Basic Medical College Shanghai University of Traditional Chinese Medicine, 1200 Cailun Road, Pudong New Area, Shanghai, 201203, China.
Shanghai Collaborative Innovation Center of Health Service in TCM, Shanghai University of TCM, 1200 Cailun Road, Shanghai, 201203, China.
BMC Med Inform Decis Mak. 2021 May 5;21(1):147. doi: 10.1186/s12911-021-01508-8.
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.
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.
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.
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.
舌诊是中医诊断技术现代化的一个重要研究领域。舌像质量是构建舌诊领域标准数据集的基础。为了在中医行业建立一个标准的舌像数据库，我们需要评估大量舌像的质量，并将合格的图像添加到数据库中。因此，建立一个自动、高效和准确的质量控制模型对于中医智能舌诊技术的发展具有重要意义。
采用机器学习方法，包括支持向量机（SVM）、随机森林（RF）、梯度提升决策树（GBDT）、自适应提升算法（Adaboost）、朴素贝叶斯、决策树（DT）、残差神经网络（ResNet）、牛津大学视觉几何组开发的卷积神经网络（VGG）和密集连接卷积网络（DenseNet），用于识别高质量和低质量的舌像。使用准确率、精确率、召回率和 F1 分数等指标对这些方法的性能进行比较。
实验结果表明，三种深度学习模型的准确率均在 96%以上，ResNet-152 和 DenseNet-169 的准确率均在 98%以上。模型 ResNet-152 的准确率为 99.04%，精确率为 99.05%，召回率为 99.04%，F1 得分为 99.05%。性能优于其他八种模型。这八种模型分别是 VGG-16、DenseNet-169、SVM、RF、GBDT、Adaboost、朴素贝叶斯和 DT。ResNet-152 被选为舌像 IQA 的质量筛选模型。
本研究结果表明，在舌像质量评估的决策过程中，可以应用各种 CNN 模型，并且应用深度学习方法，特别是深度卷积神经网络，评估低质量舌像的可行性。
