A novel approach based on computerized image analysis for traditional Chinese medical diagnosis of the tongue

Effects of Sitting and Supine Positions on Tongue Color as Measured by Tongue Image Analyzing System and Its Relation to Biometric Information

Tongue diagnosis is one of the important diagnostic methods in Kampo (traditional Japanese) medicine, in which the color and shape of the tongue are used to determine the patient's constitution and systemic symptoms. Tongue diagnosis is performed with the patient in the sitting or supine positions; however, the differences in tongue color in these two different positions have not been analyzed. We developed tongue image analyzing system (TIAS), which can quantify tongue color by capturing tongue images in the sitting and supine positions. We analyzed the effects on tongue color in two different body positions. Tongue color was quantified as L∗a∗b∗ from tongue images of 18 patients in two different body positions by taking images with TIAS. The CIEDE 2000 color difference equation (ΔE00) was used to assess the difference in tongue color in two different body positions. Correlations were also determined between ΔE00, physical characteristics, and laboratory test values. The mean and median ΔE00 for 18 patients were 2.85 and 2.34, respectively. Of these patients, 77.8% had a ΔE00 < 4.1. A weak positive correlation was obtained between ΔE00 and systolic blood pressure and fasting plasma glucose. Approximately 80% of patients' tongue color did not change between the sitting and supine positions. This indicates that the diagnostic results of tongue color are trustworthy even if medical professionals perform tongue diagnosis in two different body positions.

Artificial intelligence in tongue diagnosis: classification of tongue lesions and normal tongue images using deep convolutional neural network

OBJECTIVE

This study aims to classify tongue lesion types using tongue images utilizing Deep Convolutional Neural Networks (DCNNs).

METHODS

A dataset consisting of five classes, four tongue lesion classes (coated, geographical, fissured tongue, and median rhomboid glossitis), and one healthy/normal tongue class, was constructed using tongue images of 623 patients who were admitted to our clinic. Classification performance was evaluated on VGG19, ResNet50, ResNet101, and GoogLeNet networks using fusion based majority voting (FBMV) approach for the first time in the literature.

RESULTS

In the binary classification problem (normal vs. tongue lesion), the highest classification accuracy performance of 93,53% was achieved utilizing ResNet101, and this rate was increased to 95,15% with the application of the FBMV approach. In the five-class classification problem of tongue lesion types, the VGG19 network yielded the best accuracy rate of 83.93%, and the fusion approach improved this rate to 88.76%.

CONCLUSION

The obtained test results showed that tongue lesions could be identified with a high accuracy by applying DCNNs. Further improvement of these results has the potential for the use of the proposed method in clinic applications.

ExpACVO-Hybrid Deep learning: Exponential Anti Corona Virus Optimization enabled Hybrid Deep learning for tongue image segmentation towards diabetes mellitus detection

A metabolic disease known as diabetes mellitus (DM) is primarily brought on by an increase in blood sugar levels. On the other hand, DM and the complications it causes, such as diabetic Retinopathy (DR), will quickly emerge as one of the major health challenges of the twenty-first century. This indicates a huge economic burden on health-related authorities and governments. The detection of DM in the earlier stage can lead to early diagnosis and a considerable drop in mortality. Therefore, in order to detect DM at an early stage, an efficient detection system having the ability to detect DM is required. An effective classification method, named Exponential Anti Corona Virus Optimization (ExpACVO) is devised in this research work for Diabetes Mellitus (DM) detection using tongue images. Here, the UNet-Conditional Random Field-Recurrent Neural Network (UNet-CRF-RNN) is used to segment the images, and the proposed ExpACVO algorithm is used to train the UNet-CRF-RNN. Deep Q Network (DQN) classifier is used for DM detection, and the proposed ExpACVO is used for DQN training. The proposed ExpACVO algorithm is a newly created formula that combines Anti Corona Virus Optimization(ACVO) with Exponential Weighted Moving Average (EWMA). With maximum testing accuracy, sensitivity, and specificity values of 0.932, 0.950, and 0.914, respectively, the developed technique thus achieved improved performance.

A multi-step approach for tongue image classification in patients with diabetes

BACKGROUND

In China, diabetes is a common, high-incidence chronic disease. Diabetes has become a severe public health problem. However, the current diagnosis and treatment methods are difficult to control the progress of diabetes. Traditional Chinese Medicine (TCM) has become an option for the treatment of diabetes due to its low cost, good curative effect, and good accessibility.

OBJECTIVE

Based on the tongue images data to realize the fine classification of the diabetic population, provide a diagnostic basis for the formulation of individualized treatment plans for diabetes, ensure the accuracy and consistency of the TCM diagnosis, and promote the objective and standardized development of TCM diagnosis.

METHODS

We use the TFDA-1 tongue examination instrument to collect the tongue images of the subjects. Tongue Diagnosis Analysis System (TDAS) is used to extract the TDAS features of the tongue images. Vector Quantized Variational Autoencoder (VQ-VAE) extracts VQ-VAE features from tongue images. Based on VQ-VAE features, K-means clustering tongue images. TDAS features are used to describe the differences between clusters. Vision Transformer (ViT) combined with Grad-weighted Class Activation Mapping (Grad-CAM) is used to verify the clustering results and calculate positioning diagnostic information.

RESULTS

Based on VQ-VAE features, K-means divides the diabetic population into 4 clusters with clear boundaries. The silhouette, calinski harabasz, and davies bouldin scores are 0.391, 673.256, and 0.809, respectively. Cluster 1 had the highest Tongue Body L (TB-L) and Tongue Coating L (TC-L) and the lowest Tongue Coating Angular second moment (TC-ASM), with a pale red tongue and white coating. Cluster 2 had the highest TC-b with a yellow tongue coating. Cluster 3 had the highest TB-a with a red tongue. Group 4 had the lowest TB-L, TC-L, and TB-b and the highest Per-all with a purple tongue and the largest tongue coating area. ViT verifies the clustering results of K-means, the highest Top-1 Classification Accuracy (CA) is 87.8%, and the average CA is 84.4%.

CONCLUSIONS

The study organically combined unsupervised learning, self-supervised learning, and supervised learning and designed a complete diabetic tongue image classification method. This method does not rely on human intervention, makes decisions based entirely on tongue image data, and achieves state-of-the-art results. Our research will help TCM deeply participate in the individualized treatment of diabetes and provide new ideas for promoting the standardization of TCM diagnosis.

Tongue Diagnosis Index of Chronic Kidney Disease

BACKGROUND

To apply non-invasive Automatic Tongue Diagnosis System (ATDS) in analyzing tongue features in patients with chronic kidney disease (CKD).

METHODS

This was a cross-sectional, case-controlled observational study. Patients with CKD who met the inclusion and exclusion criteria were enrolled and divided into the following groups according to renal function and dialysis status: non-dialysis CKD group; end-stage renal disease (ESRD) group; and control group. Tongue images were captured and eight tongue features-shape, color, fur thickness, saliva, fissure, ecchymosis, teeth marks, and red dots-were imaged and analyzed by ATDS.

RESULTS

117 participants (57 men, 60 women) were enrolled in the study, which included 16 in control group, 38 in non-dialysis CKD group, and 63 in ESRD group. We demonstrated significant differences in the fur thickness (p = 0.045), color (p = 0.005), amounts of ecchymosis (p = 0.010), teeth marks (p = 0.016), and red dot (p < 0.001) among three groups. The areas under receiver operating characteristic curve for the amount of ecchymosis was 0.757 ± 0.055 (95% confidence interval, 0.648-0866; p < 0.001). Additionally, with increase in ecchymosis by one point, the risk of CKD dialysis rose by 1.523 times (95% confidence interval, 1.198-1.936; p = 0.001). After hemodialysis, the amount of saliva (p = 0.038), the area of saliva (p = 0.048) and the number of red dots (p = 0.040) were decreased significantly among patients with ESRD. On the contrary, the percentage of coating (p = 0.002) and area of coating (p = 0.026) were increased significantly after hemodialysis.

CONCLUSION

Blood deficiency and stasis with qi deficiency or blood heat syndrome (Zheng pattern) is common in patients with CKD. The risk of CKD dialysis increases with increasing ecchymosis. Hemodialysis can affect saliva, tongue coating, and relieve heat syndrome among ESRD patients.

Challenges and Solutions in Automated Tongue Diagnosis Techniques: A Review

Tongue diagnosis is used in various traditional medicine cultures as a non-invasive method for assessing an individual's health. Tongue image analysis has the potential for assessing the metabolism and functionality of the internal organs, making it a quick method of diagnosis. As automated systems give quantitative and objective results thereby effective in facilitating diagnosis, a review was conducted to evaluate literature on current methods of tongue diagnosis. Different methods of tongue diagnosis in the literature were identified and compared. Information on automated tongue diagnosis system, such as image acquisition, color correction, segmentation, feature extraction and classification, particularly in traditional medicine were reviewed. The aim of the review was to identify effective image processing techniques to be compatible with automated system for tongue diagnosis using some easily available to all imaging device rather than a dedicated state of art acquisition systems, which may not be easily accessible to general public. All methods identified were either being researched or developed and no specific system was identified that is currently available for routine use in clinics or home monitoring for patients. The healthcare sector could benefit from access to validated and automated tongue diagnosis systems. The feasibility of a mobile enabled platform to intelligently make use of this traditional method of diagnosis should be explored. In order to provide cheap and quick preliminary diagnosis for clinical practice automation of this noninvasive traditional technique can prove to be a boon for health care sector.

Digital tongue image analyses for health assessment

Traditional Chinese Medicine (TCM), as an effective alternative medicine, utilizes tongue diagnosis as a major method to assess the patient's health status by examining the tongue's color, shape, and texture. Tongue images can also give the pre-disease indications without any significant disease symptoms, which provides a basis for preventive medicine and lifestyle adjustment. However, traditional tongue diagnosis has limitations, as the process may be subjective and inconsistent. Hence, computer-aided tongue diagnoses have a great potential to provide more consistent and objective health assessments. This paper reviewed the current trends in TCM tongue diagnosis, including tongue image acquisition hardware, tongue segmentation, feature extraction, color correction, tongue classification, and tongue diagnosis system. We also present a case of TCM constitution classification based on tongue images.

Application of U-Net with Global Convolution Network Module in Computer-Aided Tongue Diagnosis

The rapid development of intelligent manufacturing provides strong support for the intelligent medical service ecosystem. Researchers are committed to building Wise Information Technology of 120 (WIT 120) for residents and medical personnel with the concept of simple smart medical care and through core technologies such as Internet of Things, Big Data Analytics, Artificial Intelligence, and microservice framework, to improve patient safety, medical quality, clinical efficiency, and operational benefits. Among them, how to use computers and deep learning technology to assist in the diagnosis of tongue images and realize intelligent tongue diagnosis has become a major trend. Tongue crack is an important feature of tongue states. Not only does change of tongue crack states reflect objectively and accurately changed circumstances of some typical diseases and TCM syndrome but also semantic segmentation of fissured tongue can combine the other features of tongue states to further improve tongue diagnosis systems' identification accuracy. Although computer tongue diagnosis technology has made great progress, there are few studies on the fissured tongue, and most of them focus on the analysis of tongue coating and body. In this paper, we do systematic and in-depth researches and propose an improved U-Net network for image semantic segmentation of fissured tongue. By introducing the Global Convolution Network module into the encoder part of U-Net, it solves the problem that the encoder part is relatively simple and cannot extract relatively abstract high-level semantic features. Finally, the method is verified by experiments. The improved U-Net network has a better segmentation effect and higher segmentation accuracy for fissured tongue image dataset. It can be used to design a computer-aided tongue diagnosis system.

Fully-channel regional attention network for disease-location recognition with tongue images

OBJECTIVE

Using the deep learning model to realize tongue image-based disease location recognition and focus on solving two problems: 1. The ability of the general convolution network to model detailed regional tongue features is weak; 2. Ignoring the group relationship between convolution channels, which caused the high redundancy of the model.

METHODS

To enhance the convolutional neural networks. In this paper, a stochastic region pooling method is proposed to gain detailed regional features. Also, an inner-imaging channel relationship modeling method is proposed to model multi-region relations on all channels. Moreover, we combine it with the spatial attention mechanism.

RESULTS

The tongue image dataset with the clinical disease-location label is established. Abundant experiments are carried out on it. The experimental results show that the proposed method can effectively model the regional details of tongue image and improve the performance of disease location recognition.

CONCLUSION

In this paper, we construct the tongue image dataset with disease-location labels to mine the relationship between tongue images and disease locations. A novel fully-channel regional attention network is proposed to model the local detail tongue features and improve the modeling efficiency.

SIGNIFICANCE

The applications of deep learning in tongue image disease-location recognition and the proposed innovative models have guiding significance for other assistant diagnostic tasks. The proposed model provides an example of efficient modeling of detailed tongue features, which is of great guiding significance for other auxiliary diagnosis applications.

The Impact of Artificial Intelligence on Traditional Chinese Medicine

Traditional Chinese Medicine (TCM) is a well-established medical system with a long history. Currently, artificial intelligence (AI) is rapidly expanding in many fields including TCM. AI will significantly improve the reliability and accuracy of diagnostics, thus increasing the use of effective therapeutic methods for patients. This systematic review provides an updated overview on the major breakthroughs in the field of AI-assisted TCM four diagnostic methods, syndrome differentiation, and treatment. AI-assisted TCM diagnosis is mainly based on digital data collected by modern electronic instruments, which makes TCM diagnosis more quantitative, objective, and standardized. As a result, the diagnosis decisions made by different TCM doctors exhibit more consistency, accuracy, and reliability. Meanwhile, the therapeutic efficacy of TCM can be evaluated objectively. Therefore, AI is promoting TCM from experience to evidence-based medicine, a genuine scientific revolution. Furthermore, huge and non-uniform knowledge on formula-syndrome relationships and the combination rules of herbal TCM formulae could be better standardized with the help of AI analysis, which is necessary for the clinical efficacy evaluation and further optimization on the standardized TCM formulae. AI bridges the gap between TCM and modern science and technology. AI may bring clinical TCM diagnostics closer to western medicine. With the help of AI, more scientific evidence about TCM will be discovered. It can be expected that more unified guidelines for specific TCM syndromes will be issued with the development of AI-assisted TCM therapies in the future.

Computational Traditional Chinese Medicine diagnosis: A literature survey

BACKGROUND AND OBJECTIVE

Traditional Chinese Medicine (TCM) diagnosis is based on the theoretical principles and knowledge, where it is steeped in thousands of years of history to diagnose various types of diseases and syndromes. It can be generally divided into four main diagnostic approaches: 1. Inspection, 2. Auscultation and olfaction, 3. Inquiry, and 4. Palpation, which are widely used in TCM hospitals in China and around the world. With the development of intelligent computing technology in recent years, computational TCM diagnosis has grown rapidly.

METHODS

In this paper, we aim to systematically summarize the development of computational TCM diagnosis based on four diagnostic approaches, mainly focusing on digital acquisition devices, collected datasets, and computational detection approaches (algorithms). Furthermore, all related works of this field are compared and explored in detail.

RESULTS

This survey provides the principles, applications, and current progress in computing for readers and researchers in terms of computational TCM diagnosis. Moreover, the future development direction, prospect, and technological trend of computational TCM diagnosis will also be discussed in this study.

CONCLUSIONS

Recent computational TCM diagnosis works are compared in detail to show the pros/cons, where we provide some meaningful suggestions and opinions on the future research approaches in this area. This work is useful for disease detection in computational TCM diagnosis as well as health management in the smart healthcare area.

INDEX TERMS

Computational diagnosis, Traditional Chinese Medicine, survey, smart healthcare.

Development status and prospects of international standardization of medical devices of Traditional Chinese Medicine

As Traditional Chinese Medicine (TCM) becomes widely used in many countries around the world, global demand for intelligent and modernized medical devices of TCM is increasing. Medical devices of TCM have played an important role in diagnosis and treatment of disease. Standardization on medical devices of TCM cannot only be beneficial to ensuring the life safety of patients, but also to enhancing the effectiveness of diagnosis and treatment. This paper includes (1) classification and trends in medical devices of TCM; (2) status review on international standardization of medical devices of TCM; (3) key technical factors in developing international standards for medical devices of TCM and (4) prospects for international standardization development of medical devices of TCM.

Can Traditional Chinese Medicine Diagnosis Be Parameterized and Standardized? A Narrative Review

The integration of Traditional Chinese Medicine (TCM) in Western health systems and research requires a rational communicable theory, scientific proof of efficacy and safety, and quality control measures. The existence of clear definitions and the diagnosis standardization are critical factors to establish the patient's vegetative functional status accurately and, therefore, systematically apply TCM therapeutics such as the stimulation of reflex skin areas known as acupoints. This science-based conceptualization entails using validated methods, or even developing new systems able to parameterize the diagnosis and assess TCM related effects by objective measurements. Traditionally, tongue and pulse diagnosis and the functional evaluation of action points by pressure sensitivity and physical examination may be regarded as essential diagnostic tools. Parameterizing these techniques is a future key point in the objectification of TCM diagnosis, such as by electronic digital image analysis, mechanical pulse diagnostic systems, or the systematic evaluation of acupoints' electrophysiology. This review aims to demonstrate and critically analyze some achievements and limitations in the clinical application of device-assisted TCM diagnosis systems to evaluate functional physiological patterns. Despite some limitations, tongue, pulse, and electrophysiological diagnosis devices have been reported as a useful tool while establishing a person's functional status.

Overcoming Barriers for Clinical Research of Acupuncture

Acupuncture is increasingly being used in the management of a wide range of symptoms. Despite decades of acupuncture research, a significant gap remains in translating evidence into specific and clear clinical guidelines for acupuncture practice. In this article, the authors discuss the gap between acupuncture research and clinical practice and exploring options to overcome the limitations of current clinical research of acupuncture.

An annotated dataset of tongue images supporting geriatric disease diagnosis

Hospitalized geriatric patients are a highly heterogeneous group often with variable diseases and conditions. Physicians, and geriatricians especially, are devoted to seeking non-invasive testing tools to support a timely, accurate diagnosis. Chinese tongue diagnosis, mainly based on the color and texture of the tongue, offers a unique solution. To develop a non-invasive assessment tool using machine learning in supporting a timely, accurate diagnosis in the elderly, we created an annotated dataset of 15% of 688 (=100) tongue images collected from hospitalized geriatric patients in a tertiary hospital in Shanghai, China. Images were captured via a light-field camera using CIELAB color space (to simulate human visual perception) and then were manually labeled by a panel of subject matter experts after chart reviewing patients’ clinical information documented in the hospital's information system. We expect that the dataset can assist in implementing a systematic means of conducting Chinese tongue diagnosis, predicting geriatric syndromes using tongue appearance, and even developing an mHealth application to provide individualized health suggestions for the elderly.

TISNet-Enhanced Fully Convolutional Network with Encoder-Decoder Structure for Tongue Image Segmentation in Traditional Chinese Medicine

Extracting the tongue body accurately from a digital tongue image is a challenge for automated tongue diagnoses, as the blurred edge of the tongue body, interference of pathological details, and the huge difference in the size and shape of the tongue. In this study, an automated tongue image segmentation method using enhanced fully convolutional network with encoder-decoder structure was presented. In the frame of the proposed network, the deep residual network was adopted as an encoder to obtain dense feature maps, and a Receptive Field Block was assembled behind the encoder. Receptive Field Block can capture adequate global contextual prior because of its structure of the multibranch convolution layers with varying kernels. Moreover, the Feature Pyramid Network was used as a decoder to fuse multiscale feature maps for gathering sufficient positional information to recover the clear contour of the tongue body. The quantitative evaluation of the segmentation results of 300 tongue images from the SIPL-tongue dataset showed that the average Hausdorff Distance, average Symmetric Mean Absolute Surface Distance, average Dice Similarity Coefficient, average precision, average sensitivity, and average specificity were 11.2963, 3.4737, 97.26%, 95.66%, 98.97%, and 98.68%, respectively. The proposed method achieved the best performance compared with the other four deep-learning-based segmentation methods (including SegNet, FCN, PSPNet, and DeepLab v3+). There were also similar results on the HIT-tongue dataset. The experimental results demonstrated that the proposed method can achieve accurate tongue image segmentation and meet the practical requirements of automated tongue diagnoses.

Human Tongue Thermography Could Be a Prognostic Tool for Prescreening the Type II Diabetes Mellitus

Diabetes mellitus is one of the life threatening diseases over the globe, and an early prediction of diabetes is of utmost importance in this current scenario. International Diabetes Federation (IDF) reported nearly half of the world's population was undiagnosed and unaware of being developed into diabetes. In 2017, around 84 million individuals were living with diabetes, and it might increase to 156 million by the end of 2045 stated by IDF. Generally, the diagnosis of diabetes relies on the biochemical method that may cause uneasiness and probability of infections to the subjects. To overcome such difficulties, a noninvasive method is much needed around the globe for primary screening. A change in body temperature is an indication of various diseases. Infrared thermal imaging is relatively a novel technique for skin temperature measurement and turned out to be well known in the medical field due to being noninvasive, risk-free, and repeatable. According to traditional Chinese medicine, the human tongue is a sensitive mirror that reflects the body's pathophysiological condition. So, we have (i) analysed and classified diabetes based on thermal variations at human tongue, (ii) segmented the hot spot regions from tongue thermogram by RGB (red, green, blue) based color histogram image segmentation method and extracted the features using gray level co-occurrence matrix algorithm, (iii) classified normal and diabetes using various machine learning algorithms, and (iv) developed computer aided diagnostic system to classify diabetes mellitus. The baseline measurements and tongue thermograms were obtained from 140 subjects. The measured tongue surface temperature of the diabetic group was found to be greater than normal. The statistical correlation between the HbA_1c and the thermal distribution in the tongue region was found to be r² = 0.5688. The Convolutional Neural Network has outperformed the other classifiers with 94.28% accuracy rate. Thus, tongue thermograms could be used as a preliminary screening approach for diabetes prognosis.

Association between tongue coating thickness and ultraviolet fluorescence in patients with functional dyspepsia: A prospective observational study

The aim of this study was to examine the correlation between the tongue coating thickness (TCT) and ultraviolet (UV) fluorescence and propose a new method for the estimation of TCT using a computerized tongue image acquisition system (CTIS).In this prospective and observational single-center study, we acquired tongue images under visible light and near-UV light for 60 patients with functional dyspepsia. Tongue images were acquired twice within a 30-minute interval to assess the reliability of CTIS. Then, the tongue coating was scraped and weighed to derive the wet weight of the tongue coating (WWTC). The percentage of the tongue coating area was calculated from the tongue images acquired under visible light. Mean color values (mCVs) for the UV fluorescence of the dorsal surface of the tongue were also computed.The reliabilities of the derived mCVs and percentage of the tongue coating area were acceptable (intraclass correlation coefficients, 0.907-0.947). The mCVs were more strongly correlated with WWTC than with the area, with mCV of modified lightness showing the strongest association (r = 0.785, P < .01). Finally, we suggested an estimation model for TCT based on the results.The results of this study suggest that both UV fluorescence of the dorsal tongue and the distribution area of tongue coating are useful parameters for the quantitative assessment of tongue coating. We believe that these findings will contribute to the development of a clinically useful CTIS.

Tooth-Marked Tongue Recognition Using Gradient-Weighted Class Activation Maps

The tooth-marked tongue is an important indicator in traditional Chinese medicinal diagnosis. However, the clinical competence of tongue diagnosis is determined by the experience and knowledge of the practitioners. Due to the characteristics of different tongues, having many variations such as different colors and shapes, tooth-marked tongue recognition is challenging. Most existing methods focus on partial concave features and use specific threshold values to classify the tooth-marked tongue. They lose the overall tongue information and lack the ability to be generalized and interpretable. In this paper, we try to solve these problems by proposing a visual explanation method which takes the entire tongue image as an input and uses a convolutional neural network to extract features (instead of setting a fixed threshold artificially) then classifies the tongue and produces a coarse localization map highlighting tooth-marked regions using Gradient-weighted Class Activation Mapping. Experimental results demonstrate the effectiveness of the proposed method.

Tooth-Marked Tongue Recognition Using Multiple Instance Learning and CNN Features

Tooth-marked tongue or crenated tongue can provide valuable diagnostic information for traditional Chinese Medicine doctors. However, tooth-marked tongue recognition is challenging. The characteristics of different tongues are multiform and have a great amount of variations, such as different colors, different shapes, and different types of teeth marks. The regions of teeth mark only appear along the lateral borders. Most existing methods make use of concave regions information to classify the tooth-marked tongue which leads to inconstant performance when the region of teeth mark is not concave. In this paper, we try to solve these problems by proposing a three-stage approach which first makes use of concavity information to propose the suspected regions, then use a convolutional neural network to extract deep features and at last use a multiple-instance classifier to make the final decision. Experimental results demonstrate the effectiveness of the proposed method.

Microbial biomarkers of common tongue coatings in patients with gastric cancer

PURPOSE

The study aims to explore the characteristic microorganisms of the common tongue coatings in patients with gastric cancer (GC).

METHODS

A total of 115 GC patients were assigned to four groups: White-thin coating (W-thin) group, White-thick coating (W-thick) group, Yellow-thin coating (Y-thin) group and Yellow-thick coating (Y-thick) group. Thirty-five healthy volunteers with White-thin coating were recruit as controls. High-throughput sequencing was used to describe the microbial community of the tongue coatings based on 16S rRNA and 18S rRNA genes. Multi-factors statistical analysis was carried out to present the microbial biomarkers of the tongue coating in GC patients.

RESULTS

At bacterial phylum level, Saccharibacteria had higher relative abundance in W-thick group than W-thin group, Proteobacteria was more abundant in W-thin group than Y-thick group and less abundant in Y-thick group than Y-thin group. At fungal genus level, Guehomyces and Aspergillus presented to be significantly different among the common tongue coatings. Forteen significantly increased taxa were sorted out as the microbial biomarkers of common tongue coatings by LEfSe and ROC analysis. At species level, bacterial Capnocytophaga leadbetteri and fungal Ampelomyces_sp_IRAN_1 may be the potential biomarkers of W-thin coating, four bacterial species (Megasphaera micronuciformis, Selenomonas sputigena ATCC 35185, Acinetobacter ursingii, Prevotella maculosa) may be the potential biomarkers of W-thick coating. In general, the white coatings held more complex commensal relationship than the yellow coatings.

CONCLUSION

The common tongue coating owned characteristic microorganisms and special commensal relationship in the GC patients.

A non-invasive measurement of tongue surface temperature

Oral temperature, tongue specifically, is a key factor affecting oral sensation and perception of food flavour and texture. It is therefore very important to know how the tongue temperature is affected by food consumption. Unfortunately, traditional methods such as clinical thermometers and thermocouples for oral temperature measurement are not most applicable during food oral consumption due to its invasive nature and interference with food. In this study, infrared thermal (IRT) imager was investigated for its feasibility for the measurement of tongue surface temperature. The IRT technique was firstly calibrated using a digital thermometer (DT). The technique was then used to measure tongue surface temperature after tongue was stimulated by (1) water rinsing at different temperatures (0-45 °C); and (2) treated with capsaicin solutions (5, 10, and 20 ppm). For both cases, tongue surface temperature showed significant changes as a result of the physical and chemical stimulation. Results confirm that IRT is feasible for tongue temperature measurement and could be a useful supporting tool in future for the study of food oral processing and sensory perception.

Using Traditional Chinese Medicine Ideas as a Mechanism to Engage People in Health Awareness

Improving health awareness is essential to health and healthcare sustainability. How to arouse attention to the health of people and encourage them to attend to healthcare progress so that we can reduce the costs of promoting healthcare by achieving more with less effort remains to be explored. In this paper, we provide a simplified health management app, called iTongue, with a basis in traditional Chinese medicine. People use iTongue to take pictures of their tongues to have a general idea of their health. We realize automated tongue image diagnosis using machine learning techniques to establish the relationship between the tongue image features and the cold or hot ZHENG (traditional Chinese medicine syndrome) in traditional Chinese medicine by learning through examples and assisting people to engage in health management. The results show that health management interaction based on traditional Chinese medicine has a positive influence on improving people’s attention to their health, encouraging them to participate in health management activities and develop the habit of caring about their health over the long term. In the future, we could consider using this kind of traditional Chinese medicine idea as a means of publicity to engage people in healthcare and to assist healthcare sustainability development.

Reliability, Accuracy, and Use Frequency of Evaluation Methods for Amount of Tongue Coating

OBJECTIVE

To classify the evaluation methods for amount of tongue coating (TC) and investigate their reliability, accuracy, and frequency of use.

METHODS

Articles published from 1985 to 2015 were searched for evaluation methods for the amount of TC in PubMed and the Cochrane Library. Only clinical researches were included except protocol articles. The methods were classified according to their characteristics.

RESULTS

Finally, 113 articles were selected. The evaluation method for the amount of TC from the articles was classified into 4 types: intuitive, specificative, computerized, and weighing TC. The reliability in the intuitive and specificative methods (κ =0.33-0.92) showed varying levels among the studies. In general, the amount of TC calculated by the specificative method (Spearman's r=0.68-0.80) was more strongly related to the directly measured value than to the value estimated by the computerized method (Pearson's r=0.442). The number of articles published on this topic has increased consistently, and the specificative method was the most frequently used. Despite the higher reliability of the computerized method, it has not been widely used.

CONCLUSIONS

The high prevalence of the specificative method would continue in clinical practice because of its convenience and accuracy. However, to establish higher reliability, the limitation of the subjectivity of the assessors should be overcome through calibration training. In the computerized method, novel algorithms are needed to obtain a higher accuracy so that it can help the practitioners confidently estimate the amount of TC.

Advances in automated tongue diagnosis techniques

Tongue diagnosis can be an effective, noninvasive method to perform an auxiliary diagnosis any time anywhere, which can support the global need in the primary healthcare system. This work reviews the recent advances in tongue diagnosis, which is a significant constituent of traditional oriental medicinal technology, and explores the literature to evaluate the works done on the various aspects of computerized tongue diagnosis, namely preprocessing, tongue detection, segmentation, feature extraction, tongue analysis, especially in traditional Chinese medicine (TCM). In spite of huge volume of work done on automatic tongue diagnosis (ATD), there is a lack of adequate survey, especially to combine it with the current diagnosis trends. This paper studies the merits, capabilities, and associated research gaps in current works on ATD systems. After exploring the algorithms used in tongue diagnosis, the current trend and global requirements in health domain motivates us to propose a conceptual framework for the automated tongue diagnostic system on mobile enabled platform. This framework will be able to connect tongue diagnosis with the future point-of-care health system.

Research on Techniques of Multifeatures Extraction for Tongue Image and Its Application in Retrieval

Tongue diagnosis is one of the important methods in the Chinese traditional medicine. Doctors can judge the disease's situation by observing patient's tongue color and texture. This paper presents a novel approach to extract color and texture features of tongue images. First, we use improved GLA (Generalized Lloyd Algorithm) to extract the main color of tongue image. Considering that the color feature cannot fully express tongue image information, the paper analyzes tongue edge's texture features and proposes an algorithm to extract them. Then, we integrate the two features in retrieval by different weight. Experimental results show that the proposed method can improve the detection rate of lesion in tongue image relative to single feature retrieval.

A Quantitative Investigation of Pulse and Tongue Features in Post-Stroke Depressive Patients and Healthy Volunteers: An Observational Pilot Study

BACKGROUND

Depression is among the most common neuropsychiatric complications after stroke, having a negative impact on one's quality of life. A number of therapeutic modalities have been used for post-stroke depression (PSD) including traditional Chinese medicine (TCM). However, a lack of objectivity in TCM hampers further improvement in diagnosis and research, since TCM diagnosis is mainly based on subjective judgment of clinicians. In this study, a modern TCM diagnostic device was used to conduct an objective study of pulse and tongue features in PSD patients and healthy individuals.

METHODS

A total of 67 volunteers participated. Pulse and tongue information of each participant was acquired and analyzed by the TCM Four Diagnosis Auxiliary Apparatus. Quantitative data were gathered and compared between the PSD group and the healthy group.

RESULTS

Higher rates of weak, slow, slippery, and string pulse were observed in the PSD group (p < 0.01), whereas normal pulse (p < 0.01) was detected in the healthy group. In the tongue analysis, higher rates of purple tongue (p < 0.01) with yellow fur (p < 0.01) and pale-pink tongue (p = 0.023) with white fur (p < 0.01) were observed in the PSD and the healthy groups, respectively. Abnormal tongue features (old, soft, thin, enlarged, thorny, and cracked) were detected (p < 0.05) in the PSD group.

CONCLUSIONS

Objective and quantitative data of PSD patients and healthy individuals may help providing valuable clinical information for PSD research and establish quantitative TCM diagnostic standards for pulse and tongue diagnosis in clinical practice and research.

The association between objective tongue color and endoscopic findings: results from the Kyushu and Okinawa population study (KOPS)

Background

The relation between tongue color and gastroesophageal disease is unclear. This study was done to investigate the associations between tongue color (TC), endoscopic findings, Helicobacter.pylori infection status, and serological atrophic gastritis (SAG).

Methods

The participants were 896 residents of Ishigaki Island, Okinawa, aged 28–86 years. The tongue was photographed, esophagogastroduodenoscopy was done, and serum antibody to H.pylori was measured. SAG was defined as a serum Pepsinogen (PG)Ilevel ≤70 ng/ml and a PGI/IIratio ≤3.0. TC was measured by the device-independent international commission on Illumination 1976 L*a*b* color space standards at four points: (1) edge, (2) posterior, (3) middle, and (4) apex. We also calculated the ratio of the tongue edge to the three other measured points to examine the association between the coating of the tongue and the endoscopic and laboratory findings.

Results

Participants were excluded who had two or more endoscopic findings (n = 315) or who had SAG without seropositivity to H.pylori (n = 33). The remaining 548 participants were divided into three groups: SAG and seropositive to H.pylori (n = 67), seropositive to H.pylori alone (n = 56), and without SAG and seronegative for H.pylori (n = 425). We divided 425 residents into a single endoscopic finding positive group (n = 207) and a negative group, which served as a control (n = 218). The most frequent single endoscopic finding was esophageal hernia (n = 110), followed by erosive esophagitis (n = 35) and erosive gastritis (EG) (n = 45). EH was significantly associated with TC (2b*/1b*) (P < 0.05). EG was significantly associated with TC (3a*, 3b*) (P < 0.05). Seropositivity to H.pylori was significantly associated with TC (3 L*, 3 L*/1 L*) (P < 0.05, <0.01), and seropositivity to both H.pylori and SAG was significantly associated with TC (3 L*/1 L*) (P < 0.05). Multivariate analysis extracted TC (3a*, 3b*) as an independent factor associated with a differential diagnosis of EG (Odds ratio (OR) 2.66 P = 0.008, OR 2.17 P = 0.045).

Conclusions

The tongue body color of the middle area reflects acute change of gastric mucosa, such as erosive gastritis. Tongue diagnosis would be a useful, non-invasive screening tool for EG.

Tongue color changes within a menstrual cycle in eumenorrheic women

Tongue color (舌色 shé sè) has been used to diagnose abnormal body conditions for thousands of years in traditional Chinese Medicine (中醫 zhōng yī). However, it is not clear whether tongue color alters with physiological changes within a normal menstrual cycle (月經周期 yuè jīng zhōu qī). This study investigated difference in tongue color between the follicular phase and luteal phase in eumenorrheic women. Tongue surface photographs were taken in the follicular phase and the luteal phase of thirty-two volunteers with biphasic basal body temperature. Color values on five areas of the tongue surface were examined and comparisons of color values were made between the two phases according to the red–green–blue (RGB), hue–saturation–brightness (HSB), luminance-a-b (Lab), and cyan–magenta–yellow–black (CMYK) models. Based on the RGB model, the values of green and blue in the tip area were larger in the follicular phase than both in the luteal phase. The values of magenta and yellow based in the CMYK model were smaller in the tip area in the follicular phase than that in the luteal phase. The saturation in the tip area was smaller in the follicular phase than that in the luteal phase. Based on the Lab model, b value in the middle area was smaller in the follicular phase than that in the luteal phase. The data revealed that tongue color varied within a eumenorrheic menstrual cycle, suggesting that tongue color differences between the follicular and luteal phases need to be considered while practicing tongue diagnosis (舌診 shé zhěn) or performing clinical studies among childbearing women.

Significant Geometry Features in Tongue Image Analysis

The shape of a human tongue and its relation to a patients' state, either healthy or diseased (and if diseased which disease), is quantitatively analyzed using geometry features by means of computerized methods in this paper. Thirteen geometry features based on measurements, distances, areas, and their ratios are extracted from tongue images captured by a specially designed device with color correction. Using the features, 5 tongue shapes (rectangle, acute and obtuse triangles, square, and circle) are defined based on traditional Chinese medicine (TCM). Classification of the shapes is subsequently carried out with a decision tree. A large dataset consisting of 672 images comprising of 130 healthy and 542 disease examples (labeled according to Western medical practices) are tested. Experimental results show that the extracted geometry features are effective at tongue shape classification (coarse level). Even if more than one disease class belongs to the same shape, the disease classes can still be discriminated via fine level classification using a combination of the geometry features, with an average accuracy of 76.24% for all shapes.

Advances in Patient Classification for Traditional Chinese Medicine: A Machine Learning Perspective

As a complementary and alternative medicine in medical field, traditional Chinese medicine (TCM) has drawn great attention in the domestic field and overseas. In practice, TCM provides a quite distinct methodology to patient diagnosis and treatment compared to western medicine (WM). Syndrome (ZHENG or pattern) is differentiated by a set of symptoms and signs examined from an individual by four main diagnostic methods: inspection, auscultation and olfaction, interrogation, and palpation which reflects the pathological and physiological changes of disease occurrence and development. Patient classification is to divide patients into several classes based on different criteria. In this paper, from the machine learning perspective, a survey on patient classification issue will be summarized on three major aspects of TCM: sign classification, syndrome differentiation, and disease classification. With the consideration of different diagnostic data analyzed by different computational methods, we present the overview for four subfields of TCM diagnosis, respectively. For each subfield, we design a rectangular reference list with applications in the horizontal direction and machine learning algorithms in the longitudinal direction. According to the current development of objective TCM diagnosis for patient classification, a discussion of the research issues around machine learning techniques with applications to TCM diagnosis is given to facilitate the further research for TCM patient classification.

Proposal for a new noncontact method for measuring tongue moisture to assist in tongue diagnosis and development of the tongue image analyzing system, which can separately record the gloss components of the tongue

Tongue diagnosis is a noninvasive diagnosis and is traditionally one of the most important tools for physicians who practice Kampo (traditional Japanese) medicine. However, it is a subjective process, and its results can depend on the experience of the physician performing it. Previous studies have reported how to measure and evaluate the shape and color of the tongue objectively. Therefore, this study focused on the glossy component in order to quantify tongue moisture in tongue diagnosis. We hypothesized that moisture appears as a gloss in captured images and measured the amount of water on the tongue surface in 13 subjects. The results showed a high correlation between the degree of gloss and the amount of water on the tongue surface and suggested that the moisture on the tongue can be estimated by the degree of gloss in a captured image. Because the moisture level on the tongue changes during the course of taking photos, it became clear that we had to wait at least 3 minutes between photos. Based on these results, we established the tongue image analyzing system (TIAS), which can consistently record the gloss and color of the tongue surface simultaneously.

Detecting diabetes mellitus and nonproliferative diabetic retinopathy using tongue color, texture, and geometry features

Diabetes mellitus (DM) and its complications leading to diabetic retinopathy (DR) are soon to become one of the 21st century's major health problems. This represents a huge financial burden to healthcare officials and governments. To combat this approaching epidemic, this paper proposes a noninvasive method to detect DM and nonproliferative diabetic retinopathy (NPDR), the initial stage of DR based on three groups of features extracted from tongue images. They include color, texture, and geometry. A noninvasive capture device with image correction first captures the tongue images. A tongue color gamut is established with 12 colors representing the tongue color features. The texture values of eight blocks strategically located on the tongue surface, with the additional mean of all eight blocks are used to characterize the nine tongue texture features. Finally, 13 features extracted from tongue images based on measurements, distances, areas, and their ratios represent the geometry features. Applying a combination of the 34 features, the proposed method can separate Healthy/DM tongues as well as NPDR/DM-sans NPDR (DM samples without NPDR) tongues using features from each of the three groups with average accuracies of 80.52% and 80.33%, respectively. This is on a database consisting of 130 Healthy and 296 DM samples, where 29 of those in DM are NPDR.

Traditional East Asian medicine: how to understand and approach diagnostic findings and patterns in a modern scientific framework?

Research into the diagnostic methods and patterns of traditional East Asian medical (TEAM) systems of practice such as acupuncture and herbal medicine face certain challenges due to the nature of thinking in TEAM and the subjective basis of judgments made in practice. The TEAM-based diagnosis can take into account various findings and signs such as the appearance of the tongue, palpable qualities of the radial pulses, palpable qualities and findings on the abdomen, the complexion of the patient and so on. Both diagnostic findings and the patterns of diagnosis cannot be assumed to have objective bases or to be causally related to the complaints of the patient. However, the diagnoses of TEAM based acupuncture and herbal medicine have tended to look at pictures of the whole patient and rather than focus on a particular symptom, they have looked across a myriad of signs and symptoms to decide or identify the 'pattern' of diagnosis according to the theory in question. Although open for selective and subjective biases each diagnosis pattern always comes with a prescribed treatment tailored to the pattern. Further, the same research requirements needed for the validation of the diagnoses are needed also for these clinical observations and judgments. Hence, it is necessary, albeit challenging for research on TEAM diagnoses to first address these issues before proceeding to more complex investigations such as the development of instruments for making diagnostic observations, instruments for forming diagnostic conclusions or studies investigating the physiological bases of the diagnostic patterns. Preliminary work has started and instruments have been made, but we suggest that any instrumentation must necessarily be first validated by matching of the calibrated or scaled observations or judgments to observations made and agreed upon by relevant experts. Reliability of all observations and judgments are needed before any other tool, technology or more advanced approach can proceed and also whenever the natural system of diagnosis-treatment is applied in clinical trials. In this paper the authors highlight the core problems and describe a step wise process for addressing them.

Study of factors involved in tongue color diagnosis by kampo medical practitioners using the farnsworth-munsell 100 hue test and tongue color images

In traditional Japanese medicine (Kampo medicine), tongue color is important in discerning a patient's constitution and medical conditions. However, tongue color diagnosis is susceptible to the subjective factors of the observer. To investigate factors involved in tongue color diagnosis, both color discrimination and tongue color diagnosis were researched in 68 Kampo medical practitioners. Color discrimination was studied by the Farnsworth-Munsell 100 Hue test, and tongue color diagnosis was studied by 84 tongue images. We found that overall color discrimination worsened with aging. However, the color discrimination related to tongue color regions was maintained in subjects with 10 or more years of Kampo experience. On the other hand, tongue color diagnosis significantly differed between subjects with <10 years of experience and ≥10 years of experience. Practitioners with ≥10 years of experience could maintain a consistent diagnosis of tongue color regardless of their age.

Computerized tongue image segmentation via the double geo-vector flow

BACKGROUND

Visual inspection for tongue analysis is a diagnostic method in traditional Chinese medicine (TCM). Owing to the variations in tongue features, such as color, texture, coating, and shape, it is difficult to precisely extract the tongue region in images. This study aims to quantitatively evaluate tongue diagnosis via automatic tongue segmentation.

METHODS

Experiments were conducted using a clinical image dataset provided by the Laboratory of Traditional Medical Syndromes, Shanghai University of TCM. First, a clinical tongue image was refined by a saliency window. Second, we initialized the tongue area as the upper binary part and lower level set matrix. Third, a double geo-vector flow (DGF) was proposed to detect the tongue edge and segment the tongue region in the image, such that the geodesic flow was evaluated in the lower part, and the geo-gradient vector flow was evaluated in the upper part.

RESULTS

The performance of the DGF was evaluated using 100 images. The DGF exhibited better results compared with other representative studies, with its true-positive volume fraction reaching 98.5%, its false-positive volume fraction being 1.51%, and its false-negative volume fraction being 1.42%. The errors between the proposed automatic segmentation results and manual contours were 0.29 and 1.43% in terms of the standard boundary error metrics of Hausdorff distance and mean distance, respectively.

CONCLUSIONS

By analyzing the time complexity of the DGF and evaluating its performance via standard boundary and area error metrics, we have shown both efficiency and effectiveness of the DGF for automatic tongue image segmentation.

Statistical analysis of tongue images for feature extraction and diagnostics

In this paper, an in-depth analysis on the statistical distribution characteristics of human tongue color that aims to propose a mathematically described tongue color space for diagnostic feature extraction is presented. Three characteristics of tongue color space, i.e., tongue color gamut that defines the range of colors, color centers of 12 tongue color categories, and color distribution of typical image features in the tongue color gamut, are elaborately investigated in this paper. Based on a large database, which contains over 9000 tongue images collected by a specially designed noncontact colorimetric imaging system using a digital camera, the tongue color gamut is established in the CIE chromaticity diagram by an innovatively proposed color gamut boundary descriptor using one-class SVM algorithm. Thereafter, centers of 12 tongue color categories are defined accordingly. Furthermore, color distributions of several typical tongue features, such as red points and petechial points, are obtained to build a relationship between the tongue color space and color distributions of various tongue features. With the obtained tongue color space, a new color feature extraction method is proposed for diagnostic classification purposes, with experimental results validating its effectiveness.

Tongue color analysis for medical application

An in-depth systematic tongue color analysis system for medical applications is proposed. Using the tongue color gamut, tongue foreground pixels are first extracted and assigned to one of 12 colors representing this gamut. The ratio of each color for the entire image is calculated and forms a tongue color feature vector. Experimenting on a large dataset consisting of 143 Healthy and 902 Disease (13 groups of more than 10 samples and one miscellaneous group), a given tongue sample can be classified into one of these two classes with an average accuracy of 91.99%. Further testing showed that Disease samples can be split into three clusters, and within each cluster most if not all the illnesses are distinguished from one another. In total 11 illnesses have a classification rate greater than 70%. This demonstrates a relationship between the state of the human body and its tongue color.

Classification and Progression Based on CFS-GA and C5.0 Boost Decision Tree of TCM Zheng in Chronic Hepatitis B

Chronic hepatitis B (CHB) is a serious public health problem, and Traditional Chinese Medicine (TCM) plays an important role in the control and treatment for CHB. In the treatment of TCM, zheng discrimination is the most important step. In this paper, an approach based on CFS-GA (Correlation based Feature Selection and Genetic Algorithm) and C5.0 boost decision tree is used for zheng classification and progression in the TCM treatment of CHB. The CFS-GA performs better than the typical method of CFS. By CFS-GA, the acquired attribute subset is classified by C5.0 boost decision tree for TCM zheng classification of CHB, and C5.0 decision tree outperforms two typical decision trees of NBTree and REPTree on CFS-GA, CFS, and nonselection in comparison. Based on the critical indicators from C5.0 decision tree, important lab indicators in zheng progression are obtained by the method of stepwise discriminant analysis for expressing TCM zhengs in CHB, and alterations of the important indicators are also analyzed in zheng progression. In conclusion, all the three decision trees perform better on CFS-GA than on CFS and nonselection, and C5.0 decision tree outperforms the two typical decision trees both on attribute selection and nonselection.