Deep learning for predicting lumbar segmental instability using neutral lateral lumbar radiographs: a retrospective study
European Spine Journal · 13.06.2026
DOI: 10.1007/s00586-026-10092-2 ↗Kurz gefasst
Fachartikel in der Zeitschrift European Spine Journal, online erschienen am 13.06.2026. Verfasst von Jiajun Song und 5 weiteren Autor:innen. Beteiligte Einrichtung: 154 Anshan Road, Heping District, Tianjin, China, 300052, Tianjin Medical University General Hospital, Tianjin, China. Die Arbeit nennt 25 Literaturangaben. Gefördert von: Tianjin Key Medical Discipline (Specialty) Construct Project, Tianjin Health Commission Science and Technology Key Discipline Project, Tianjin Key Medical Discipline Construction Project.
Abstract (Originalsprache)
OBJECTIVE To develop a deep learning model for predicting lumbar segmental instability (LSI) using neutral lateral lumbar radiographs and to identify key radiographic features associated with LSI. METHODS A DenseNet121-based stacking ensemble model was integrated with Support Vector Machine, Random Forest, and Softmax classifiers. Model validation employed 10-fold cross-validation, with performance assessed using AUC, accuracy, sensitivity, specificity, and F1-score. Sensitivity analyses evaluated robustness across spinal/non-spinal regions, age/gender subgroups, and feature interactions. Gradient-weighted Class Activation Mapping (Grad-CAM) was used to localize critical anatomical regions, which were further validated in machine learning frameworks. RESULTS The DenseNet121-stacking model achieved an AUC of 0.838, accuracy of 77.5%, sensitivity of 75.9%, and specificity of 78.4%. Calibration curves confirmed strong alignment with clinical outcomes. Grad-CAM identified facet joints (34.93%), intervertebral discs (25.99%), and osteophytes (22.66%) as the predominant contributors. The integration of these features into machine learning models yielded an AUC of 0.749. Subgroup analyses demonstrated consistent performance across age and gender groups. Decision curve analysis confirmed the clinical utility of the model in all cohorts. CONCLUSION The stacking ensemble model developed in this study effectively predicts LSI based on neutral lateral lumbar radiographs and identifies key imaging biomarkers, including facet joint hypertrophy, disc degeneration, and osteophyte formation. The model demonstrated stable performance across different age and gender groups, indicating strong generalizability and providing a reliable tool for precise clinical screening and individualized decision-making.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- 154 Anshan Road, Heping District, Tianjin, China, 300052, Tianjin Medical University General Hospital, Tianjin, China.
- 154 Anshan Road, Heping District, Tianjin, China, 300052, Tianjin Medical University General Hospital, Tianjin, China. 462570672@qq.com.
- 154 Anshan Road, Heping District, Tianjin, China, 300052, Tianjin Medical University General Hospital, Tianjin, China. sqfeng@tmu.edu.cn.
Förderung
- Tianjin Key Medical Discipline (Specialty) Construct Project
- Tianjin Health Commission Science and Technology Key Discipline Project
- Tianjin Key Medical Discipline Construction Project
Zitieren
APA
Song, J., Du, J., Liu, S., Chen, J., Zhang, D., & Feng, S. Q. (2026). Deep learning for predicting lumbar segmental instability using neutral lateral lumbar radiographs: a retrospective study. European Spine Journal. https://doi.org/10.1007/s00586-026-10092-2
Vancouver
Song J, Du J, Liu S, Chen J, Zhang D, Feng SQ. Deep learning for predicting lumbar segmental instability using neutral lateral lumbar radiographs: a retrospective study. European Spine Journal. 2026. doi:10.1007/s00586-026-10092-2
BibTeX
@article{Song2026,
author = {Song, Jiajun and Du, Jiawei and Liu, Shengwei and Chen, Junyu and Zhang, Di and Feng, Shi-Qing},
title = {Deep learning for predicting lumbar segmental instability using neutral lateral lumbar radiographs: a retrospective study},
journal = {European Spine Journal},
year = {2026},
doi = {10.1007/s00586-026-10092-2}
}
EUVIMED