PCOR-net: A prototype-enhanced contrastive ordinal regression network for pneumoconiosis staging
Journal of X-Ray Science and Technology · 2026-05 · 34 (3) · 302-313
DOI: 10.1177/08953996261433872 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of X-Ray Science and Technology, online erschienen am 08.04.2026. Verfasst von Guohua Ji und 5 weiteren Autor:innen. Beteiligte Einrichtung: College of Computer Science and Technology (College of Data Science), Taiyuan University of Technology, Taiyuan, China. Hauptthemen laut MEDLINE: Pneumoconiosis, Radiography, Thoracic, Neural Networks, Computer. Die Arbeit nennt 41 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Central Guiding Local Science and Technology Development Funds, Special Funding for Shanxi Province Science and Technology Innovation Talent Teams.
Abstract (Originalsprache)
Background
Pneumoconiosis is one of the most severe occupational diseases, and accurate staging is essential for treatment planning and disease management. However, the visual features on chest X-rays are often subtle and exhibit gradual transitions between stages, posing challenges for traditional classification models.
Objective
The study aims to overcome the limitations of current staging methods, and to develop a model that simultaneously captures the ordinal progression of pneumoconiosis and enhances feature discrimination for reliable staging.
Methods
We propose a Prototype-enhanced Contrastive Ordinal Regression Network (PCOR-Net) for pneumoconiosis staging. PCOR-Net adopts a dual-branch architecture, where a momentum-updated teacher encoder builds dynamic class prototypes, and a student encoder learns more discriminative features under prototype-guided supervision. To capture the ordinal structure of disease progression, we introduce an ordinal-aware prototype contrastive mechanism and a learnable-threshold ordinal regression module that adapts to the non-uniform nature of stage transitions. Three loss functions—prototype contrastive loss, feature distillation loss, and ordinal regression loss—are jointly optimized in a unified framework.
Results
We conducted experiments on the pneumoconiosis dataset, where PCOR-Net achieved an accuracy of 91.18% and a Quadratic Weighted Kappa (QWK) of 92.72%, outperforming existing state-of-the-art methods. To assess generalizability, PCOR-Net was also evaluated on a COVID-19 severity dataset, demonstrating good transferability.
Conclusions
PCOR-Net demonstrates strong effectiveness and robustness in pneumoconiosis staging and generalizes well to the COVID-19 grading dataset, providing reliable support for clinical diagnosis with improved accuracy and ordinal consistency.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- College of Computer Science and Technology (College of Data Science), Taiyuan University of Technology, Taiyuan, China.
- School of Software, Taiyuan University of Technology, Taiyuan, China.
- College of Information, Jinzhong College of Information, Jinzhong, China.
- School of Automation and Software Engineering, Shanxi University, Taiyuan, China.
- NHC Key Laboratory of Pneumoconiosis, First Hospital of Shanxi Medical University, Taiyuan, China.
- Macau University of Science and Technology, Macau, China.
ORCID-Profile: Guohua Ji
Förderung
- National Natural Science Foundation of China
- Central Guiding Local Science and Technology Development Funds
- Special Funding for Shanxi Province Science and Technology Innovation Talent Teams
Zitieren
APA
Ji, G., Zhao, J., Chu, S., Ren, X., Wei, Y., & Chen, Q. (2026). PCOR-net: A prototype-enhanced contrastive ordinal regression network for pneumoconiosis staging. Journal of X-Ray Science and Technology, 34(3), 302-313. https://doi.org/10.1177/08953996261433872
Vancouver
Ji G, Zhao J, Chu S, Ren X, Wei Y, Chen Q. PCOR-net: A prototype-enhanced contrastive ordinal regression network for pneumoconiosis staging. Journal of X-Ray Science and Technology. 2026;34(3):302-313. doi:10.1177/08953996261433872
BibTeX
@article{Ji2026,
author = {Ji, Guohua and Zhao, Juanjuan and Chu, Surong and Ren, Xueting and Wei, Yangyang and Chen, Qi},
title = {PCOR-net: A prototype-enhanced contrastive ordinal regression network for pneumoconiosis staging},
journal = {Journal of X-Ray Science and Technology},
year = {2026},
volume = {34},
number = {3},
pages = {302--313},
doi = {10.1177/08953996261433872}
}
EUVIMED