A Perspective on Tongue Diagnosis in Patients with Breast Cancer

Introduction. Breast cancer (BC) is the most common cancer in women and patients with BC often undergo complex treatment. In Taiwan, nearly 80% of patients with BC seek traditional Chinese medicine (TCM) during adjuvant chemotherapy to relieve discomfort and side effects. This study investigated tongue features and pattern differentiation through noninvasive TCM tongue diagnosis in patients with BC. Materials and Methods. This cross-sectional, case-controlled, retrospective observational study collected patient data through a chart review. The tongue features were extracted using the automatic tongue diagnosis system (ATDS). Nine tongue features, including tongue shape, tongue color, fur thickness, fur color, saliva, tongue fissures, ecchymoses, teeth marks, and red dots, were analyzed. Results and Discussion. Objective image analysis techniques were used to identify significant differences in the many tongue features between BC patients and non-BC individuals. A significantly larger proportion of patients with BC had a small tongue ( p < 0.001 ), pale tongue ( p < 0.001 ), thick fur ( p < 0.001 ), yellow fur ( p < 0.001 ), wet saliva ( p < 0.001 ), thick tongue fur ( p < 0.001 ), fissures ( p = 0.040 ), and ecchymoses in the heart-lung area ( p = 0.013 ). According to logistic regression, small tongue shape, pale tongue color, yellow fur color, wet saliva, and the amounts of fissures were associated with a significantly increased odds ratio for BC. Conclusions. This study showed significant differences in tongue features, such as small tongue shape, pale tongue color, thick fur, yellow fur color, wet saliva, fissure, and ecchymoses in the heart-lung area in patients with BC. These tongue features would imply yin deficiency, deficiencies of blood, stagnation of heat, and phlegm/blood stasis in TCM theory. There is a need to investigate effective and safe treatment to enhance the role of TCM in integrated medical care for patients with BC.

Construction of a Standardized Tongue Image Database for Diagnostic Education: Development of a Tongue Diagnosis e-Learning System

Tongue examination is an important diagnostic method for judging pathological conditions in Kampo (traditional Japanese medicine), but it is not easy for beginners to learn the diagnostic technique. One reason is that there are few objective diagnostic criteria for tongue examination findings, and the educational method for tongue examination is not standardized in Japan, warranting the need for a tongue image database for e-learning systems that could dramatically improve the efficiency of education. Therefore, we constructed a database comprising tongue images whose findings were determined on the basis of votes given by five Kampo medicine specialists (KMSs) and confirmed the educational usefulness of the database for tongue diagnosis e-learning systems. The study was conducted in the following five steps: development of a tongue imaging collection system, collection of tongue images, evaluation and annotation of tongue images, development of a tongue diagnosis e-learning system, and verification of the educational usefulness of this system. Five KMSs evaluated the tongue images obtained from 125 participants in the following eight aspects: (i) tongue body size, (ii) tongue body color, (iii) tongue body dryness and wetness, (iv) tooth marks on the edge of the tongue, (v) cracks on the surface of the tongue, (vi) thickness of tongue coating, (vii) color of tongue coating, and (viii) dryness and wetness of tongue coating. Medical students (MSs) were given a tongue diagnosis test using an e-learning system after a lecture on tongue diagnosis. The cumulative and individual match rates (%) (individual match rates of 100% (5/5), 80% (4/5), and 60% (3/5) are shown in parentheses, respectively) were as follows: (i) tongue body size: 92.8 (26.4/26.4/40.0); (ii) tongue body color: 83.2 (10.4/20.8/52.0); (iii) tongue body dryness and wetness: 88.8 (13.6/34.4/40.8); (iv) tooth marks on the edge of the tongue: 88.8 (6.4/35.2/47.2); (v) cracks on the surface of the tongue: 96.8 (24.0/35.2/37.6); (vi) thickness of tongue coating: 84.8 (7.2/21.6/56.0); (vii) color of tongue coating: 88.0 (15.2/37.6/35.2); and (viii) dryness and wetness of tongue coating: 74.4 (4.8/19.2/50.4). The test showed that the tongue diagnosis ability of MSs who attended a lecture on tongue diagnosis was almost the same as that of KMSs. We successfully constructed a tongue image database standardized for training specialists on tongue diagnosis and confirmed the educational usefulness of the e-learning system using a database. This database will contribute to the standardization and popularization of Kampo education.

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.

Automatic Segmentation of Tongue Image Based on Res-Unet Approach

Tongue diagnosis occupies an important position in the field of traditional Chinese medicine and has been developed for thousands of years. Doctors diagnose disease based on tongue images of patients stored in hospital databases. Hence, segmenting the tongue area of the tongue image facilitates the diagnosis and saves space for storing the tongue image. In order to solve such a challenging problem, we put forward a method combing Unet and Res-net for tongue image segmentation and implements the end-to-end form. In our Res-Unet architecture, including four encoder blocks and four decoder blocks, and the residual network (Res-net) block used as the backbone for each block. The upsampling layer restores the features extracted by the sampling layer. We use our own datasets named TongueSet1 (TS1) and Tongueset2 (TS2) that collected from the hospital. The collection methods of these two datasets are different; TS1 is collected by professionals while TS2 is taken by nurses. This method obtained the latest results on both data sets. We used accuracy (acc) and mean intersection (mIoU) as the evaluation indicators of our model. Among them, the acc and mIoU of the model on TongueSet1 reached 0.984 and 0.925, on TongueSet2 reached 0.985 and 0.925.

The Herbal Formula CWBSD Improves Sleep Quality Dependent on Oral Microbial Type and Tongue Diagnostic Features in Insomnia

Cheonwangbosim-dan (CWBSD) is a traditional Korean herb formula that has been widely prescribed for insomnia patients with a heart-yin deficiency (HYD) pattern. Several studies have reported that heart function and insomnia are interrelated, and few have explored associations between insomnia, oral microbiota, and tongue diagnosis. This study aimed to evaluate the effects of CWBSD on primary insomnia, tongue diagnosis, and oral microbiota. At baseline, 56 patients with primary insomnia were assigned to two groups, a HYD group and a non-HYD (NHYD) group and they took CWBSD for 6 weeks. During the study, Pittsburgh Sleep Quality Indices (PSQIs) and Insomnia Severity Indices (ISIs) decreased significantly in both groups. However, the PSQI reduction observed in the HYD group was greater than in the NHYD group and sleep times increased only in the HYD group. As sleep quality improved, the amount of tongue coating increased at the posterior tongue, where heart function appears. At baseline, the HYD and NHYD group had a specific oral microbiota (Veillonella at genus level), but no significant change was observed after taking CWBSD. Additionally, subjects were divided into two oral microbiota types (“orotypes”). The genera Prevotella, Veillonella, or Neisseria were abundant in each orotype. The reduction in PSQI in orotype 1 during the 6-week treatment period was greater than in orotype 2. In conclusion, this study shows that CWBSD could be used to treat primary insomnia in patients with a HYD pattern as determined using tongue diagnosis and oral microbiota distributional patterns.