Capturing three-dimensional in vivo lumbar intervertebral joint kinematics using dynamic stereo-X-ray imaging

Abstract

Availability of accurate three-dimensional (3D) kinematics of lumbar vertebrae is necessary to understand normal and pathological biomechanics of the lumbar spine. Due to the technical challenges of imaging the lumbar spine motion in vivo, it has been difficult to obtain comprehensive, 3D lumbar kinematics during dynamic functional tasks. The present study demonstrates a recently developed technique to acquire true 3D lumbar vertebral kinematics, in vivo, during a functional load-lifting task. The technique uses a high-speed dynamic stereo-radiography (DSX) system coupled with a volumetric model-based bone tracking procedure. Eight asymptomatic male participants performed weight-lifting tasks, while dynamic X-ray images of their lumbar spines were acquired at 30 fps. A custom-designed radiation attenuator reduced the radiation white-out effect and enhanced the image quality. High resolution CT scans of participants' lumbar spines were obtained to create 3D bone models, which were used to track the X-ray images via a volumetric bone tracking procedure. Continuous 3D intervertebral kinematics from the second lumbar vertebra (L2) to the sacrum (S1) were derived. Results revealed motions occurring simultaneously in all the segments. Differences in contributions to overall lumbar motion from individual segments, particularly L2-L3, L3-L4, and L4-L5, were not statistically significant. However, a reduced contribution from the L5-S1 segment was observed. Segmental extension was nominally linear in the middle range (20%-80%) of motion during the lifting task, but exhibited nonlinear behavior at the beginning and end of the motion. L5-S1 extension exhibited the greatest nonlinearity and variability across participants. Substantial AP translations occurred in all segments (5.0 ± 0.3 mm) and exhibited more scatter and deviation from a nominally linear path compared to segmental extension. Maximum out-of-plane rotations (<1.91 deg) and translations (<0.94 mm) were small compared to the dominant motion in the sagittal plane. The demonstrated success in capturing continuous 3D in vivo lumbar intervertebral kinematics during functional tasks affords the possibility to create a baseline data set for evaluating the lumbar spinal function. The technique can be used to address the gaps in knowledge of lumbar kinematics, to improve the accuracy of the kinematic input into biomechanical models, and to support development of new disk replacement designs more closely replicating the natural lumbar biomechanics.