EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

A Novel Tongue Coating Segmentation Method Based on Improved TransUNet

Jiaze Wu iD, Zijian Li iD, Yiheng Cai iD, Hao Liang iD, Long Zhou, Ming Chen, Jing Guan

Sensors · 2024

DOI: 10.3390/s24144455 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, 2024. Verfasst von Jiaze Wu und 6 weiteren Autor:innen. Beteiligte Einrichtung: School of Traditional Chinese Medicine, Beijing University of Chinese Medicine, Beijing 102488, China. Hauptthemen laut MEDLINE: Tongue, Neural Networks, Computer, Image Processing, Computer-Assisted. Die Arbeit wurde bisher 10-mal zitiert (Crossref) und nennt 46 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Key Research and Development Program of China, National Natural Science Foundation of China, Leading Research Project of Hunan University of Chinese Medicine.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

As an important part of the tongue, the tongue coating is closely associated with different disorders and has major diagnostic benefits. This study aims to construct a neural network model that can perform complex tongue coating segmentation. This addresses the issue of tongue coating segmentation in intelligent tongue diagnosis automation.

Method

This work proposes an improved TransUNet to segment the tongue coating. We introduced a transformer as a self-attention mechanism to capture the semantic information in the high-level features of the encoder. At the same time, the subtraction feature pyramid (SFP) and visual regional enhancer (VRE) were constructed to minimize the redundant information transmitted by skip connections and improve the spatial detail information in the low-level features of the encoder.

Results

Comparative and ablation experimental findings indicate that our model has an accuracy of 96.36%, a precision of 96.26%, a dice of 96.76%, a recall of 97.43%, and an IoU of 93.81%. Unlike the reference model, our model achieves the best segmentation effect.

Conclusion

The improved TransUNet proposed here can achieve precise segmentation of complex tongue images. This provides an effective technique for the automatic extraction in images of the tongue coating, contributing to the automation and accuracy of tongue diagnosis.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

TongueNeural Networks, ComputerImage Processing, Computer-AssistedHumansAlgorithms

Stichwörter der Autor:innen

TransUNetcomputer visiondeep learningmedical image segmentationtongue diagnosis

Autor:innen und Institutionen

  • School of Traditional Chinese Medicine, Beijing University of Chinese Medicine, Beijing 102488, China.
  • Department of Information, Beijing University of Technology, Beijing 100124, China.
  • School of Chinese Medicine, Hunan University of Chinese Medicine, Changsha 410208, China.

ORCID-Profile: Jiaze Wu, Zijian Li, Yiheng Cai, Hao Liang

Förderung

  • National Key Research and Development Program of China
  • National Natural Science Foundation of China
  • Leading Research Project of Hunan University of Chinese Medicine

Zitieren

APA

Wu, J., Li, Z., Cai, Y., Liang, H., Zhou, L., Chen, M., & Guan, J. (2024). A Novel Tongue Coating Segmentation Method Based on Improved TransUNet. Sensors. https://doi.org/10.3390/s24144455

Vancouver

Wu J, Li Z, Cai Y, Liang H, Zhou L, Chen M, et al. A Novel Tongue Coating Segmentation Method Based on Improved TransUNet. Sensors. 2024. doi:10.3390/s24144455

BibTeX
@article{Wu2024,
  author = {Wu, Jiaze and Li, Zijian and Cai, Yiheng and Liang, Hao and Zhou, Long and Chen, Ming and Guan, Jing},
  title = {A Novel Tongue Coating Segmentation Method Based on Improved TransUNet},
  journal = {Sensors},
  year = {2024},
  doi = {10.3390/s24144455}
}
Kostenlos starten →