Deep learning-based tongue image recognition for hypertension with phlegm-dampness constitution
10.3969/j.issn.1005-202X.2025.04.016
- VernacularTitle:基于深度学习的痰湿体质高血压舌象识别
- Author:
Qianqian ZHU
1
;
Lan WANG
;
Nan JIANG
;
Changwu DONG
Author Information
1. 安徽中医药大学中医学院,安徽 合肥 230012
- Publication Type:Journal Article
- Keywords:
tongue manifestation;
deep learning;
hypertension;
phlegm-dampness constitution;
neural network
- From:
Chinese Journal of Medical Physics
2025;42(4):534-541
- CountryChina
- Language:Chinese
-
Abstract:
Objective To objectively identify whether people with phlegm-dampness constitution suffer from hypertension or not using deep learning semantic segmentation model and residual neural network,so as to promote the modernization of tongue manifestation research,and provide a more objective and scientific basis for clinical decision-making in traditional Chinese medicine(TCM).Methods The tongue regions of 547 subjects were outlined and labeled using the Label Me image labeling tool,followed by tongue body segmentation using the U-Net segmentation algorithm which separated the tongue body from the complex background.In the subsequent study,3 deep learning models,namely ResNet-34,ResNet-50 and YOLOv5,were used to classify the tongue manifestations of hypertensive patients and the sub-health both with phlegm-dampness,and to construct the corresponding classification models whose performances were objectively evaluated by drawing confusion matrix and calculating F1 value and accuracy.Results The experimental results showed that all 3 models performed well in the classification task.ResNet-34 vs ResNet-50 had F1 values of 91.46%vs 92.08%,accuracies of 92.87%vs 93.05%,precisions of 90.48%vs 95.26%,and recall rates of 92.89%vs 89.11%.YOLOv5 had an overall accuracy of 85.6%,achieving 85.3%and 85.7%accuracies in the specific classifications for hypertensive patients with phlegm-dampness and the sub-health with phlegm-dampness.Conclusion All 3 models(ResNet-34,ResNet-50 and YOLOv5)performed well in the classification task,with ResNet-50 being the best.It proves that the deep learning model can better accomplish the classification and recognition of tongue manifestations,which reflects the great potential of deep learning in the automated classification for TCM tongue diagnosis,and also provides a strong technical support for the modernization and objectivity of TCM diagnosis.
