Tongue image quality assessment based on a deep convolutional neural network
Abstract Background Tongue diagnosis is an important research field of TCM diagnostic technology modernization. The quality of tongue images is the basis for constructing a standard dataset in the field of tongue diagnosis. To establish a standard tongue image database in the TCM industry, we need t...
Main Authors: | , , , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
BMC
2021-05-01
|
Series: | BMC Medical Informatics and Decision Making |
Subjects: | |
Online Access: | https://doi.org/10.1186/s12911-021-01508-8 |
id |
doaj-276681deb44d4994a94ce49ee4678c21 |
---|---|
record_format |
Article |
spelling |
doaj-276681deb44d4994a94ce49ee4678c212021-05-09T11:40:52ZengBMCBMC Medical Informatics and Decision Making1472-69472021-05-0121111410.1186/s12911-021-01508-8Tongue image quality assessment based on a deep convolutional neural networkTao Jiang0Xiao-juan Hu1Xing-hua Yao2Li-ping Tu3Jing-bin Huang4Xu-xiang Ma5Ji Cui6Qing-feng Wu7Jia-tuo Xu8Basic Medical College Shanghai University of Traditional Chinese MedicineShanghai Collaborative Innovation Center of Health Service in TCM, Shanghai University of TCMBasic Medical College Shanghai University of Traditional Chinese MedicineBasic Medical College Shanghai University of Traditional Chinese MedicineBasic Medical College Shanghai University of Traditional Chinese MedicineBasic Medical College Shanghai University of Traditional Chinese MedicineBasic Medical College Shanghai University of Traditional Chinese MedicineSchool of Information Science and Engineering, Xiamen UniversityBasic Medical College Shanghai University of Traditional Chinese MedicineAbstract Background Tongue diagnosis is an important research field of TCM diagnostic technology modernization. The quality of tongue images is the basis for constructing a standard dataset in the field of tongue diagnosis. To establish a standard tongue image database in the TCM industry, we need to evaluate the quality of a massive number of tongue images and add qualified images to the database. Therefore, an automatic, efficient and accurate quality control model is of significance to the development of intelligent tongue diagnosis technology for TCM. Methods Machine learning methods, including Support Vector Machine (SVM), Random Forest (RF), Gradient Boosting Decision Tree (GBDT), Adaptive Boosting Algorithm (Adaboost), Naïve Bayes, Decision Tree (DT), Residual Neural Network (ResNet), Convolution Neural Network developed by Visual Geometry Group at University of Oxford (VGG), and Densely Connected Convolutional Networks (DenseNet), were utilized to identify good-quality and poor-quality tongue images. Their performances were made comparisons by using metrics such as accuracy, precision, recall, and F1-Score. Results The experimental results showed that the accuracy of the three deep learning models was more than 96%, and the accuracy of ResNet-152 and DenseNet-169 was more than 98%. The model ResNet-152 obtained accuracy of 99.04%, precision of 99.05%, recall of 99.04%, and F1-score of 99.05%. The performances were better than performances of other eight models. The eight models are VGG-16, DenseNet-169, SVM, RF, GBDT, Adaboost, Naïve Bayes, and DT. ResNet-152 was selected as quality-screening model for tongue IQA. Conclusions Our research findings demonstrate various CNN models in the decision-making process for the selection of tongue image quality assessment and indicate that applying deep learning methods, specifically deep CNNs, to evaluate poor-quality tongue images is feasible.https://doi.org/10.1186/s12911-021-01508-8Tongue diagnosisQuality assessmentDeep learningResNetDenseNet |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Tao Jiang Xiao-juan Hu Xing-hua Yao Li-ping Tu Jing-bin Huang Xu-xiang Ma Ji Cui Qing-feng Wu Jia-tuo Xu |
spellingShingle |
Tao Jiang Xiao-juan Hu Xing-hua Yao Li-ping Tu Jing-bin Huang Xu-xiang Ma Ji Cui Qing-feng Wu Jia-tuo Xu Tongue image quality assessment based on a deep convolutional neural network BMC Medical Informatics and Decision Making Tongue diagnosis Quality assessment Deep learning ResNet DenseNet |
author_facet |
Tao Jiang Xiao-juan Hu Xing-hua Yao Li-ping Tu Jing-bin Huang Xu-xiang Ma Ji Cui Qing-feng Wu Jia-tuo Xu |
author_sort |
Tao Jiang |
title |
Tongue image quality assessment based on a deep convolutional neural network |
title_short |
Tongue image quality assessment based on a deep convolutional neural network |
title_full |
Tongue image quality assessment based on a deep convolutional neural network |
title_fullStr |
Tongue image quality assessment based on a deep convolutional neural network |
title_full_unstemmed |
Tongue image quality assessment based on a deep convolutional neural network |
title_sort |
tongue image quality assessment based on a deep convolutional neural network |
publisher |
BMC |
series |
BMC Medical Informatics and Decision Making |
issn |
1472-6947 |
publishDate |
2021-05-01 |
description |
Abstract Background Tongue diagnosis is an important research field of TCM diagnostic technology modernization. The quality of tongue images is the basis for constructing a standard dataset in the field of tongue diagnosis. To establish a standard tongue image database in the TCM industry, we need to evaluate the quality of a massive number of tongue images and add qualified images to the database. Therefore, an automatic, efficient and accurate quality control model is of significance to the development of intelligent tongue diagnosis technology for TCM. Methods Machine learning methods, including Support Vector Machine (SVM), Random Forest (RF), Gradient Boosting Decision Tree (GBDT), Adaptive Boosting Algorithm (Adaboost), Naïve Bayes, Decision Tree (DT), Residual Neural Network (ResNet), Convolution Neural Network developed by Visual Geometry Group at University of Oxford (VGG), and Densely Connected Convolutional Networks (DenseNet), were utilized to identify good-quality and poor-quality tongue images. Their performances were made comparisons by using metrics such as accuracy, precision, recall, and F1-Score. Results The experimental results showed that the accuracy of the three deep learning models was more than 96%, and the accuracy of ResNet-152 and DenseNet-169 was more than 98%. The model ResNet-152 obtained accuracy of 99.04%, precision of 99.05%, recall of 99.04%, and F1-score of 99.05%. The performances were better than performances of other eight models. The eight models are VGG-16, DenseNet-169, SVM, RF, GBDT, Adaboost, Naïve Bayes, and DT. ResNet-152 was selected as quality-screening model for tongue IQA. Conclusions Our research findings demonstrate various CNN models in the decision-making process for the selection of tongue image quality assessment and indicate that applying deep learning methods, specifically deep CNNs, to evaluate poor-quality tongue images is feasible. |
topic |
Tongue diagnosis Quality assessment Deep learning ResNet DenseNet |
url |
https://doi.org/10.1186/s12911-021-01508-8 |
work_keys_str_mv |
AT taojiang tongueimagequalityassessmentbasedonadeepconvolutionalneuralnetwork AT xiaojuanhu tongueimagequalityassessmentbasedonadeepconvolutionalneuralnetwork AT xinghuayao tongueimagequalityassessmentbasedonadeepconvolutionalneuralnetwork AT lipingtu tongueimagequalityassessmentbasedonadeepconvolutionalneuralnetwork AT jingbinhuang tongueimagequalityassessmentbasedonadeepconvolutionalneuralnetwork AT xuxiangma tongueimagequalityassessmentbasedonadeepconvolutionalneuralnetwork AT jicui tongueimagequalityassessmentbasedonadeepconvolutionalneuralnetwork AT qingfengwu tongueimagequalityassessmentbasedonadeepconvolutionalneuralnetwork AT jiatuoxu tongueimagequalityassessmentbasedonadeepconvolutionalneuralnetwork |
_version_ |
1721454134378364928 |