MEAT-SAM: More Efficient Automated Tongue Segmentation Model
In Traditional Chinese Medicine (TCM) diagnostics, the appearance of the tongue is a crucial indicator of health. TCM practitioners traditionally assess the tongue’s shape, color, texture, and other features to aid diagnosis. With advancements in technology, digitizing and analyzing tongu...
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2025-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10816397/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841542519919214592 |
|---|---|
| author | Fudong Zhong Chuanbo Qin Yue Feng Junying Zeng Xudong Jia Fuguang Zhong Jun Luo Min Yang |
| author_facet | Fudong Zhong Chuanbo Qin Yue Feng Junying Zeng Xudong Jia Fuguang Zhong Jun Luo Min Yang |
| author_sort | Fudong Zhong |
| collection | DOAJ |
| description | In Traditional Chinese Medicine (TCM) diagnostics, the appearance of the tongue is a crucial indicator of health. TCM practitioners traditionally assess the tongue’s shape, color, texture, and other features to aid diagnosis. With advancements in technology, digitizing and analyzing tongue images using computer has become possible, making tongue image segmentation an important step in realizing automated tongue diagnosis. While existing network models have shown good results, they often struggle with tongue images against complex backgrounds, particularly on resource-limited edge devices. To tackle this challenge, this paper introduces a novel, more efficient automated tongue image segmentation model (MEAT-SAM). MEAT-SAM leverages a lightweight large model, a first in the field of tongue image segmentation. Compared to previous models, MEAT-SAM reduces the overall model parameters, improves segmentation speed, and enables operation on more resource-constrained edge devices. Despite its efficiency, MEAT-SAM maintains performance close to the state-of-the-art (SOTA) even with complex tongue image backgrounds. Tested on three different datasets (TongueDataset01, TongueDataset02, TongueDataset03), MEAT-SAM achieved IoU of 96.63%, 95.58%, and 95.07%, demonstrating excellent generalization and robustness against various complex background conditions in tongue images. Furthermore, MEAT-SAM can run effectively on the computationally limited Jetson Nano single-board computer, achieving similar segmentation effects as in experimental testing. |
| format | Article |
| id | doaj-art-09a318ad2a9d45c1b70ee47478f9e1b4 |
| institution | Kabale University |
| issn | 2169-3536 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj-art-09a318ad2a9d45c1b70ee47478f9e1b42025-01-14T00:01:01ZengIEEEIEEE Access2169-35362025-01-01135175519210.1109/ACCESS.2024.352296110816397MEAT-SAM: More Efficient Automated Tongue Segmentation ModelFudong Zhong0Chuanbo Qin1Yue Feng2Junying Zeng3https://orcid.org/0000-0002-7559-0637Xudong Jia4https://orcid.org/0000-0001-7911-8869Fuguang Zhong5Jun Luo6Min Yang7https://orcid.org/0009-0009-6044-8513School of Electronics and Information Engineering, Wuyi University, Jiangmen, ChinaSchool of Electronics and Information Engineering, Wuyi University, Jiangmen, ChinaSchool of Electronics and Information Engineering, Wuyi University, Jiangmen, ChinaSchool of Electronics and Information Engineering, Wuyi University, Jiangmen, ChinaSchool of Electronics and Information Engineering, Wuyi University, Jiangmen, ChinaSchool of Electronics and Information Engineering, Wuyi University, Jiangmen, ChinaSchool of Economics and Management, Wuyi University, Jiangmen, ChinaSchool of Electronics and Information Engineering, Wuyi University, Jiangmen, ChinaIn Traditional Chinese Medicine (TCM) diagnostics, the appearance of the tongue is a crucial indicator of health. TCM practitioners traditionally assess the tongue’s shape, color, texture, and other features to aid diagnosis. With advancements in technology, digitizing and analyzing tongue images using computer has become possible, making tongue image segmentation an important step in realizing automated tongue diagnosis. While existing network models have shown good results, they often struggle with tongue images against complex backgrounds, particularly on resource-limited edge devices. To tackle this challenge, this paper introduces a novel, more efficient automated tongue image segmentation model (MEAT-SAM). MEAT-SAM leverages a lightweight large model, a first in the field of tongue image segmentation. Compared to previous models, MEAT-SAM reduces the overall model parameters, improves segmentation speed, and enables operation on more resource-constrained edge devices. Despite its efficiency, MEAT-SAM maintains performance close to the state-of-the-art (SOTA) even with complex tongue image backgrounds. Tested on three different datasets (TongueDataset01, TongueDataset02, TongueDataset03), MEAT-SAM achieved IoU of 96.63%, 95.58%, and 95.07%, demonstrating excellent generalization and robustness against various complex background conditions in tongue images. Furthermore, MEAT-SAM can run effectively on the computationally limited Jetson Nano single-board computer, achieving similar segmentation effects as in experimental testing.https://ieeexplore.ieee.org/document/10816397/Automatedefficientlightweightimage segmentationrobustness |
| spellingShingle | Fudong Zhong Chuanbo Qin Yue Feng Junying Zeng Xudong Jia Fuguang Zhong Jun Luo Min Yang MEAT-SAM: More Efficient Automated Tongue Segmentation Model IEEE Access Automated efficient lightweight image segmentation robustness |
| title | MEAT-SAM: More Efficient Automated Tongue Segmentation Model |
| title_full | MEAT-SAM: More Efficient Automated Tongue Segmentation Model |
| title_fullStr | MEAT-SAM: More Efficient Automated Tongue Segmentation Model |
| title_full_unstemmed | MEAT-SAM: More Efficient Automated Tongue Segmentation Model |
| title_short | MEAT-SAM: More Efficient Automated Tongue Segmentation Model |
| title_sort | meat sam more efficient automated tongue segmentation model |
| topic | Automated efficient lightweight image segmentation robustness |
| url | https://ieeexplore.ieee.org/document/10816397/ |
| work_keys_str_mv | AT fudongzhong meatsammoreefficientautomatedtonguesegmentationmodel AT chuanboqin meatsammoreefficientautomatedtonguesegmentationmodel AT yuefeng meatsammoreefficientautomatedtonguesegmentationmodel AT junyingzeng meatsammoreefficientautomatedtonguesegmentationmodel AT xudongjia meatsammoreefficientautomatedtonguesegmentationmodel AT fuguangzhong meatsammoreefficientautomatedtonguesegmentationmodel AT junluo meatsammoreefficientautomatedtonguesegmentationmodel AT minyang meatsammoreefficientautomatedtonguesegmentationmodel |