Significant differences in femoral torsion values depending on the CT measurement technique

This study compared the feasibility of six different CT-based measurement techniques for establishing an indication for derotational osteotomy in the cases of patellar instability or femoral fracture. CT scans of 52 single human cadaver femora were measured using six different torsion measurement techniques (described by Waidelich, Murphy, and Yoshioka on transverse images and Hernandez, Jarrett, and Yoshioka on oblique images). All measurements were performed by four observers twice to assess intraobserver and interobserver agreement. The intraclass correlation coefficient (ICC), ANOVA, and Bonferroni post hoc test were used for the statistical analysis. Significant differences (P < 0.001) between the values for femoral torsion were observed with all techniques except Yoshioka's techniques on transverse and oblique slices (P = 1.000) (transverse images: Waidelich 22.4A degrees +/- 6.8A degrees, Murphy 17.5A degrees +/- 7.0A degrees, Yoshioka 13.4A degrees +/- 6.9A degrees; oblique images: Hernandez 11.4A degrees +/- 7.4A degrees, Jarrett 14.9A degrees +/- 7.5A degrees, Yoshioka oblique 13.4A degrees +/- 7.1A degrees). Intraobserver and interobserver agreement showed a high level of reproducibility (ICC 0.877-0.986; mean 0.8A degrees-2.9A degrees) for all techniques, with the greatest difference being observed with Hernandez's technique (11.4A degrees/10A degrees). Femoral torsion values depend on the measurement technique. When derotational osteotomy is being considered, it is essential to use different threshold values depending on the measurement technique.