A Fully Automated Multistage Deep Learning System for Lenke Classification
Journal of Bone and Joint Surgery · 2026
DOI: 10.2106/jbjs.25.01015 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Bone and Joint Surgery, 2026. Verfasst von Lingcong Xu und 7 weiteren Autor:innen. Beteiligte Einrichtung: Department of Orthopedics, Sichuan Provincial People's Hospital School of Medicine, University of Electronic Science and Technology of China, Chengdu…. Hauptthemen laut MEDLINE: Scoliosis, Deep Learning. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 16 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0).
Abstract (Originalsprache)
Background
The Lenke classification for adolescent idiopathic scoliosis (AIS) has interobserver variability due to subjective clinical assessment. We developed and validated a fully automated deep learning system for precise Lenke classification using spinal radiographs.
Methods
This retrospective study included 650 individuals (mean age, 13.75 ± 2.23 years; 433 female, 217 male; 618 Han Chinese, 32 Tibetan), comprising 183 healthy controls and 467 patients with AIS (aged 10 to 18 years; 25° ≤ Cobb angle < 90°) with full-spine radiographs. A multistage deep learning system consisting of (1) Swin-Unet segmentation of vertebrae (C7-S1) for automated Cobb angle measurement, (2) DeepLabv3+ localization of lumbar pedicles (L1-L5) to determine modifiers via the centroid-to-CSVL (central sacral vertebral line) distance, and (3) a fusion module integrating features to curve types and lumbar (A/B/C) and sagittal thoracic (–/N/+) modifiers was designed to perform end-to-end Lenke classification automatically. Validation used an independent test set.
Results
The system achieved 95.6% overall accuracy in Lenke classification and had a macro-averaged F1 score of 0.862. Vertebral segmentation attained Dice coefficients of 0.917 (anteroposterior) and 0.942 (lateral). Cobb angle measurements showed excellent agreement with those of experts (intraclass correlation coefficient, 0.969 to 0.976 for thoracic or thoracolumbar/lumbar curves). Modifier assignment achieved F1 scores of 0.912 (lumbar A/B/C) and 0.928 (sagittal –/N/+), exceeding clinical acceptability thresholds.
Conclusions
The fully automated system was able to perform rapid, objective, interpretable, and clinically reliable classification of the Lenke type directly from radiographs, with performance comparable with that of expert assessment. It demonstrates potential for standardizing AIS surgical planning, reducing diagnostic variability, and improving surgical workflow efficiency. Level of Evidence: Diagnostic Level III . See Instructions for Authors for a complete description of levels of evidence.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Autor:innen und Institutionen
- Department of Orthopedics, Sichuan Provincial People's Hospital School of Medicine, University of Electronic Science and Technology of China, Chengdu, People's Republic of China.
- Department of Orthopedics, Sichuan East Hospital, Sichuan Provincial People's Hospital, The First People's Hospital of Dazhou, Dazhou, People's Republic of China.
ORCID-Profile: Lingcong Xu, Wenjie Zhong, Niezhenghao He, Jiang Hu, Kun Zhang, Haowen Cui
Zitieren
APA
Xu, L., Liu, C., Zhong, W., Xu, K., He, N., Hu, J., Zhang, K., & Cui, H. (2026). A Fully Automated Multistage Deep Learning System for Lenke Classification. Journal of Bone and Joint Surgery. https://doi.org/10.2106/jbjs.25.01015
Vancouver
Xu L, Liu C, Zhong W, Xu K, He N, Hu J, et al. A Fully Automated Multistage Deep Learning System for Lenke Classification. Journal of Bone and Joint Surgery. 2026. doi:10.2106/jbjs.25.01015
BibTeX
@article{Xu2026,
author = {Xu, Lingcong and Liu, Caiyuan and Zhong, Wenjie and Xu, Ke and He, Niezhenghao and Hu, Jiang and Zhang, Kun and Cui, Haowen},
title = {A Fully Automated Multistage Deep Learning System for Lenke Classification},
journal = {Journal of Bone and Joint Surgery},
year = {2026},
doi = {10.2106/jbjs.25.01015}
}
EUVIMED