Tack Alexander, Preim Bernhard, Zachow Stefan
Zuse Institute Berlin, Research Group for Computational Diagnosis and Therapy Planning, Department of Visual and Data-centric Computing, Takustraße 7, Berlin, 14195, Germany.
Otto von Guericke University Magdeburg, Department of Simulation and Graphics, Universitätsplatz 2, Magdeburg, 39106, Germany.
Comput Methods Programs Biomed. 2021 Jun;205:106080. doi: 10.1016/j.cmpb.2021.106080. Epub 2021 Apr 8.
We present a fully automated method for the quantification of knee alignment from full-leg radiographs.
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.
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 ± 1.5 mm for all structures. The average mismatch between HKA angle determinations of Cooke and Duryea was 0.09 ± 0.63°; YARLA resulted in a mismatch of 0.09 ± 0.73° compared to Cooke and of 0.18 ± 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.
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.
我们提出了一种用于从全腿X光片中定量分析膝关节对线的全自动方法。
训练了一种先进的目标检测器YOLOv4，用于在全腿X光片中定位髋关节、膝关节和踝关节的感兴趣区域。训练残差神经网络以回归每个感兴趣区域的地标坐标。基于检测到的地标计算膝关节对线，即髋-膝-踝（HKA）角。通过与180张X光片上手动放置的地标进行比较，评估地标检测的准确性。基于2943张X光片，通过与两项独立图像解读研究（Cooke；Duryea）的结果进行比较，评估HKA角计算的准确性，这两项研究均可通过骨关节炎倡议公开获取。使用斯皮尔曼相关系数、加权kappa系数以及关于类别分配的对应关系来评估一致性。
对于所有结构，专家手动放置的地标与我们提出的“YOLOv4和Resnet地标回归算法”（YARLA）自动检测到的地标之间的平均偏差小于2.0±1.5毫米。Cooke和Duryea的HKA角测定之间的平均差异为0.09±0.63°；与Cooke相比，YARLA导致的差异为0.09±0.73°，与Duryea相比为0.18±0.6７°。Cooke和Duryea的加权kappa值为0.86，几乎完全一致，斯皮尔曼相关系数值为0.98，显示出极好的可靠性。YARLA也得到了类似的值，即与Cooke相比加权kappa值为0.83和0.87，斯皮尔曼相关系数值为0.98；与Duryea相比加权kappa值为0.87，斯皮尔曼相关系数值为0.98。Cooke和Duryea在所有类别分配中有91%达成一致，YARLA与Cooke相比在90%的情况下达成一致，与Duryea相比在92%的情况下达成一致。
YARLA得出的HKA角与人类专家得出的相似，为全腿X光片中膝关节对线的自动评估提供了基础。
