平均不匹配为0.09$\pm$0.63°；YARLA导致不匹配0.09$\pm$ 与Cooke相比为0.73°，为0.18° $\pm$与Duryea相比为0.67°。Cooke和Duryea在加权kappa值为0.86时几乎完全吻合，并且通过Spearman的Rho值为0.98表现出极好的可靠性。通过YARLA获得了相似的值，即与Cooke和Duryea相比，加权kappa值分别为0.83和0.87，Spearman Rho值分别为0.98和0.98。Cooke和Duryea同意了所有班级任务中的91％，而YARLA同意了90％反对Cooke以及92％反对Duryea。

结论

YARLA产生与人类专家相似的HKA角，并为自动评估全腿X射线照片中的膝盖对齐方式提供了基础。