Deep learning-based lightweight model for automated lumbar foraminal stenosis classification: sagittal CT diagnostic performance compared to clinical subspecialists
European Spine Journal · 2026
DOI: 10.1007/s00586-025-09281-2 ↗Kurz gefasst
Vergleichsstudie in der Zeitschrift European Spine Journal, 2026. Verfasst von Jia-Wei Huang und 7 weiteren Autor:innen. Beteiligte Einrichtung: The Second Affiliated Hospital and Yuying Children's Hospital of Wenzhou Medical University, Wenzhou, China. Hauptthemen laut MEDLINE: Deep Learning, Lumbar Vertebrae, Spinal Stenosis, Tomography, X-Ray Computed. Die Arbeit nennt 23 Literaturangaben.
Abstract (Originalsprache)
PURPOSE: Magnetic resonance imaging (MRI) is essential for diagnosing lumbar foraminal stenosis (LFS). However, access remains limited in China due to uneven equipment distribution, high costs, and long waiting times. Therefore, this study developed a lightweight deep learning (DL) model using sagittal CT images to classify LFS severity as a potential clinical alternative where MRI is unavailable. METHODS: A retrospective study included 868 sagittal CT images from 177 patients (2016-2025). Data were split at the patient level into training (n = 125), validation (n = 31), and test sets (n = 21), with annotations, based on the Lee grading system, provided by two spine surgeons. Two DL models were developed: DL1 (EfficientNet-B0) and DL2 (MobileNetV3-Large-100), both of which incorporated a Faster R-CNN with a ResNet-50-based region-of-interest (ROI) detector. Diagnostic performance was benchmarked against spine surgeons with different levels of clinical experience. RESULTS: DL1 achieved 82.35% diagnostic accuracy (matching the senior spine surgeon's 83.33%), with DL2 at 80.39% (mean 81.37%), both exceeding the junior spine surgeon's 62.75%. DL1 demonstrated near-perfect diagnostic agreement with the senior spine surgeon, as validated by Cohen's kappa analysis (κ = 0.815; 95% CI: 0.723-0.907), whereas DL2 showed substantial consistency (κ = 0.799; 95% CI: 0.703-0.895). Inter-model agreement yielded κ = 0.782 (95% CI: 0.682-0.882). CONCLUSIONS: The DL models achieved a mean diagnostic accuracy of 81.37%, comparable to that of the senior spine surgeon (83.33%) in grading LFS severity on sagittal CT. However, given the limited sample size and absence of external validation, their applicability and generalisability to other populations and in multi-centre, large-scale datasets remain uncertain.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- The Second Affiliated Hospital and Yuying Children's Hospital of Wenzhou Medical University, Wenzhou, China.
- The Second Affiliated Hospital and Yuying Children's Hospital of Wenzhou Medical University, Wenzhou, China. tiannaifeng@163.com.
Zitieren
APA
Huang, J. W., Zhang, Y. L., Li, K. Y., Li, H. L., Ye, H. B., Chen, Y. H., Lin, X. X., & Tian, N. F. (2026). Deep learning-based lightweight model for automated lumbar foraminal stenosis classification: sagittal CT diagnostic performance compared to clinical subspecialists. European Spine Journal. https://doi.org/10.1007/s00586-025-09281-2
Vancouver
Huang JW, Zhang YL, Li KY, Li HL, Ye HB, Chen YH, et al. Deep learning-based lightweight model for automated lumbar foraminal stenosis classification: sagittal CT diagnostic performance compared to clinical subspecialists. European Spine Journal. 2026. doi:10.1007/s00586-025-09281-2
BibTeX
@article{Huang2026,
author = {Huang, Jia-Wei and Zhang, Yu-Long and Li, Kai-Yu and Li, Hua-Lin and Ye, Hao-Bo and Chen, Yu-Han and Lin, Xin-Xiao and Tian, Nai-Feng},
title = {Deep learning-based lightweight model for automated lumbar foraminal stenosis classification: sagittal CT diagnostic performance compared to clinical subspecialists},
journal = {European Spine Journal},
year = {2026},
doi = {10.1007/s00586-025-09281-2}
}
EUVIMED