Tongue-LiteSAM: A Lightweight Model for Tongue Image Segmentation With Zero-Shot
Objective: Tongue image segmentation is a crucial step in the intelligent recognition of tongue diagnosis in Traditional Chinese Medicine (TCM). Existing deep learning-based tongue image segmentation models face issues such as poor versatility and insufficient expressiveness in zero-shot tasks. This...
Saved in:
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2025-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10838509/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832590349540786176 |
|---|---|
| author | Daiqing Tan Hao Zang Xinyue Zhang Han Gao Ji Wang Zaijian Wang Xing Zhai Huixia Li Yan Tang Aiqing Han |
| author_facet | Daiqing Tan Hao Zang Xinyue Zhang Han Gao Ji Wang Zaijian Wang Xing Zhai Huixia Li Yan Tang Aiqing Han |
| author_sort | Daiqing Tan |
| collection | DOAJ |
| description | Objective: Tongue image segmentation is a crucial step in the intelligent recognition of tongue diagnosis in Traditional Chinese Medicine (TCM). Existing deep learning-based tongue image segmentation models face issues such as poor versatility and insufficient expressiveness in zero-shot tasks. This study aims to construct an efficient model with zero-shot suitable for tongue image segmentation in TCM. Methods: We developed the Tongue-LiteSAM model by improving the SAM (Segment Anything Model) framework to suit tongue segmentation. Based on the basic SAM model, the improvement involved modifying the image encoder by integrating two lightweight ViT-Tiny image encoders, effectively reducing the model’s parameter count. Additionally, data perturbation techniques were employed to enhance the zero-shot segmentation capability of the model and ensure robust performance across different data sources. Results: Experiments conducted on six distinct tongue image datasets demonstrated that the Tongue-LiteSAM model outperformed traditional convolutional neural network-based models and transformers, the original SAM model, and other related improved models in tongue image segmentation tasks. Conclusion: The Tongue-LiteSAM model provides a more objective and consistent solution for tongue diagnosis, and has better zero-shot segmentation capabilities. By optimizing the model structure and data processing strategies, the accuracy and practicality of tongue diagnosis models are effectively improved, offering new technical support for the modernization and precision of TCM tongue diagnosis. |
| format | Article |
| id | doaj-art-a2b5d4539bea40b9b3cf8399d134d2e9 |
| institution | Kabale University |
| issn | 2169-3536 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj-art-a2b5d4539bea40b9b3cf8399d134d2e92025-01-24T00:01:14ZengIEEEIEEE Access2169-35362025-01-0113116891170310.1109/ACCESS.2025.352865810838509Tongue-LiteSAM: A Lightweight Model for Tongue Image Segmentation With Zero-ShotDaiqing Tan0https://orcid.org/0009-0007-1559-7785Hao Zang1https://orcid.org/0009-0002-8413-0402Xinyue Zhang2Han Gao3https://orcid.org/0009-0007-5410-8884Ji Wang4Zaijian Wang5Xing Zhai6Huixia Li7Yan Tang8https://orcid.org/0009-0009-4023-7700Aiqing Han9https://orcid.org/0000-0002-1087-0873School of Management, Beijing University of Chinese Medicine, Beijing, ChinaSchool of Management, Beijing University of Chinese Medicine, Beijing, ChinaSchool of Nursing, Beijing University of Chinese Medicine, Beijing, ChinaSchool of Humanities, Beijing University of Chinese Medicine, Beijing, ChinaNational Institute of TCM Constitution and Prevention Medicine, Beijing University of Chinese Medicine, Beijing, ChinaThird Affiliated Hospital of Beijing University of Chinese Medicine, Beijing, ChinaSchool of Management, Beijing University of Chinese Medicine, Beijing, ChinaThird Affiliated Hospital of Beijing University of Chinese Medicine, Beijing, ChinaSchool of Management, Beijing University of Chinese Medicine, Beijing, ChinaSchool of Management, Beijing University of Chinese Medicine, Beijing, ChinaObjective: Tongue image segmentation is a crucial step in the intelligent recognition of tongue diagnosis in Traditional Chinese Medicine (TCM). Existing deep learning-based tongue image segmentation models face issues such as poor versatility and insufficient expressiveness in zero-shot tasks. This study aims to construct an efficient model with zero-shot suitable for tongue image segmentation in TCM. Methods: We developed the Tongue-LiteSAM model by improving the SAM (Segment Anything Model) framework to suit tongue segmentation. Based on the basic SAM model, the improvement involved modifying the image encoder by integrating two lightweight ViT-Tiny image encoders, effectively reducing the model’s parameter count. Additionally, data perturbation techniques were employed to enhance the zero-shot segmentation capability of the model and ensure robust performance across different data sources. Results: Experiments conducted on six distinct tongue image datasets demonstrated that the Tongue-LiteSAM model outperformed traditional convolutional neural network-based models and transformers, the original SAM model, and other related improved models in tongue image segmentation tasks. Conclusion: The Tongue-LiteSAM model provides a more objective and consistent solution for tongue diagnosis, and has better zero-shot segmentation capabilities. By optimizing the model structure and data processing strategies, the accuracy and practicality of tongue diagnosis models are effectively improved, offering new technical support for the modernization and precision of TCM tongue diagnosis.https://ieeexplore.ieee.org/document/10838509/Segment anything modeltongue image segmentationtraditional Chinese medicine |
| spellingShingle | Daiqing Tan Hao Zang Xinyue Zhang Han Gao Ji Wang Zaijian Wang Xing Zhai Huixia Li Yan Tang Aiqing Han Tongue-LiteSAM: A Lightweight Model for Tongue Image Segmentation With Zero-Shot IEEE Access Segment anything model tongue image segmentation traditional Chinese medicine |
| title | Tongue-LiteSAM: A Lightweight Model for Tongue Image Segmentation With Zero-Shot |
| title_full | Tongue-LiteSAM: A Lightweight Model for Tongue Image Segmentation With Zero-Shot |
| title_fullStr | Tongue-LiteSAM: A Lightweight Model for Tongue Image Segmentation With Zero-Shot |
| title_full_unstemmed | Tongue-LiteSAM: A Lightweight Model for Tongue Image Segmentation With Zero-Shot |
| title_short | Tongue-LiteSAM: A Lightweight Model for Tongue Image Segmentation With Zero-Shot |
| title_sort | tongue litesam a lightweight model for tongue image segmentation with zero shot |
| topic | Segment anything model tongue image segmentation traditional Chinese medicine |
| url | https://ieeexplore.ieee.org/document/10838509/ |
| work_keys_str_mv | AT daiqingtan tonguelitesamalightweightmodelfortongueimagesegmentationwithzeroshot AT haozang tonguelitesamalightweightmodelfortongueimagesegmentationwithzeroshot AT xinyuezhang tonguelitesamalightweightmodelfortongueimagesegmentationwithzeroshot AT hangao tonguelitesamalightweightmodelfortongueimagesegmentationwithzeroshot AT jiwang tonguelitesamalightweightmodelfortongueimagesegmentationwithzeroshot AT zaijianwang tonguelitesamalightweightmodelfortongueimagesegmentationwithzeroshot AT xingzhai tonguelitesamalightweightmodelfortongueimagesegmentationwithzeroshot AT huixiali tonguelitesamalightweightmodelfortongueimagesegmentationwithzeroshot AT yantang tonguelitesamalightweightmodelfortongueimagesegmentationwithzeroshot AT aiqinghan tonguelitesamalightweightmodelfortongueimagesegmentationwithzeroshot |