Journal: Global Spine Journal

Abbreviation

Publisher

SAGE

Journal Volumes

ISSN

2192-5690
2192-5682

Description

Filters

2022 - 20252
Reset filters

Search Results

Publications 1 - 2 of 2
  • Evaluation of Spinal Fusion in Thoracic and Thoracolumbar Spine on Standard X-Rays: A New Grading System for Spinal Interbody Fusion
    Item type: Journal Article
    Patil, Nirmal D.; Ghait, Hussein Abou El; Boehm, Christian; et al. (2022)
    Global Spine Journal
    Abstract Study Design: Retrospective evaluation of prospectively collected data. Objective: Analyzing time course and stages of interbody fusion of a uniformly operated cohort, defining a grading system and establishing diagnosis-dependent periods of bone healing. Methods: Sequential lateral radiographs of 238 patients (313 levels) with interbody fusion operated thoracoscopically were analyzed. Results: Evaluation of 1696 radiographs with a mean follow-up of 65.19 months and average numbers of 5.42 (2-18) images per level was performed. Diagnoses were Pyogenic Spondylitis (74), Fracture (96), Ankylosing Spondylitis (38) and Degenerative Disease (105). No case with Grade 2 deteriorated to Grade 5. On average, Grade 4 persisted for 113 days, Grade 3 for 197 days, Grade 2 for 286 days and Grade 1 for 316 days. The first 95% of levels (“Green Zone”, ≤ Grade 2) fused at 1 year, the remaining 4% levels fused between 12 and 17 months (“Yellow Zone”) and the last 1% (“Red Zone”) fused after 510 days. Conclusion: Sequential lateral radiographs permit evaluation of interbody fusion. Grade 2 is the threshold point for fusion; once accomplished, failure is unlikely. If fusion (Grade 2,1 or 0) is not reached within 510 days, it should be regarded as failed. The 510-day-threshold could reduce the necessity of CT scanning for assessing fusion.
  • Automatic Calculation of Cervical Spine Parameters Using Deep Learning: Development and Validation on an External Dataset
    Item type: Journal Article
    Nakarai, Hiroyuki; Cina, Andrea; Jutzeler, Catherine; et al. (2025)
    Global Spine Journal
    Study design: Retrospective data analysis. Objectives: This study aims to develop a deep learning model for the automatic calculation of some important spine parameters from lateral cervical radiographs. Methods: We collected two datasets from two different institutions. The first dataset of 1498 images was used to train and optimize the model to find the best hyperparameters while the second dataset of 79 images was used as an external validation set to evaluate the robustness and generalizability of our model. The performance of the model was assessed by calculating the median absolute errors between the model prediction and the ground truth for the following parameters: T1 slope, C7 slope, C2-C7 angle, C2-C6 angle, Sagittal Vertical Axis (SVA), C0-C2, Redlund-Johnell distance (RJD), the cranial tilting (CT) and the craniocervical angle (CCA). Results: Regarding the angles, we found median errors of 1.66° (SD 2.46°), 1.56° (1.95°), 2.46° (SD 2.55), 1.85° (SD 3.93°), 1.25° (SD 1.83°), .29° (SD .31°) and .67° (SD .77°) for T1 slope, C7 slope, C2-C7, C2-C6, C0-C2, CT, and CCA respectively. As concerns the distances, we found median errors of .55 mm (SD .47 mm) and .47 mm (.62 mm) for SVA and RJD respectively. Conclusions: In this work, we developed a model that was able to accurately predict cervical spine parameters from lateral cervical radiographs. In particular, the performances on the external validation set demonstrate the robustness and the high degree of generalizability of our model on images acquired in a different institution.
Publications 1 - 2 of 2