EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Prior-guided feature fusion for tongue image-based gastrointestinal disease auxiliary diagnosis

Ying Zhu, Zili Zhou, Yuchao Cheng, Jiayu Zhang, Hong Mao, Ling He, Jing Zhang

Frontiers in Physiology · 29.04.2026 · 17

DOI: 10.3389/fphys.2026.1811717 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Frontiers in Physiology, online erschienen am 29.04.2026. Verfasst von Ying Zhu und 6 weiteren Autor:innen. Beteiligte Einrichtung: School of Biomedical Engineering, Sichuan University, Chengdu, China. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 37 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Sichuan Provincial Science and Technology Support Program.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Introduction

Gastrointestinal diseases (GIDs) are a major global health burden, but traditional endoscopic screening faces limitations due to its invasiveness. Tongue image analysis offers a non‑invasive alternative but is subjective, relying on clinical experience.

Methods

To address this, we propose a novel computational framework that synergistically integrates clinical prior knowledge with data-driven learning for non-invasive screening via tongue image analysis. Our framework introduces two key innovations: a TransNeXt hybrid backbone to extract comprehensive local and global tongue features, and a Channel Attention Gated Fusion module that performs asymmetric feature recalibration and prior-guided adaptive integration.

Results

Evaluated on a multicenter gastrointestinal disease tongue image dataset, our framework demonstrates robust performance, with an SVM classifier achieving an accuracy of 0.874, a Macro-F1 score of 0.879, and an AUC of 0.898.

Discussion

Ablation studies confirm the critical synergy between multimodal feature fusion and data augmentation. This work establishes an effective and objective computational solution for tongue diagnosis, with strong potential for clinical translation as an auxiliary screening tool.

Schlagwörter

Stichwörter der Autor:innen

channel attentioncomputer-aided diagnosisgastrointestinal diseasesgated feature fusiontongue image analysis

Autor:innen und Institutionen

  • School of Biomedical Engineering, Sichuan University, Chengdu, China.
  • Department of Gastroenterology, Sichuan Provincial Second Traditional Chinese Medicine Hospital, Chengdu, China.
  • School of Business, Singapore University of Social Sciences, Singapore, Singapore.
  • Department of Anorectal Surgery, Sichuan Provincial Second Traditional Chinese Medicine Hospital, Chengdu, China.

Förderung

  • Sichuan Provincial Science and Technology Support Program

Zitieren

APA

Zhu, Y., Zhou, Z., Cheng, Y., Zhang, J., Mao, H., He, L., & Zhang, J. (2026). Prior-guided feature fusion for tongue image-based gastrointestinal disease auxiliary diagnosis. Frontiers in Physiology, 17. https://doi.org/10.3389/fphys.2026.1811717

Vancouver

Zhu Y, Zhou Z, Cheng Y, Zhang J, Mao H, He L, et al. Prior-guided feature fusion for tongue image-based gastrointestinal disease auxiliary diagnosis. Frontiers in Physiology. 2026;17. doi:10.3389/fphys.2026.1811717

BibTeX
@article{Zhu2026,
  author = {Zhu, Ying and Zhou, Zili and Cheng, Yuchao and Zhang, Jiayu and Mao, Hong and He, Ling and Zhang, Jing},
  title = {Prior-guided feature fusion for tongue image-based gastrointestinal disease auxiliary diagnosis},
  journal = {Frontiers in Physiology},
  year = {2026},
  volume = {17},
  doi = {10.3389/fphys.2026.1811717}
}
Kostenlos starten →