A Novel Tongue Coating Segmentation Method Based on Improved TransUNet

Overview

Journal Sensors (Basel)

Publisher MDPI

Specialty Biotechnology

Date 2024 Jul 27

PMID 39065853

Authors

Jiaze Wu

Zijian Li

Yiheng Cai

Hao Liang

Long Zhou

Ming Chen

Jing Guan

Affiliations

Soon will be listed here.

Abstract

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.

References

Kim J, Lee H, Kim H, Kim J, Kim K . Differences in the Tongue Features of Primary Dysmenorrhea Patients and Controls over a Normal Menstrual Cycle. Evid Based Complement Alternat Med. 2017; 2017:6435702. PMC: 5469986. DOI: 10.1155/2017/6435702. View

Shi Y, Guo D, Chun Y, Liu J, Liu L, Tu L . A lung cancer risk warning model based on tongue images. Front Physiol. 2023; 14:1154294. PMC: 10267397. DOI: 10.3389/fphys.2023.1154294. View

Zhang Y, Zhao H, Guo Y, Meng Y, Yu S, Pan B . Relationship between thick or greasy tongue-coating microbiota and tongue diagnosis in patients with primary liver cancer. Front Microbiol. 2023; 13:903616. PMC: 9835093. DOI: 10.3389/fmicb.2022.903616. View

Ali Mohammed M, Al Kawas S, Al-Qadhi G . Tongue-coating microbiome as a cancer predictor: A scoping review. Arch Oral Biol. 2021; 132:105271. DOI: 10.1016/j.archoralbio.2021.105271. View

Chen J, Sun Y, Li J, Lyu M, Yuan L, Sun J . In-depth metaproteomics analysis of tongue coating for gastric cancer: a multicenter diagnostic research study. Microbiome. 2024; 12(1):6. PMC: 10773145. DOI: 10.1186/s40168-023-01730-8. View

Zhou Z, Siddiquee M, Tajbakhsh N, Liang J . UNet++: A Nested U-Net Architecture for Medical Image Segmentation. Deep Learn Med Image Anal Multimodal Learn Clin Decis Support (2018). 2020; 11045:3-11. PMC: 7329239. DOI: 10.1007/978-3-030-00889-5_1. View

Jiang T, Lu Z, Hu X, Zeng L, Ma X, Huang J . Deep Learning Multi-label Tongue Image Analysis and Its Application in a Population Undergoing Routine Medical Checkup. Evid Based Complement Alternat Med. 2022; 2022:3384209. PMC: 9536899. DOI: 10.1155/2022/3384209. View

Zhang Z, Wu C, Coleman S, Kerr D . DENSE-INception U-net for medical image segmentation. Comput Methods Programs Biomed. 2020; 192:105395. DOI: 10.1016/j.cmpb.2020.105395. View

Li Z, Zheng Y, Shan D, Yang S, Li Q, Wang B . ScribFormer: Transformer Makes CNN Work Better for Scribble-Based Medical Image Segmentation. IEEE Trans Med Imaging. 2024; 43(6):2254-2265. DOI: 10.1109/TMI.2024.3363190. View

10.

Hu Y, Wen G, Luo M, Yang P, Dai D, Yu Z . Fully-channel regional attention network for disease-location recognition with tongue images. Artif Intell Med. 2021; 118:102110. DOI: 10.1016/j.artmed.2021.102110. View

11.

Yan J, Cai J, Xu Z, Guo R, Zhou W, Yan H . Tongue crack recognition using segmentation based deep learning. Sci Rep. 2023; 13(1):511. PMC: 9832139. DOI: 10.1038/s41598-022-27210-x. View

12.

Li J, Cui L, Tu L, Hu X, Wang S, Shi Y . Research of the Distribution of Tongue Features of Diabetic Population Based on Unsupervised Learning Technology. Evid Based Complement Alternat Med. 2022; 2022:7684714. PMC: 9276481. DOI: 10.1155/2022/7684714. View

13.

Hu M, Lan K, Fang W, Huang Y, Ho T, Lin C . Automated tongue diagnosis on the smartphone and its applications. Comput Methods Programs Biomed. 2018; 174:51-64. DOI: 10.1016/j.cmpb.2017.12.029. View

14.

Kusakunniran W, Borwarnginn P, Karnjanapreechakorn S, Thongkanchorn K, Ritthipravat P, Tuakta P . Encoder-decoder network with RMP for tongue segmentation. Med Biol Eng Comput. 2023; 61(5):1193-1207. DOI: 10.1007/s11517-022-02761-3. View

15.

Wang X, Wang X, Lou Y, Liu J, Huo S, Pang X . Constructing tongue coating recognition model using deep transfer learning to assist syndrome diagnosis and its potential in noninvasive ethnopharmacological evaluation. J Ethnopharmacol. 2021; 285:114905. DOI: 10.1016/j.jep.2021.114905. View

16.

Quan Y, Zhang D, Zhang L, Tang J . Centralized Feature Pyramid for Object Detection. IEEE Trans Image Process. 2023; 32:4341-4354. DOI: 10.1109/TIP.2023.3297408. View

17.

Han S, Yang X, Qi Q, Pan Y, Chen Y, Shen J . Potential screening and early diagnosis method for cancer: Tongue diagnosis. Int J Oncol. 2016; 48(6):2257-64. PMC: 4864042. DOI: 10.3892/ijo.2016.3466. View

18.

Badrinarayanan V, Kendall A, Cipolla R . SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation. IEEE Trans Pattern Anal Mach Intell. 2017; 39(12):2481-2495. DOI: 10.1109/TPAMI.2016.2644615. View

19.

Chen L, Papandreou G, Kokkinos I, Murphy K, Yuille A . DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs. IEEE Trans Pattern Anal Mach Intell. 2017; 40(4):834-848. DOI: 10.1109/TPAMI.2017.2699184. View

20.

Xu H, Chen X, Qian P, Li F . A two-stage segmentation of sublingual veins based on compact fully convolutional networks for Traditional Chinese Medicine images. Health Inf Sci Syst. 2023; 11(1):19. PMC: 10079802. DOI: 10.1007/s13755-023-00214-1. View