Study on Tongue Image Features Based on Deep Learning

VernacularTitle:基于深度学习的舌象特征研究
Author: Tao CUI ¹ ; Jiajun HE ; Hua HE ; Rui LI ; Liang ZHAO ; Deshuang KOU
Author Information

1. 天津市医疗器械审评查验中心天津 300191
Keywords: transfer learning; tongue image feature; deep learning; tongue segmentation; tongue diagnosis of traditional Chinese medicine(TCM)
From: Journal of Medical Informatics 2024;45(7):81-87
CountryChina
Language:Chinese
Abstract: Purpose/Significance To apply deep learning technology to achieve the purpose of tongue image analysis automation,so as to provide references for the standardization of tongue image of traditional Chinese medicine(TCM),and further promote the moderni-zation of TCM diagnosis and treatment technology.Method/Process It develops a new semantic segmentation loss function with region-based correlation and label relaxation to enhance the capability of tongue image segmentation model to learn pixel relationships and handle mislabeled data.Additionally,leveraging inherent color-related priors in tongue image features,the model is simplified by decomposing it into two multi-label classification tasks,thereby accelerating model training and reducing its complexity.Result/Conclusion The pro-posed algorithm is proven effective on a self-constructed dataset,attaining a high 96.57％MIoU in tongue segmentation,and demon-strating strong performance with a macro F1-score of 88.58％and average accuracy of 82.59％.