Fully automated Assessment of Knee Alignment from Full-Leg X-Rays employing a "YOLOv4 And Resnet Landmark regression Algorithm" (YARLA): Data from the Osteoarthritis Initiative

Alexander Tack; Bernhard Preim; Stefan Zachow

doi:10.1016/j.cmpb.2021.106080

Fully automated Assessment of Knee Alignment from Full-Leg X-Rays employing a "YOLOv4 And Resnet Landmark regression Algorithm" (YARLA): Data from the Osteoarthritis Initiative

Comput Methods Programs Biomed. 2021 Jun:205:106080. doi: 10.1016/j.cmpb.2021.106080. Epub 2021 Apr 8.

Authors

Alexander Tack¹, Bernhard Preim², Stefan Zachow³

Affiliations

¹ Zuse Institute Berlin, Research Group for Computational Diagnosis and Therapy Planning, Department of Visual and Data-centric Computing, Takustraße 7, Berlin, 14195, Germany. Electronic address: tack@zib.de.
² Otto von Guericke University Magdeburg, Department of Simulation and Graphics, Universitätsplatz 2, Magdeburg, 39106, Germany.
³ Zuse Institute Berlin, Research Group for Computational Diagnosis and Therapy Planning, Department of Visual and Data-centric Computing, Takustraße 7, Berlin, 14195, Germany.

PMID: 33892211
DOI: 10.1016/j.cmpb.2021.106080

Abstract

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 ± 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.

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.

Keywords: Deep learning; Hip-knee-ankle angle; Mechanical axes; Osteoarthritis; Valgus; Varus.

MeSH terms

Algorithms
Bone Malalignment*
Humans
Knee Joint / diagnostic imaging
Leg
Osteoarthritis*
Reproducibility of Results
Retrospective Studies
X-Rays