Tongue image quality assessment based on a deep convolutional neural network.

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.

Distribution characteristics of oral microbiota and its relationship with intestinal microbiota in patients with type 2 diabetes mellitus.

Introduction: Type 2 diabetes mellitus (T2DM) has a high incidence rate globally, increasing the burden of death, disability, and the economy worldwide. Previous studies have found that the compositions of oral and intestinal microbiota changed respectively in T2DM; whether the changes were associated or interacted between the two sites and whether there were some associations between T2DM and the ectopic colonization of oral microbiota in the gut still need to be identified. Research design and methods: We performed a cross-sectional observational study; 183 diabetes and 74 controls were enrolled. We used high-throughput sequencing technology to detect the V3-V4 region of 16S rRNA in oral and stool samples. The Source Tracker method was used to identify the proportion of the intestinal microbiota that ectopic colonized from the oral cavity. Results: The oral marker bacteria of T2DM were found, such as Actinobacteria, Streptococcus, Rothia, and the intestinal marker bacteria were Bifidobacterium, Streptococcus, and Blautia at the genus level. Among them, Actinobacteria and Blautia played a vital role in different symbiotic relationships of oral and intestinal microbiota. The commonly distributed bacteria, such as Firmicutes, Bacteroidetes, and Actinobacteria, were found in both oral and intestine. Moreover, the relative abundance and composition of bacteria were different between the two sites. The glycine betaine degradation I pathway was the significantly up-regulated pathway in the oral and intestinal flora of T2DM. The main serum indexes related to oral and intestinal flora were inflammatory. The relative abundance of Proteobacteria in the intestine and the Spirochete in oral was positively correlated, and the correlation coefficient was the highest, was 0.240 (P<0.01). The proportion of ectopic colonization of oral flora in the gut of T2DM was 2.36%. Conclusion: The dysbacteriosis exited in the oral and intestine simultaneously, and there were differences and connections in the flora composition at the two sites in T2DM. Ectopic colonization of oral flora in the intestine might relate to T2DM. Further, clarifying the oral-gut-transmitting bacteria can provide an essential reference for diagnosing and treating T2DM in the future.

Relationships Between Diurnal Changes of Tongue Coating Microbiota and Intestinal Microbiota.

The oral cavity and the intestine are the main distribution locations of human digestive bacteria. Exploring the relationships between the tongue coating and gut microbiota, the influence of the diurnal variations of the tongue coating microbiota on the intestinal microbiota can provide a reference for the development of the disease diagnosis and monitoring, as well as the medication time. In this work, a total of 39 healthy college students were recruited. We collected their tongue coating microbiota which was collected before and after sleep and fecal microbiota. The diurnal variations of tongue coating microbiota are mainly manifested on the changes in diversity and relative abundance. There are commensal bacteria in the tongue coating and intestines, especially Prevotella which has the higher proportion in both sites. The relative abundance of Prevotella in the tongue coating before sleep has a positive correlation with intestinal Prevotella; the r is 0.322 (p < 0.05). Bacteroides in the intestine had the most bacteria associated with the tongue coating and had the highest correlation coefficient with Veillonella in the oral cavity, which was 0.468 (p < 0.01). These results suggest that the abundance of the same flora in the two sites may have a common change trend. The SourceTracker results show that the proportion of intestinal bacteria sourced from tongue coating is less than 1%. It indicates that oral flora is difficult to colonize in the intestine in healthy people. This will provide a reference for the study on the oral and intestinal microbiota in diseases.

Application of computer tongue image analysis technology in the diagnosis of NAFLD.

Nonalcoholic fatty liver disease (NAFLD), a leading cause of chronic hepatic disease, can progress to liver fibrosis, cirrhosis, and hepatocellular carcinoma. Therefore, it is extremely important to explore early diagnosis and screening methods. In this study, we developed models based on computer tongue image analysis technology to observe the tongue characteristics of 1778 participants (831 cases of NAFLD and 947 cases of non-NAFLD). Combining quantitative tongue image features, basic information, and serological indexes, including the hepatic steatosis index (HSI) and fatty liver index (FLI), we utilized machine learning methods, including Logistic Regression, Support Vector Machine (SVM), Random Forest (RF), Gradient Boosting Decision Tree (GBDT), Adaptive Boosting Algorithm (AdaBoost), Naïve Bayes, and Neural Network for NAFLD diagnosis. The best fusion model for diagnosing NAFLD by Logistic Regression, which contained the tongue image parameters, waist circumference, BMI, GGT, TG, and ALT/AST, achieved an AUC of 0.897 (95% CI, 0.882-0.911), an accuracy of 81.70% with a sensitivity of 77.62% and a specificity of 85.22%; in addition, the positive likelihood ratio and negative likelihood ratio were 5.25 and 0.26, respectively. The application of computer intelligent tongue diagnosis technology can improve the accuracy of NAFLD diagnosis and may provide a convenient technical reference for the establishment of early screening methods for NAFLD, which is worth further research and verification.

Tongue color clustering and visual application based on 2D information.

PURPOSE: Studies have shown the association between tongue color and diseases. To help clinicians make more objective and accurate decisions quickly, we take unsupervised learning to deal with the basic clustering of tongue color in a 2D way. METHODS: A total of 595 typical tongue images were analyzed. The 3D information extracted from the image was transformed into 2D information by principal component analysis (PCA). K-Means was applied for clustering into four diagnostic groups. The results were evaluated by clustering accuracy (CA), Jaccard similarity coefficient (JSC), and adjusted rand index (ARI). RESULTS: The new 2D information totally retained 89.63% original information in the L*a*b* color space. And our methods successfully classified tongue images into four clusters and the CA, ARI, and JSC were 89.04%, 0.721, and 0.890, respectively. CONCLUSIONS: The 2D information of tongue color can be used for clustering and to improve the visualization. K-Means combined with PCA could be used for tongue color classification and diagnosis. Methods in the paper might provide reference for the other research based on image diagnosis technology.

Tongue Image Database Construction Based on the Expert Opinions: Assessment for Individual Agreement and Methods for Expert Selection.

This study aims at introducing a method for individual agreement evaluation to identify the discordant raters from the experts' group. We exclude those experts and decide the best experts selection method, so as to improve the reliability of the constructed tongue image database based on experts' opinions. Fifty experienced experts from the TCM diagnostic field all over China were invited to give ratings for 300 randomly selected tongue images. Gwet's AC1 (first-order agreement coefficient) was used to calculate the interrater and intrarater agreement. The optimization of the interrater agreement and the disagreement score were put forward to evaluate the external consistency for individual expert. The proposed method could successfully optimize the interrater agreement. By comparing three experts' selection methods, the interrater agreement was, respectively, increased from 0.53 [0.32-0.75] for original one to 0.64 [0.39-0.80] using method A (inclusion of experts whose intrarater agreement>0.6), 0.69 [0.63-0.81] using method B (inclusion of experts whose disagreement score="0"), and 0.76 [0.67-0.83] using method C (inclusion of experts whose intrarater agreement>0.6& disagreement score="0"). In this study, we provide an estimate of external consistency for individual expert, and the comprehensive consideration of both the internal consistency and the external consistency for each expert would be superior to either one in the tongue image construction based on expert opinions.

A Study of Machine-Learning Classifiers for Hypertension Based on Radial Pulse Wave.

OBJECTIVE: In this study, machine learning was utilized to classify and predict pulse wave of hypertensive group and healthy group and assess the risk of hypertension by observing the dynamic change of the pulse wave and provide an objective reference for clinical application of pulse diagnosis in traditional Chinese medicine (TCM). METHOD: The basic information from 450 hypertensive cases and 479 healthy cases was collected by self-developed H20 questionnaires and pulse wave information was acquired by self-developed pulse diagnostic instrument (PDA-1). H20 questionnaires and pulse wave information were used as input variables to obtain different machine learning classification models of hypertension. This method was aimed at analyzing the influence of pulse wave on the accuracy and stability of machine learning model, as well as the feature contribution of hypertension model after removing noise by K-means. RESULT: Compared with the classification results before removing noise, the accuracy and the area under the curve (AUC) had been improved. The accuracy rates of AdaBoost, Gradient Boosting, and Random Forest (RF) were 86.41%, 86.41%, and 85.33%, respectively. AUC were 0.86, 0.86, and 0.85, respectively. The maximum accuracy of SVM increased from 79.57% to 83.15%, and the AUC stability increased from 0.79 to 0.83. In addition, the features of importance on traditional statistics and machine learning were consistent. After removing noise, the features with large changes were h1/t1, w1/t, t, w2, h2, t1, and t5 in AdaBoost and Gradient Boosting (top10). The common variables for machine learning and traditional statistics were h1/t1, h5, t, Ad, BMI, and t2. CONCLUSION: Pulse wave-based diagnostic method of hypertension has significant value in reference. In view of the feasibility of digital-pulse-wave diagnosis and dynamically evaluating hypertension, it provides the research direction and foundation for Chinese medicine in the dynamic evaluation of modern disease diagnosis and curative effect.

Clinical epidemiology of gastric cancer in Hehuang valley of China: a 10-year epidemiological study of gastric cancer.

AIM: To investigate the clinical epidemiological characteristics of gastric cancer in the Hehuang valley, China, to provide a reference for treatment and prevention of regional gastric cancer. METHODS: Between February 2003 and February 2013, the records of 2419 patients with gastric cancer were included in this study. The patient's characteristics, histological and pathological features, as well as the dietary habits of the patients, were investigated. RESULTS: The clinical data showed that adenocarcinoma was the leading histological type of gastric cancer in this area. Characteristics of gastric cancer in different ethnic groups and age showed that the 60.55-65.50 years group showed the high incidence of gastric cancer in all ethnic groups. There were more male gastric cancer patients than female. Intestinal was the most common type of gastric cancer in the Hehuang valley. There was no significant difference in the proportion of sex in terms of Helicobacter pylori infection. The impact of dietary habits on gastric cancer showed that regular consumption of fried or grilled food, consumption of high-salt, high-fat and spicy food and drinking strong Boiled brick-tea were three important factors associated with gastric cancer in males and females. CONCLUSION: Differences existed in race, sex, and age of patients according to the epidemiology of gastric cancer in the Hehuang valley. Moreover, dietary habits was also an important factor contributing to gastric cancer.