CNN-Based Tongue Image Segmentation in Traditional Chinese Medicine

Dechao Xu; Dingcheng Tian

doi:10.53941/aim.2025.100004

Abstract

Tongue image segmentation is a key component of the intelligent diagnosis in Traditional Chinese Medicine (TCM), and its accuracy directly affects the subsequent classification and diagnostic results. However, current research faces challenges due to data scarcity and limited model adaptability. The lack of publicly available tongue image datasets restricts the model’s generalization ability, while traditional algorithms are highly sensitive to lighting and posture changes. Moreover, general deep learning models have not been optimized for the characteristics of blurry tongue edges and low contrast background, which often leads to loss of details or over-segmentation. To address these issues, this study has constructed a high-quality dataset containing 1405 tongue images and proposes a lightweight tongue image segmentation network (TSNet). TSNet employs depthwise separable convolutions to reduce computational cost, introduces a Parallel Atrous Spatial Pyramid Pooling (PASPP) module to extract multi-scale features and handle blurred boundaries, and incorporates a Boundary Adjustment (BA) module to enhance edge segmentation accuracy. Experimental results show that TSNet achieves a mean Intersection over Union (mIoU) of 97.20% while using fewer parameters than mainstream models. While preserving tongue details, it effectively reduces the number of parameters, providing an efficient solution for tongue image segmentation in TCM.

References

1.
Tian, D.; Chen, W.; Xu, D.; et al. A review of traditional Chinese medicine diagnosis using machine learning: Inspection, auscultation-olfaction, inquiry, and palpation. Comput. Biol. Med. 2024, 170, 108074.
2.
Balasubramaniyan, S.; Jeyakumar, V.; Nachimuthu, D.S. Panoramic tongue imaging and deep convolutional machine learning model for diabetes diagnosis in humans. Sci. Rep. 2022, 12, 186.
3.
Dong SU, I.; Zhang, L.; Fei, Y. Data-driven based four examinations in TCM: A survey. Digit. Chin. Med. 2022, 5, 377–385.
4.
Wu, K.; Zhang, D. Robust tongue segmentation by fusing region-based and edge-based approaches. Expert Syst. Appl. 2015, 42, 8027–8038.
5.
Cao, H.; Wang, Y.; Chen, J.; et al. Swin-unet: Unet-like pure transformer for medical image segmentation. In Proceedings of the European Conference on Computer Vision, Tel Aviv, Israel, 23–27 October 2022; Springer Nature: Cham, Switzerland, 2022; pp. 205–218.
6.
Zhu, Z.; Liu, L.; Free, R.C.; et al. OPT-CO: Optimizing pre-trained transformer models for efficient COVID-19 classification with stochastic configuration networks. Inf. Sci. 2024, 680, 121141.
7.
Lu, S.Y.; Zhu, Z.; Tang, Y.; et al. CTBViT: A novel ViT for tuberculosis classification with efficient block and randomized classifier. Biomed. Signal Process. Control 2025, 100, 106981.
8.
Lu, S.Y.; Zhang, Y.D.; Yao, Y.D. A regularized transformer with adaptive token fusion for Alzheimer’s disease diagnosis in brain magnetic resonance images. Eng. Appl. Artif. Intell. 2025, 155, 111058.
9.
Zhu, Z.; Ren, Z.; Lu, S.; et al. DLBCNet: A deep learning network for classifying blood cells. Big Data Cogn. Comput. 2023, 7, 75.
10.
Huang, X.; Zhang, H.; Zhuo, L.; et al. TISNet-Enhanced fully convolutional network with encoder-decoder structure for tongue image segmentation in Traditional Chinese Medicine. Comput. Math. Methods Med. 2020, 2020, 6029258.
11.
Yao, L.; Xu, Y.; Zhang, S.; et al. HPA-UNet: A Hybrid Post-Processing Attention U-Net for Tongue Segmentation. IEEE J. Biomed. Health Inform. 2024. https://doi.org/10.1109/JBHI.2024.3446623
12.
Jia, G.; Cui, Z.; Fei, Q. QA-TSN: QuickAccurate Tongue Segmentation Net. Knowl. -Based Syst. 2025, 307, 112648.
13.
Huang, Z.; Huang, R.; Zhang, J.; et al. Attention guided tongue segmentation with geometric knowledge in complex environments. Biomed. Signal Process. Control 2025, 104, 107426.
14.
Chen, L.C.; Papandreou, G.; Kokkinos, I.; et al. Deeplab: Semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected crfs. IEEE Trans. Pattern Anal. Mach. Intell. 2017, 40, 834–848.
15.
Badrinarayanan, V.; Kendall, A.; Cipolla, R. Segnet: A deep convolutional encoder-decoder architecture for image segmentation. IEEE Trans. Pattern Anal. Mach. Intell. 2017, 39, 2481–2495.
16.
BioHit. Tongueimagedataset. 2014. Available online: https://github.com/BioHit/TongeImageDataset (accessed on 1 August 2024).
17.
Long, J.; Shelhamer, E.; Darrell, T. Fully convolutional networks for semantic segmentation. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Boston, MA, USA, 7–12 June 2015; pp. 3431–3440.
18.
Peng, C.; Zhang, X.; Yu, G.; et al. Large kernel matters—Improve semantic segmentation by global convolutional network. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, HI, USA, 21–26 July 2017; pp. 4353–4361.
19.
Quan, T.M.; Hildebrand, D.G.C.; Jeong, W.K. Fusionnet: A deep fully residual convolutional neural network for image segmentation in connectomics. Front. Comput. Sci. 2021, 3, 613981.
20.
Chen, L.C.; Zhu, Y.; Papandreou, G.; et al. Encoder-decoder with atrous separable convolution for semantic image segmentation. In Proceedings of the European Conference on Computer Vision (ECCV), Munich, Germany, 8–14 September 2018; pp. 801–818.
21.
Yu, C.; Wang, J.; Peng, C.; et al. Bisenet: Bilateral segmentation network for real-time semantic segmentation. In Proceedings of the European Conference on Computer Vision (ECCV), Munich, Germany, 8–14 September 2018; pp. 325–341.

Scilight Press

Author Information

Abstract

Keywords

References

About Scilight

Journals

Publishing Policies

Contact Us