Single‐View Contrastive Learning for Laryngeal Leukoplakia Classification With NBI Laryngoscopy Images
Head & Neck · 2025
DOI: 10.1002/hed.28157 ↗Kurz gefasst
Fachartikel in der Zeitschrift Head & Neck, 2025. Verfasst von Zhenzhen You und 9 weiteren Autor:innen. Beteiligte Einrichtung: Shaanxi Key Laboratory for Network Computing and Security Technology, School of Computer Science and Engineering, Xi'an University of Technology, Xi'…. Hauptthemen laut MEDLINE: Laryngoscopy, Narrow Band Imaging, Leukoplakia, Laryngeal Neoplasms. Die Arbeit nennt 34 Literaturangaben. Gefördert von: Key projects of Natural Science and Technology Research Program of Shaanxi, General Program of National Natural Science Foundation of China, Natural Science Basic Research Program of Shaanxi Province.
Abstract (Originalsprache)
Background
Laryngeal cancer is the second most common upper respiratory tract cancer. Early and accurate diagnosis can improve the cure rate of patients. Laryngoscopy with NBI is a commonly used tool that can help endoscopists diagnose laryngeal diseases. However, the fine classification of laryngeal leukoplakia using NBI images is challenging for computer‐aided diagnosis.
Methods
In this article, we propose a single‐view contrastive learning network to locate lesion regions, construct sample pairs for contrastive learning, and provide pseudo‐labels to unlabeled data in order to achieve fine classification under small samples. Firstly, we pretrain the backbone network using the original NBI images. Secondly, in order to augment the number of samples for contrastive learning, we design different patch generation methods based on an attention‐guided network. The original NBI images are cropped into small patches for the purpose of generating lesion‐related regions and complementary samples. The pseudo‐labels of these small patches are obtained by applying the pre‐trained backbone network. Finally, we combine the contrastive loss function and the cross‐entropy loss function for jointly training the backbone network and contrastive learning network. Our NBI dataset is classified into six categories: normal tissue, inflammatory keratosis, mild dysplasia, moderate dysplasia, severe dysplasia, and squamous cell carcinoma. Results and Conclusion Experimental results demonstrate that our model achieves an accuracy of 96.12%, which is higher than the current mainstream models. Our model also achieves high specificity and sensitivity. The code is available at https://github.com/hans‐bbt/single‐view‐contrastive‐learning .
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Shaanxi Key Laboratory for Network Computing and Security Technology, School of Computer Science and Engineering, Xi'an University of Technology, Xi'an, China.
- Department of Otolaryngology, Second Affiliated Hospital of Medical College, Xi'an Jiaotong University, Xi'an, China.
ORCID-Profile: Zhenzhen You
Förderung
- Key projects of Natural Science and Technology Research Program of Shaanxi
- General Program of National Natural Science Foundation of China
- Natural Science Basic Research Program of Shaanxi Province
- Applied Technology Research and Development Project in Beilin District, Xian City
- Xi'an Jiaotong University Medical "Basic-Clinical" Integration Innovation Project
- College Student Innovation Training Program Project
Zitieren
APA
You, Z., Han, B., Shi, Z., Du, S., Zhao, M., Lv, Z., Hei, X., Liu, H., Ren, X., & Yan, Y. (2025). Single‐View Contrastive Learning for Laryngeal Leukoplakia Classification With NBI Laryngoscopy Images. Head & Neck. https://doi.org/10.1002/hed.28157
Vancouver
You Z, Han B, Shi Z, Du S, Zhao M, Lv Z, et al. Single‐View Contrastive Learning for Laryngeal Leukoplakia Classification With NBI Laryngoscopy Images. Head & Neck. 2025. doi:10.1002/hed.28157
BibTeX
@article{You2025,
author = {You, Zhenzhen and Han, Botao and Shi, Zhenghao and Du, Shuangli and Zhao, Minghua and Lv, Zhiyong and Hei, Xinhong and Liu, Haiqin and Ren, Xiaoyong and Yan, Yan},
title = {Single‐View Contrastive Learning for Laryngeal Leukoplakia Classification With NBI Laryngoscopy Images},
journal = {Head & Neck},
year = {2025},
doi = {10.1002/hed.28157}
}
EUVIMED