Weakly supervised multiple-instance active learning for tooth-marked tongue recognition
Frontiers in Physiology · 11.06.2025 · 16
DOI: 10.3389/fphys.2025.1598850 ↗Kurz gefasst
Fachartikel in der Zeitschrift Frontiers in Physiology, online erschienen am 11.06.2025. Verfasst von Feilin Deng und 3 weiteren Autor:innen. Beteiligte Einrichtung: School of Medical Information Engineering, Guangzhou University of Chinese Medicine, Guangzhou, China. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 41 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Introduction
Recognizing a tooth-marked tongue has important clinical diagnostic value in traditional Chinese medicine. Current deep learning methods for tooth mark detection require extensive manual labeling and tongue segmentation, which is labor-intensive. Therefore, we propose a weakly supervised multipleinstance active learning model for tooth-marked tongue recognition, aiming to eliminate preprocessing segmentation and reduce the annotation workload while maintaining diagnostic accuracy.
Method
We propose a one-stage method tongenerate tooth mark instances that eliminates the need for pre-segmentation of the tongue. To make full use of unlabeled data, we introduce a semisupervised learning paradigm to pseudo-label unlabeled tongue images with high model confidence in active learning and incorporate them into the training set to improve the training efficiency of the active learning model. In addition, we propose an instance-level hybrid query method considering the diversity of tooth marks.
Result
Experimental results on clinical tongue images verify the effectiveness of the proposed method, which achieves an accuracy of 93.88% for tooth-marked tongue recognition, outperforming the recently introduced weakly supervised approaches.
Conclusion
The proposed method is effective with only a small amount of image-level annotation, and its performance is comparable to that of image-level annotation, instance-level annotation and pixel-level annotation, which require a large number of tooth markers. Our method significantly reduces the annotation cost of the binary classification task of traditional Chinese medicine tooth mark recognition.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- School of Medical Information Engineering, Guangzhou University of Chinese Medicine, Guangzhou, China.
Zitieren
APA
Deng, F., Li, S., Yang, Z., & Zhou, W. (2025). Weakly supervised multiple-instance active learning for tooth-marked tongue recognition. Frontiers in Physiology, 16. https://doi.org/10.3389/fphys.2025.1598850
Vancouver
Deng F, Li S, Yang Z, Zhou W. Weakly supervised multiple-instance active learning for tooth-marked tongue recognition. Frontiers in Physiology. 2025;16. doi:10.3389/fphys.2025.1598850
BibTeX
@article{Deng2025,
author = {Deng, Feilin and Li, Shangxuan and Yang, Zizhu and Zhou, Wu},
title = {Weakly supervised multiple-instance active learning for tooth-marked tongue recognition},
journal = {Frontiers in Physiology},
year = {2025},
volume = {16},
doi = {10.3389/fphys.2025.1598850}
}
EUVIMED