Extraction of the tongue body from digital images is essential for automated tongue diagnoses in traditional Chinese medicine. This paper presents a fully automated active contour initial method that utilizes prior knowledge of the tongue shape and its location in tongue images. Then colorspace information is introduced to control curve evolution. Combining the geometrical Snake model with the parameterized GVFSnake model, a novel approach for automatic tongue segmentation: C 2 G 2 FSnake (color control-geometric & gradient flow Snake) is proposed. This method increases the curve velocity but decreases the complexity. C 2 G 2 FSnake greatly extends practical usage to tongue segmentation, at the same time increasing the precision. Compared with other state-of-the-art works using different images of tongue color, C 2 G 2 FSnake realizes automatic tongue segmentation with greatly improved accuracy.

BackgroundIn Traditional Chinese Medicine (TCM), tongue diagnosis has been an important diagnostic method for the last 3000 years. Tongue diagnosis is a non-invasive, simple and valuable diagnostic tool. TCM treats the tongue coating on a very sensitive scale that reflects physiological and pathological changes in the organs, especially the spleen and stomach. Tongue coating can diagnose disease severity and determine the TCM syndrome (“Zheng” in Chinese). The biological bases of different tongue coating appearances are still poorly understood and lack systematic investigation at the molecular level.MethodsTongue coating samples were collected from 70 chronic gastritis patients and 20 normal controls. 16S rRNA denatured gradient gel electrophoresis (16S rRNA–DGGE) and liquid chromatography and mass spectrometry (LC–MS) were designed to profile tongue coatings. The statistical techniques used were principal component analysis and partial least squares–discriminate analysis.ResultsTen potential metabolites or markers were found in chronic gastritis patients, including UDP-D-galactose, 3-ketolactose, and vitamin D2, based on LC–MS. Eight significantly different strips were observed in samples from chronic gastritis patients based on 16S rRNA–DGGE. Two strips, Strips 8 and 10, were selected for gene sequencing. Strip 10 sequencing showed a 100% similarity to Rothia mucilaginosa. Strip 8 sequencing showed a 96.2% similarity to Moraxella catarrhalis.ConclusionsChanges in glucose metabolism could possibly form the basis of tongue coating conformation in chronic gastritis patients. The study revealed important connections between metabolic components, microecological components and tongue coating in chronic gastritis patients. Compared with other diagnostic regimens, such as blood tests or tissue biopsies, tongue coating is more amenable to, and more convenient for, both patients and doctors.

BackgroundVisual 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.MethodsExperiments 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.ResultsThe 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.ConclusionsBy 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.

BackgroundIn Traditional Chinese Medicine (TCM), the lip diagnosis is an important diagnostic method which has a long history and is applied widely. The lip color of a person is considered as a symptom to reflect the physical conditions of organs in the body. However, the traditional diagnostic approach is mainly based on observation by doctor’s nude eyes, which is non-quantitative and subjective. The non-quantitative approach largely depends on the doctor’s experience and influences accurate the diagnosis and treatment in TCM. Developing new quantification methods to identify the exact syndrome based on the lip diagnosis of TCM becomes urgent and important. In this paper, we design a computer-assisted classification model to provide an automatic and quantitative approach for the diagnosis of TCM based on the lip images.MethodsA computer-assisted classification method is designed and applied for syndrome diagnosis based on the lip images. Our purpose is to classify the lip images into four groups: deep-red, red, purple and pale. The proposed scheme consists of four steps including the lip image preprocessing, image feature extraction, feature selection and classification. The extracted 84 features contain the lip color space component, texture and moment features. Feature subset selection is performed by using SVM-RFE (Support Vector Machine with recursive feature elimination), mRMR (minimum Redundancy Maximum Relevance) and IG (information gain). Classification model is constructed based on the collected lip image features using multi-class SVM and Weighted multi-class SVM (WSVM). In addition, we compare SVM with k-nearest neighbor (kNN) algorithm, Multiple Asymmetric Partial Least Squares Classifier (MAPLSC) and Naïve Bayes for the diagnosis performance comparison. All displayed faces image have obtained consent from the participants.ResultsA total of 257 lip images are collected for the modeling of lip diagnosis in TCM. The feature selection method SVM-RFE selects 9 important features which are composed of 5 color component features, 3 texture features and 1 moment feature. SVM, MAPLSC, Naïve Bayes, kNN showed better classification results based on the 9 selected features than the results obtained from all the 84 features. The total classification accuracy of the five methods is 84%, 81%, 79% and 81%, 77%, respectively. So SVM achieves the best classification accuracy. The classification accuracy of SVM is 81%, 71%, 89% and 86% on Deep-red, Pale Purple, Red and lip image models, respectively. While with the feature selection algorithm mRMR and IG, the total classification accuracy of WSVM achieves the best classification accuracy. Therefore, the results show that the system can achieve best classification accuracy combined with SVM classifiers and SVM-REF feature selection algorithm.ConclusionsA diagnostic system is proposed, which firstly segments the lip from the original facial image based on the Chan-Vese level set model and Otsu method, then extracts three kinds of features (color space features, Haralick...