Can artificial intelligence support or even replace physicians in measuring sagittal balance?

European Spine Journal (2022) 31:1943–1951

Sagittal balance (SB) plays an important role in the surgical treatment of spinal disorders. The aim of this research study is to provide a detailed evaluation of a new, fully automated algorithm based on artificial intelligence (AI) for the determination of SB parameters on a large number of patients with and without instrumentation.

Methods Pre- and postoperative sagittal full body radiographs of 170 patients were measured by two human raters, twice by one rater and by the AI algorithm which determined: pelvic incidence, pelvic tilt, sacral slope, L1-S1 lordosis, T4-T12 thoracic kyphosis (TK) and the spino-sacral angle (SSA). To evaluate the agreement between human raters and AI, the mean error (95% confidence interval (CI)), standard deviation and an intra- and inter-rater reliability was conducted using intra-class correlation (ICC) coefficients.

Results ICC values for the assessment of the intra- (range: 0.88–0.97) and inter-rater (0.86–0.97) reliability of human raters are excellent. The algorithm is able to determine all parameters in 95% of all pre- and in 91% of all postoperative images with excellent ICC values (PreOP-range: 0.83–0.91, PostOP: 0.72–0.89). Mean errors are smallest for the SSA (PreOP: −0.1° (95%-CI: −0.9°–0.6°); PostOP: −0.5° (−1.4°–0.4°)) and largest for TK (7.0° (6.1°–7.8°); 7.1° (6.1°–8.1°)).

Conclusion A new, fully automated algorithm that determines SB parameters has excellent reliability and agreement with human raters, particularly on preoperative full spine images. The presented solution will relieve physicians from timeconsuming routine work of measuring SB parameters and allow the analysis of large databases efficiently.

Tear-drop technique in iliac screw placement: a technical analysis

Acta Neurochirurgica (2021) 163:1577–1581

Instrumentation of the lumbosacral region is one of the more challenging regions due to the complex anatomical structures and biomechanical forces. Screw insertion can be done both navigated and based on X-ray verification. In this study, we demonstrate a fast and reliable open, low exposure X-ray-guided technique of iliac screw placement.

Methods Between October 2016 and August 2019, 48 patients underwent sacropelvic fixation in tear-drop technique. Screw insertion was performed in open technique by using an X-ray converter angulated 25-30° in coronal and sagittal view. The anatomical insertion point was the posterior superior iliac spine. Verification of correct screw placement was done by intraoperative 3D scan.

Results In total, 95 iliac screws were placed in tear-drop technique with a correct placement in 98.1%.

Conclusions The tear-drop technique showed a proper screw position in the intraoperative 3D scan and therefore may be considered an alternative technique to the navigated screw placement.

Intraoperative X-Ray Detection and MRI-Based Quantification of Brain Shift Effects Subsequent to Implantation of the First Electrode in Bilateral Implantation of Deep Brain Stimulation Electrodes

Stereotact Funct Neurosurg 2009;87:322-329 (DOI:10.1159/000235804)

After implantation of the first electrode in bilateral deep brain stimulation (DBS) lead implantation, brain shift effects in the target region and along the implantation trajectory of the second electrode are quantified with intraoperative magnetic resonance imaging (MRI). We investigated intraoperative X-ray imaging for its feasibility in indirect detection of brain shift.

Methods: In 25 patients who underwent bilateral DBS lead implantation, X-ray and MRI were performed before and after implantation of the first electrode. Two parameters of brain shift were assessed with nonrigid free-form deformation field analysis of the MRI data: global brain shift along the anterior and posterior commissure (AC-PC) line and specific brain shift along the implantation trajectory of the second electrode. Pre- and intraoperative X-ray images were geometrically and intensity corrected for detection of significant signal changes through intracranial air accumulation during implantation of the first electrode.

Results: After implantation of the first electrode, brain shift greater than 1 mm (maximum 1.3 mm) was observed at the AC and brain shift greater than 2 mm (maximum 2.5 mm) was observed along the planned implantation trajectory of the second electrode. In 1 patient, the implantation trajectory of the second electrode went through a sulcus after cortical brain shift. In 9 patients, intracranial air volume between 0.1 and 38.5 ml was observed with MRI after implantation of the first electrode. Significant X-ray absorption changes were induced by an intracranial air volume of greater than 8 ml.

Conclusion: In bilateral DBS implantation, brain shift effects can cause misallocation of the second electrode with the risk of adverse or no stimulation effects as well as unnecessary cortical damage. A lack of X-ray signal changes caused by intracranial air invasion during DBS lead implantation indicates a lack of clinically relevant brain shift.