Aim: Deep learning (DL) algorithms can be used for automated analysis of medical imaging. The aim of this study was to assess the accuracy of an innovative, fully automated DL algorithm for analysis of sagittal balance in adult spinal deformity (ASD). Material and methods: Sagittal balance (sacral slope, pelvic tilt, pelvic incidence, lumbar lordosis and sagittal vertical axis) was evaluated in 141 preoperative and postoperative radiographs of patients with ASD. The DL, landmark-based measurements, were compared with the ground truth values from validated manual measurements. Results: The DL algorithm showed an excellent consistency with the ground truth measurements. The intra-class correlation coefficient between the DL and ground truth measurements was 0.71–0.99 for preoperative and 0.72–0.96 for postoperative measurements. The DL detection rate was 91.5% and 84% for preoperative and postoperative images, respectively. Conclusion: This is the first study evaluating a complete automated DL algorithm for analysis of sagittal balance with high accuracy for all evaluated parameters. The excellent accuracy in the challenging pathology of ASD with long construct instrumentation demonstrates the eligibility and possibility for implementation in clinical routine.

Background: Spinal function can be assessed through different patient reported outcome measures (PROMs). Purpose: The aim of the present study was to evaluate a novel single-item score for the assessment of spinal function: The Subjective Spine Value (SSpV). It was hypothesized that the SSpV correlates with the established scores Oswestry disability index (ODI) and Core Outcome Measures Index (COMI). Methods: Between 08/2020 and 11/2021 151 consecutive patients were prospectively enrolled and completed a questionnaire with the ODI, COMI as well as the SSpV. Patients were divided into 4 groups depending on their specific pathology (Group 1: Degenerative pathologies, Group 2: Tumor, Group 3: Inflammatory / Infection, Group 4: Trauma). Pearson correlation coefficient was used to evaluate correlation between the SSpV and the ODI and COMI separately. Floor and ceiling effects were evaluated. Results: Overall, the SSpV correlated significantly with both ODI (p = < 0.001; r = − 0.640) and COMI (p = < 0.001; r = − 0.640). This was also observed across all investigated groups (range − 0.420–0.736). No relevant floor or ceiling effects were noticed. Conclusions: The SSpV is a valid single-item score for the assessment of spinal function. The SSpV offers a useful tool to efficiently assess spinal function in a variety of spinal pathologies. Level of evidence: I, prospective cohort study.

Purpose: Segmental instability guides surgical decision-making in isthmic lumbar spondylolisthesis (ILS). Despite concerns regarding radiation exposure, reproducibility and applicability in patients with pain or limited mobility, flexion–extension (FE) radiographs remain the standard for instability assessment. Combining upright radiographs with supine magnetic resonance imaging (MRI), both routinely obtained in clinical practice, may offer a comparable, lower-radiation alternative. This study aimed to compare segmental motion at L5/S1 between FE and upright–supine (US) imaging and to evaluate their ability to detect radiographic instability. Methods: In this retrospective cross-sectional study, consecutive patients surgically treated for isolated L5/S1 ILS were screened for eligibility. Segmental motion was assessed using FE radiographs and US imaging, including measurements of dynamic sagittal translation and the proportion of patients identified with radiographic signs of instability. Preoperative pain intensity was assessed using the Numeric Rating Scale (NRS). Results: Of 126 screened patients, 78 met inclusion criteria (59% female; median age 48.5 years; median BMI 26.4 kg/m²). Dynamic sagittal translation was significantly greater on US than on FE ( p < 0.001). US imaging identified more cases of radiographic instability ( p < 0.001). Only US-measured translation was associated with preoperative low back pain intensity ( p = 0.025) and was inversely associated with intervertebral disc degeneration ( p = 0.014). Conclusions: US imaging detected a higher proportion of radiographically unstable ILS cases than FE radiographs. Furthermore, only US-derived translation was associated with pain intensity, suggesting greater clinical relevance. Combining upright radiographs with supine MRI may offer a practical, low-radiation alternative for preoperative instability assessment.

Aim: The aim of this study was to investigate the association between the level of lumbar disc herniation (LDH) and individual spinopelvic anatomy. Material and methods: Spinopelvic parameters were retrospectively evaluated in 57 patients with symptomatic LDH at L4/5 and L5/S1 undergoing minimal invasive sequestrectomy at our institution. LDH was diagnosed in 23 patients at L5/S1 and in 34 patients at L4/5. Patients with further segment degeneration at the index level were excluded from the study. Results: Spinopelvic parameters between the two groups were significantly different. Patients with LDH at L5/S1 had statistically significant lower Pelvic Incidence (PI), Pelvic Tilt (PT), Relative Lumbar Lordosis (RLL) and PI-LL than patients with LDH at L4/5. C7 Sagittal Vertical Axis (C7SVA) was statistically significant lower in patients with LDH at L5/S1. Both groups had no sagittal imbalance. Patients with LDH at L5/S1 were significantly younger than patients with LDH at L4/5. There was a significant positive correlation between age and PT. We observed no significant differences for preoperative values of Lumar Lordosis (LL) and Sacral Slope between the two groups. Conclusions: This is the first study to reveal individual spinopelvic anatomy and, in particular, PI to be associated with the distinct level of LDH. These findings substantiate the biomechanical influence of the sagittal profile on the pathogenesis of LDH. Individual spinopelvic compensatory mechanisms were available independently of the patient’s age. Minimal invasive sequestrectomy is a reliable treatment for symptomatic LDH without further segment degeneration.