Novel AI-Based Algorithm for the Automated Measurement of Cervical Sagittal Balance Parameters. A Validation Study on Pre- and Postoperative Radiographs of 129 Patients.

STUDY DESIGN: Retrospective, mono-centric cohort research study. OBJECTIVES: The analysis of cervical sagittal balance parameters is essential for preoperative planning and dependent on the physician's experience. A fully automated artificial intelligence-based algorithm could contribute to an objective analysis and save time. Therefore, this algorithm should be validated in this study. METHODS: Two surgeons measured C2-C7 lordosis, C1-C7 Sagittal Vertical Axis (SVA), C2-C7-SVA, C7-slope and T1-slope in pre- and postoperative lateral cervical X-rays of 129 patients undergoing anterior cervical surgery. All parameters were measured twice by surgeons and compared to the measurements by the AI algorithm consisting of 4 deep convolutional neural networks. Agreement between raters was quantified, among other metrics, by mean errors and single measure intraclass correlation coefficients for absolute agreement. RESULTS: ICC-values for intra- (range: .92-1.0) and inter-rater (.91-1.0) reliability reflect excellent agreement between human raters. The AI-algorithm could determine all parameters with excellent ICC-values (preop:0.80-1.0; postop:0.86-.99). For a comparison between the AI algorithm and 1 surgeon, mean errors were smallest for C1-C7 SVA (preop: -.3 mm (95% CI:-.6 to -.1 mm), post: .3 mm (.0-.7 mm)) and largest for C2-C7 lordosis (preop:-2.2° (-2.9 to -1.6°), postop: 2.3°(-3.0 to -1.7°)). The automatic measurement was possible in 99% and 98% of pre- and postoperative images for all parameters except T1 slope, which had a detection rate of 48% and 51% in pre- and postoperative images. CONCLUSION: This study validates that an AI-algorithm can reliably measure cervical sagittal balance parameters automatically in patients suffering from degenerative spinal diseases. It may simplify manual measurements and autonomously analyze large-scale datasets. Further studies are required to validate the algorithm on a larger and more diverse patient cohort.

Comparison of three validated systems to analyse spinal shape and motion.

The assessment of spinal shape and mobility is of great importance for long-term therapy evaluation. As frequent radiation should be avoided, especially in children, non-invasive measurements have gained increasing importance. Their comparability between each other however stays elusive. Three non-invasive measurement tools have been compared to each other: Idiag M360, raster stereography and Epionics SPINE. 30 volunteers (15 females/15 males) have each been assessed by each system, investigating lumbar lordosis, thoracic kyphosis and spinal range-of-motion in the sagittal plane. Lumbar lordosis differed significantly (p < 0.001) between measurement devices but correlated significant to each other (Pearson's r 0.5-0.6). Regarding thoracic kyphosis no significant difference and a high correlation (r = 0.8) could be shown between Idiag M360 and raster stereography. For lumbar mobility resulting measurements differed significantly and correlated only moderate between Idiag M360 and Epionics SPINE. Although the different measurement systems are moderate to high correlated to each other, their absolute agreement is limited. This might be explained by differences in their angle definition for lordotic and kyphotic angle, their measurement placement, or their capturing of mobility (static vs. dynamic assessment). Therefore, for long-term evaluation of the back profile, inter-modal comparison of values between different non-invasive devices should be avoided.

Biomechanics of the L5-S1 motion segment after total disc replacement - Influence of iatrogenic distraction, implant positioning and preoperative disc height on the range of motion and loading of facet joints.

Total disc replacement has been introduced to overcome negative side effects of spinal fusion. The amount of iatrogenic distraction, preoperative disc height and implant positioning have been considered important for surgical success. However, their effect on the postoperative range of motion (RoM) and loading of the facets merits further discussion. A validated osteoligamentous finite element model of the lumbosacral spine was employed and extended with four additional models to account for different disc heights. An artificial disc with a fixed center of rotation (CoR) was implemented in L5-S1. In 4000 simulations, the influence of distraction and the CoR's location on the RoM, facet joint forces (FJFs) and facet capsule ligament forces (FCLFs) was investigated. Distraction substantially altered segmental kinematics in the sagittal plane by decreasing range of flexion (0.5° per 1mm of distraction), increasing range of extension (0.7°/mm) and slightly affecting complete sagittal RoM (0.2°/mm). The distraction already strongly increased the FCLFs during surgery (up to 230N) and in flexion (~12N/mm), with higher values in models with larger preoperative disc heights, and increased FJFs in extension. A more anterior implant location decreased the RoM in all planes. In most loading cases, a more posterior location of the implant's CoR increased the FJFs and FCLFs, whereas a more caudal location increased the FCLFs but decreased the FJFs. The results of this study may explain the worse clinical results in patients with overdistraction after TDR. The complete RoM in the sagittal plane appears to be insensitive to detecting surgery-related biomechanical changes.