EUVIMEDEUVIMED entdecken
Open Access

TonguExpert: A Deep Learning-Based Algorithm Platform for Fine-Grained Extraction and Classification of Tongue Phenotypes

Ting Li iD, Ling Zuo iD, Pengyu Wang iD, Liangfu Yang iD, Zijia Liu, Xu Wang iD, Jingze Tan iD, Yajun Yang iD, Jiucun Wang iD, Yong Zhou, Li Jin iD, Guangtao Zhai und 4 weitere

Phenomics · 2025-04 · 5 (2) · 109-122

DOI: 10.1007/s43657-024-00210-9 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Phenomics, online erschienen am 26.03.2025. Verfasst von Ting Li und 15 weiteren Autor:innen. Beteiligte Einrichtung: CAS Key Laboratory of Computational Biology, Shanghai Institute of Nutrition and Health, University of Chinese Academy of Sciences, Chinese Academy o…. Die Arbeit wurde bisher 17-mal zitiert (Crossref) und nennt 37 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar. Gefördert von: the Strategic Priority Research Program of the Chinese Academy of Sciences, Youth Innovation Promotion Association of the Chinese Academy of Sciences, CAS Young Team Program for Stable Support of Basic 488 Research.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Tongue analysis holds promise for disease detection and health monitoring, especially in traditional Chinese medicine. However, its subjectivity hinders clinical applications. Deep learning offers a path for automated tongue diagnosis, yet existing methods struggle to capture subtle details, and the lack of large datasets hampers the development of robust and generalizable models. To address these challenges, we introduce TonguExpert (https://www.biosino.org/TonguExpert), a free platform for archiving, analyzing, and extracting phenotypes from tongue images. Our deep learning framework integrates cutting-edge techniques for tongue segmentation and phenotype extraction. TonguExpert analyzes a massive dataset of 5992 tongue images from a Chinese population and extracts 773 phenotypes including five predicted labels and their probabilities, 355 global features (entire tongue, tongue body, and tongue coating) and 408 local features (fissures and tooth marks) in a unified process. Besides, 580 additional features for five tongue subregions are also available for future study. Notably, TonguExpert outperforms manual classification methods, achieving high accuracy (ROC-AUC 0.89-0.99 for color, 0.97 for fissures, 0.88 for tooth marks). Additionally, the model generalizes well to predict new phenotypes (e.g., greasy coating) using external datasets. This allows the model to learn from a broader spectrum of data, potentially improving its overall performance. We also release the largest publicly available dataset of tongue images and phenotypes, which is invaluable for advancing automated analysis and clinical applications of tongue diagnosis. In summary, this research advances automated tongue diagnosis, paving the way for wider clinical adoption and potentially expanding the applications in the future. Supplementary Information: The online version contains supplementary material available at 10.1007/s43657-024-00210-9.

Schlagwörter

Stichwörter der Autor:innen

Automated platformDeep learningTonguExpertTongue imagesTongue phenotype extractionTraditional Chinese medicine

Autor:innen und Institutionen

  • CAS Key Laboratory of Computational Biology, Shanghai Institute of Nutrition and Health, University of Chinese Academy of Sciences, Chinese Academy of Sciences, Shanghai, 200031 China.
  • School of Traditional Chinese Medicine, Beijing University of Chinese Medicine, Beijing, 100029 China.
  • Institute of Image Communication and Network Engineering, Shanghai Jiao Tong University, 800 Dongchuan RD, Shanghai, 200240 China.
  • School of Life Sciences, Beijing University of Chinese Medicine, Beijing, 100029 China.
  • State Key Laboratory of Genetic Engineering, Collaborative Innovation Center for Genetics and Development, Human Phenome Institute, Fudan University, Shanghai, 200433 China.
  • Ministry of Education Key Laboratory of Contemporary Anthropology, Department of Anthropology and Human Genetics, School of Life Sciences, Fudan University, Shanghai, 200433 China.

ORCID-Profile: Ting Li, Ling Zuo, Pengyu Wang, Liangfu Yang, Xu Wang, Jingze Tan, Yajun Yang, Jiucun Wang, Li Jin, Qianqian Peng, Guoqing Zhang, Sijia Wang

Förderung

  • the Strategic Priority Research Program of the Chinese Academy of Sciences
  • Youth Innovation Promotion Association of the Chinese Academy of Sciences
  • CAS Young Team Program for Stable Support of Basic 488 Research
  • Hutian Scholar of Beijing University of Chinese Medicine
  • CAS Interdisciplinary Innovation Team
  • Shanghai Municipal Science and Technology Major Project
  • Science and Technology Commission of Shanghai Municipality
  • National Natural Science Foundation of China

Zitieren

APA

Li, T., Zuo, L., Wang, P., Yang, L., Liu, Z., Wang, X., Tan, J., Yang, Y., Wang, J., Zhou, Y., Jin, L., Zhai, G., Chen, J., Peng, Q., Zhang, G., & Wang, S. (2025). TonguExpert: A Deep Learning-Based Algorithm Platform for Fine-Grained Extraction and Classification of Tongue Phenotypes. Phenomics, 5(2), 109-122. https://doi.org/10.1007/s43657-024-00210-9

Vancouver

Li T, Zuo L, Wang P, Yang L, Liu Z, Wang X, et al. TonguExpert: A Deep Learning-Based Algorithm Platform for Fine-Grained Extraction and Classification of Tongue Phenotypes. Phenomics. 2025;5(2):109-122. doi:10.1007/s43657-024-00210-9

BibTeX
@article{Li2025,
  author = {Li, Ting and Zuo, Ling and Wang, Pengyu and Yang, Liangfu and Liu, Zijia and Wang, Xu and Tan, Jingze and Yang, Yajun and Wang, Jiucun and Zhou, Yong and Jin, Li and Zhai, Guangtao and Chen, Jianxin and Peng, Qianqian and Zhang, Guoqing and Wang, Sijia},
  title = {TonguExpert: A Deep Learning-Based Algorithm Platform for Fine-Grained Extraction and Classification of Tongue Phenotypes},
  journal = {Phenomics},
  year = {2025},
  volume = {5},
  number = {2},
  pages = {109--122},
  doi = {10.1007/s43657-024-00210-9}
}
Kostenlos starten →