Multi-task learning for classification and prediction of adolescent idiopathic scoliosis based on fringe-projection three-dimensional imaging
European Spine Journal · 2025
DOI: 10.1007/s00586-025-09340-8 ↗Kurz gefasst
Evaluationsstudie in der Zeitschrift European Spine Journal, 2025. Verfasst von Chi-Kuang Feng und 4 weiteren Autor:innen. Beteiligte Einrichtung: Department of Orthopaedics and Traumatology, Taipei Veterans General Hospital, Taipei, Taiwan. Hauptthemen laut MEDLINE: Scoliosis, Imaging, Three-Dimensional, Image Interpretation, Computer-Assisted, Deep Learning. Die Arbeit wurde bisher 5-mal zitiert (Crossref) und nennt 25 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Yang Ming Chiao Tung University.
Abstract (Originalsprache)
Purpose
This study aims to address the limitations of radiographic imaging and single-task learning models in adolescent idiopathic scoliosis assessment by developing a noninvasive, radiation-free diagnostic framework.
Methods
A multi-task deep learning model was trained using structured back surface data acquired via fringe projection three-dimensional imaging. The model was designed to simultaneously predict the Cobb angle, curve type (thoracic, lumbar, mixed, none), and curve direction (left, right, none) by learning shared morphological features.
Results
The multi-task model achieved a mean absolute error (MAE) of 2.9° and a root mean square error (RMSE) of 6.9° for Cobb angle prediction, outperforming the single-task baseline (5.4° MAE, 12.5° RMSE). It showed strong correlation with radiographic measurements ( R = 0.96, R² = 0.91). For curve classification, it reached 89% sensitivity in lumbar and mixed types, and 80% and 75% sensitivity for right and left directions, respectively, with an 87% positive predictive value for right-sided curves.
Conclusion
The proposed multi-task learning model demonstrates that jointly learning related clinical tasks allows for the extraction of more robust and clinically meaningful geometric features from surface data. It outperforms traditional single-task approaches in both accuracy and stability. This framework provides a safe, efficient, and non-invasive alternative to X-ray–based scoliosis assessment and has the potential to support real-time screening and long-term monitoring of adolescent idiopathic scoliosis in clinical practice.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Orthopaedics and Traumatology, Taipei Veterans General Hospital, Taipei, Taiwan.
- Department of Biomedical Engineering, National Yang Ming Chiao Tung University, Taipei, Taiwan.
- Department of Biomedical Engineering, National Yang Ming Chiao Tung University, Taipei, Taiwan. cyliu66@nycu.edu.tw.
- Medical Device Innovation and Translation Center, National Yang Ming Chiao Tung University, Taipei, Taiwan. cyliu66@nycu.edu.tw.
Förderung
- National Yang Ming Chiao Tung University
Zitieren
APA
Feng, C. K., Chen, Y. J., Dinh, Q. T., Tran, K. T., & Liu, C. Y. (2025). Multi-task learning for classification and prediction of adolescent idiopathic scoliosis based on fringe-projection three-dimensional imaging. European Spine Journal. https://doi.org/10.1007/s00586-025-09340-8
Vancouver
Feng CK, Chen YJ, Dinh QT, Tran KT, Liu CY. Multi-task learning for classification and prediction of adolescent idiopathic scoliosis based on fringe-projection three-dimensional imaging. European Spine Journal. 2025. doi:10.1007/s00586-025-09340-8
BibTeX
@article{Feng2025,
author = {Feng, Chi-Kuang and Chen, Yen-Ju and Dinh, Quoc-Thinh and Tran, Khac-Tuan and Liu, Cheng-Yang},
title = {Multi-task learning for classification and prediction of adolescent idiopathic scoliosis based on fringe-projection three-dimensional imaging},
journal = {European Spine Journal},
year = {2025},
doi = {10.1007/s00586-025-09340-8}
}
EUVIMED