Objective: To evaluate preoperative disability's influence on patient-reported outcomes (PROs) following surgery for degenerative spondylolisthesis (DS).
Methods: DS patients who underwent surgical intervention were retrospectively identified from a single-surgeon spine registry. Cohorts based on Oswestry Disability Index (ODI) < 41 (milder disability) and ≥ 41 (severe disability) were created. Demographic differences were accounted for with 1:1 propensity score matching. For the matched sample, perioperative and PRO data were additionally collected. PROs assessed included mental health, physical function, pain, and disability. Pre- and up to 2-year postoperative PROs were utilized. Average time to final follow-up was 15.7 ± 8.8 months. Improvements in PROs and minimal clinically important difference (MCID) rates were calculated. Continuous variables were compared through Student t-test and categorical variables were compared through chi-square tests.
Results: Altogether, 214 patients were included with 77 in the milder disability group. The severe disability group had worse postoperative day (POD) 1 pain scores and longer hospital stays (p ≤ 0.038, both). The severe disability group reported worse outcomes pre- and postoperatively (p < 0.011, all), but had greater average improvement in 12-item Short Form health survey mental composite score (SF-12 MCS), 9-Item Patient Health Questionnaire (PHQ-9), visual analogue scale (VAS)-back, and ODI by 6 weeks (p ≤ 0.037, all) and PHQ-9, VAS-back and ODI by final follow-up (p ≤ 0.015, all). The severe disability cohort was more likely to achieve MCID for SF-12 MCS, PHQ-9, and ODI (p ≤ 0.003, all).
Conclusion: Patients with greater baseline disability report higher POD 1 pain and discharge later than patients with milder disability. While these patients report inferior physical/mental health before and after surgery, they report greater improvements in mental health and disability postoperatively.
Objective: Virtual and augmented reality have enjoyed increased attention in spine surgery. Preoperative planning, pedicle screw placement, and surgical training are among the most studied use cases. Identifying osseous structures is a key aspect of navigating a 3-dimensional virtual reconstruction. To automate the otherwise time-consuming process of labeling vertebrae on each slice individually, we propose a fully automated pipeline that automates segmentation on computed tomography (CT) and which can form the basis for further virtual or augmented reality application and radiomic analysis.
Methods: Based on a large public dataset of annotated vertebral CT scans, we first trained a YOLOv8m (You-Only-Look-Once algorithm, Version 8 and size medium) to detect each vertebra individually. On the then cropped images, a 2D-U-Net was developed and externally validated on 2 different public datasets.
Results: Two hundred fourteen CT scans (cervical, thoracic, or lumbar spine) were used for model training, and 40 scans were used for external validation. Vertebra recognition achieved a mAP50 (mean average precision with Jaccard threshold of 0.5) of over 0.84, and the segmentation algorithm attained a mean Dice score of 0.75 ± 0.14 at internal, 0.77 ± 0.12 and 0.82 ± 0.14 at external validation, respectively.
Conclusion: We propose a 2-stage approach consisting of single vertebra labeling by an object detection algorithm followed by semantic segmentation. In our externally validated pilot study, we demonstrate robust performance for our object detection network in identifying individual vertebrae, as well as for our segmentation model in precisely delineating the bony structures.