Constructing an Artificial Intelligent Deep Neural Network Battery for Tongue Region Segmentation and Tongue Characteristic Recognition
Objective: This study aimed to construct a two-stage deep learning framework to segment and recognize tongue images and enhance the accuracy and efficiency of artificial intelligence (AI) tongue diagnosis in traditional Chinese medicine (TCM). Materials and Methods: Five hundred and ninety-four tong...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wolters Kluwer Medknow Publications
2024-12-01
|
| Series: | World Journal of Traditional Chinese Medicine |
| Subjects: | |
| Online Access: | https://journals.lww.com/10.4103/wjtcm.wjtcm_92_24 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841526949557567488 |
|---|---|
| author | Tian-Xing Yi Jian-Xin Chen Xue-Song Wang Meng-Jie Kou Qing-Qiong Deng Xu Wang |
| author_facet | Tian-Xing Yi Jian-Xin Chen Xue-Song Wang Meng-Jie Kou Qing-Qiong Deng Xu Wang |
| author_sort | Tian-Xing Yi |
| collection | DOAJ |
| description | Objective:
This study aimed to construct a two-stage deep learning framework to segment and recognize tongue images and enhance the accuracy and efficiency of artificial intelligence (AI) tongue diagnosis in traditional Chinese medicine (TCM).
Materials and Methods:
Five hundred and ninety-four tongue images of adequate quality were used to construct AI models. First, a multi-attention UNet model was used for semantic segmentation to distinguish the tongue body from the background. In the second stage, a residual network was employed to classify seven important tongue characteristics.
Results:
The segmentation model achieved 96.12% mean intersection over union, 98.91% mean pixel accuracy, and 97.15% mean precision. The classification models exhibited robustness across seven distinct characteristics with an overall accuracy >80%. These results indicated that the constructed models have potential applications in TCM.
Conclusions:
This two-stage approach not only streamlines the analysis of tongue images but also sets a new benchmark for accuracy in medical image processing in the field. |
| format | Article |
| id | doaj-art-5753abd86e264dcf802aef5f31445a50 |
| institution | Kabale University |
| issn | 2311-8571 |
| language | English |
| publishDate | 2024-12-01 |
| publisher | Wolters Kluwer Medknow Publications |
| record_format | Article |
| series | World Journal of Traditional Chinese Medicine |
| spelling | doaj-art-5753abd86e264dcf802aef5f31445a502025-01-16T08:46:22ZengWolters Kluwer Medknow PublicationsWorld Journal of Traditional Chinese Medicine2311-85712024-12-0110446046410.4103/wjtcm.wjtcm_92_24Constructing an Artificial Intelligent Deep Neural Network Battery for Tongue Region Segmentation and Tongue Characteristic RecognitionTian-Xing YiJian-Xin ChenXue-Song WangMeng-Jie KouQing-Qiong DengXu WangObjective: This study aimed to construct a two-stage deep learning framework to segment and recognize tongue images and enhance the accuracy and efficiency of artificial intelligence (AI) tongue diagnosis in traditional Chinese medicine (TCM). Materials and Methods: Five hundred and ninety-four tongue images of adequate quality were used to construct AI models. First, a multi-attention UNet model was used for semantic segmentation to distinguish the tongue body from the background. In the second stage, a residual network was employed to classify seven important tongue characteristics. Results: The segmentation model achieved 96.12% mean intersection over union, 98.91% mean pixel accuracy, and 97.15% mean precision. The classification models exhibited robustness across seven distinct characteristics with an overall accuracy >80%. These results indicated that the constructed models have potential applications in TCM. Conclusions: This two-stage approach not only streamlines the analysis of tongue images but also sets a new benchmark for accuracy in medical image processing in the field.https://journals.lww.com/10.4103/wjtcm.wjtcm_92_24artificial intelligencedeep learningtongue characteristic recognitiontongue diagnosistongue segmentationtraditional chinese medicine |
| spellingShingle | Tian-Xing Yi Jian-Xin Chen Xue-Song Wang Meng-Jie Kou Qing-Qiong Deng Xu Wang Constructing an Artificial Intelligent Deep Neural Network Battery for Tongue Region Segmentation and Tongue Characteristic Recognition World Journal of Traditional Chinese Medicine artificial intelligence deep learning tongue characteristic recognition tongue diagnosis tongue segmentation traditional chinese medicine |
| title | Constructing an Artificial Intelligent Deep Neural Network Battery for Tongue Region Segmentation and Tongue Characteristic Recognition |
| title_full | Constructing an Artificial Intelligent Deep Neural Network Battery for Tongue Region Segmentation and Tongue Characteristic Recognition |
| title_fullStr | Constructing an Artificial Intelligent Deep Neural Network Battery for Tongue Region Segmentation and Tongue Characteristic Recognition |
| title_full_unstemmed | Constructing an Artificial Intelligent Deep Neural Network Battery for Tongue Region Segmentation and Tongue Characteristic Recognition |
| title_short | Constructing an Artificial Intelligent Deep Neural Network Battery for Tongue Region Segmentation and Tongue Characteristic Recognition |
| title_sort | constructing an artificial intelligent deep neural network battery for tongue region segmentation and tongue characteristic recognition |
| topic | artificial intelligence deep learning tongue characteristic recognition tongue diagnosis tongue segmentation traditional chinese medicine |
| url | https://journals.lww.com/10.4103/wjtcm.wjtcm_92_24 |
| work_keys_str_mv | AT tianxingyi constructinganartificialintelligentdeepneuralnetworkbatteryfortongueregionsegmentationandtonguecharacteristicrecognition AT jianxinchen constructinganartificialintelligentdeepneuralnetworkbatteryfortongueregionsegmentationandtonguecharacteristicrecognition AT xuesongwang constructinganartificialintelligentdeepneuralnetworkbatteryfortongueregionsegmentationandtonguecharacteristicrecognition AT mengjiekou constructinganartificialintelligentdeepneuralnetworkbatteryfortongueregionsegmentationandtonguecharacteristicrecognition AT qingqiongdeng constructinganartificialintelligentdeepneuralnetworkbatteryfortongueregionsegmentationandtonguecharacteristicrecognition AT xuwang constructinganartificialintelligentdeepneuralnetworkbatteryfortongueregionsegmentationandtonguecharacteristicrecognition |