Validity of the EOS-determined pelvic parameters and orientation with pelvic positional variation: a phantom study

Abstract

The EOS is a medical imaging system that incorporates simultaneous orthogonal images, producing three-dimensional (3D) reconstructions of the whole skeletal system in various functional positions. Despite growing interest in the pelvic 3D position, the validity of the EOS has not yet been well studied. We investigated the trueness and precision of EOS imaging for pelvic parameters and orientation and assessed whether the measurement using the EOS was affected by the pelvic orientation itself. The orientation of the anterior pelvic plane and pelvic parameters of a custom-made pelvic phantom were measured by three raters using the EOS, and the measurements obtained were compared with the true values. The standard deviations of the measurement errors were 3.23°, 0.26°, 0.23°, 2.98°, 0.88°, and 3.22° for flexion, obliquity, rotation, pelvic incidence, spinopelvic tilt, and sacral slope, respectively. The root-mean square averages of the standard deviation of each measurement were 4.05°, 0.41°, 0.28°, 4.80°, 0.99°, and 5.13°, respectively. The measurement errors for sacral slope correlated significantly with geometric means of flexion, obliquity, and rotation (r = 0.364, p = 2.67 × 10–11). The EOS rendered accurate and reliable measurements regarding pelvic 3D position, even with positional variation, but positional variation could affect measurements of sacral slope.