EUVIMEDEUVIMED entdecken
Crossref

A LIGHTWEIGHT METHOD FOR TOOTH-MARKED TONGUE RECOGNITION BASED ON CONVOLUTIONAL NEURAL NETWORKS

SIYAO LU, HUARONG ZENG, ZHIFU KE, LINGXUAN CHEN

Journal of Mechanics in Medicine and Biology · 30.10.2026

DOI: 10.1142/s0219519426401196 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Mechanics in Medicine and Biology, online erschienen am 30.10.2026. Verfasst von SIYAO LU und 3 weiteren Autor:innen. Die Arbeit nennt 24 Literaturangaben. Gefördert von: Xiamen Medical and Health Guidance, Traditional Chinese Medicine Foundation of Xiamen.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The tooth-marked tongue is an important objective indicator in Traditional Chinese Medicine (TCM) tongue diagnosis, and its automatic recognition provides a computationally inexpensive route toward instrumented tongue inspection. To address the problem that existing tooth-mark recognition methods have large model sizes and high computational cost, this paper proposes a lightweight tooth-marked tongue recognition method. The method performs binary tooth-mark classification on pre-segmented tongue images: a lightweight convolutional neural network, MobileNetV3-Small, is combined with transfer learning and data augmentation to perform binary tooth-mark classification, while a class-weighted cross-entropy loss is introduced to alleviate class imbalance. Experiments on a public tooth-marked tongue dataset (1250 images), evaluated under a stratified 70:15:15 partition in which the test set is held out from model selection and averaged over 10 repetitions, show that the proposed method achieves an accuracy of [Formula: see text] and an F1 of [Formula: see text], with only 1.52[Formula: see text]M parameters (about one seventh of ResNet18), 0.061 GFLOPs, and a model size of 6.2[Formula: see text]MB, substantially reducing model complexity while maintaining comparable accuracy. Ablation studies identify transfer learning as the decisive component, and Grad-CAM visualization further shows that the model focuses on the tongue edge where tooth marks appear, indicating good interpretability.

Förderung

  • Xiamen Medical and Health Guidance
  • Traditional Chinese Medicine Foundation of Xiamen

Zitieren

APA

LU, S., ZENG, H., KE, Z., & CHEN, L. (2026). A LIGHTWEIGHT METHOD FOR TOOTH-MARKED TONGUE RECOGNITION BASED ON CONVOLUTIONAL NEURAL NETWORKS. Journal of Mechanics in Medicine and Biology. https://doi.org/10.1142/s0219519426401196

Vancouver

LU S, ZENG H, KE Z, CHEN L. A LIGHTWEIGHT METHOD FOR TOOTH-MARKED TONGUE RECOGNITION BASED ON CONVOLUTIONAL NEURAL NETWORKS. Journal of Mechanics in Medicine and Biology. 2026. doi:10.1142/s0219519426401196

BibTeX
@article{LU2026,
  author = {LU, SIYAO and ZENG, HUARONG and KE, ZHIFU and CHEN, LINGXUAN},
  title = {A LIGHTWEIGHT METHOD FOR TOOTH-MARKED TONGUE RECOGNITION BASED ON CONVOLUTIONAL NEURAL NETWORKS},
  journal = {Journal of Mechanics in Medicine and Biology},
  year = {2026},
  doi = {10.1142/s0219519426401196}
}
Kostenlos starten →