The contrastive learning method in tongue image representation learning and its significance in intelligent diagnosis

Objective Tongue diagnosis is crucial in traditional Chinese medicine (TCM). As diagnoses cannot be standardized in TCM, reaching an ideal consensus when labeling TCM syndrome is difficult. This results in the introduction of subjective bias in the representation learning method. Therefore, we explo...

Celý popis

Uloženo v:

Podrobná bibliografie
Vydáno v:	Health information science and systems Ročník 13; číslo 1; s. 51
Hlavní autoři:	Liu, Qi, Xu, Dan-dan, Yang, Peng, Liu, Quan-quan, Xia, Shuai-shuai, Zhang, Miao, Li, Ya-yun, Wang, Chun-bao, Peng, Qing-hua
Médium:	Journal Article
Jazyk:	angličtina
Vydáno:	Cham Springer International Publishing 15.08.2025 BioMed Central Ltd Springer Nature B.V
Témata:	Accuracy Annotations Artificial intelligence Bias Bioinformatics Classification Cluster analysis Clustering Computational Biology/Bioinformatics Computer Science Diagnosis Feature extraction Health Informatics Information Systems and Communication Service Labeling Labels Learning Learning strategies Medical imaging Medicine, Chinese Metabolism Methods Personal appearance Qualitative analysis Representations Semantics Standardization Tongue Traditional Chinese medicine South Dakota China Tongue image Traditional Chinese medicine Tongue diagnosis Self-supervised learning Contrastive learning
ISSN:	2047-2501, 2047-2501
On-line přístup:	Získat plný text
Tagy:	Přidat tag Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!

Popis
Shrnutí:	Objective Tongue diagnosis is crucial in traditional Chinese medicine (TCM). As diagnoses cannot be standardized in TCM, reaching an ideal consensus when labeling TCM syndrome is difficult. This results in the introduction of subjective bias in the representation learning method. Therefore, we explore the application of contrastive learning to automatically extract semantic features in tongue images, thereby reducing the need for manual labeling and avoiding manual biases in a self-supervised manner. Methods We applied clustering contrastive learning (CCL) to the representation learning of tongue images. Based on TCM theory, we also coupled with a refined data augmented strategy. The embedding of tongue images by CCL-based models was utilized in downstream tasks, and the feature extraction capability was verified through their loss drop curve, precision, and other metrics. Results The downstream task experiments showed that CCL-based models outperformed the supervised models for most evaluation metrics. In the qualitative experiment, cluster analysis showed that the CCL-based model could perceive the colors and textures of the nasolabial fold or the eye without human-supervised information. Conclusions The contrastive learning (CL) method automatically extracted tongue image features and avoided interference from artificial subjective labels. Thus, the symptoms, signs, and other phenotypes associated with Zheng (syndrome) of TCM can be objectively quantified, thereby solving long-standing standardization problem of TCM.
Bibliografie:	ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14 content type line 23
ISSN:	2047-2501 2047-2501
DOI:	10.1007/s13755-025-00365-3