This paper reviewed researches reported in the last 10 years on traditional Chinese medicine (TCM) facial diagnosis information acquisition and recognition. It summarized the information acquisition environment, facial segmentation method, recognition method and analysis of facial characteristics. Some clinical application examples based on modern consultation technologies were enumerated. Meanwhile, analysis was made on shortcomings of TCM facial diagnosis. It showed direction for its in-depth study.

The technical structure of a low-cost thermal imaging system (TIM) lunched on a mobile phone was investigated, which consists of a thermal infrared module and mobile phone and application software. The designing strategies and technical factors toward realizing various TIM array performances are interpreted, including sensor cost and Noise Equivalent Temperature Difference (NETD). In the software algorithm, a mechanism for scene-change detection was implemented to optimize the efficiency of non-uniformity correction (NUC). The performance experiments and analysis indicate that the NETD of the system can be smaller than 150 mK when the integration time is larger than 16 frames. Furthermore, a practical application for human temperature monitoring during physical exercise is proposed and interpreted. The measurement results support the feasibility and facility of the system in the medical application.
Algorithms ; Body Temperature ; Cell Phone ; Humans ; Infrared Rays ; Mobile Applications

OBJECTIVE: To explore the immunological mechanism of exfoliative tongue fur in children with asthma. METHODS: Thirty-nine children with asthma, twenty-eight children with repetitive respiratory tract infection (non-asthma) and eleven healthy children were divided into five groups, which were asthma with exfoliative fur or with non-exfoliative fur groups, non-asthma with exfoliative fur or with non-exfoliative fur groups and normal control group. The concentrations of keratin 13 and bcl-2 in cells exfoliated from tongue fur were detected by immunohistochemical method. The expression levels of blood cell chemokine receptor-3 (CCR-3) and CD4(+) were examined by flow cytometry, and the levels of serum cortisol and IgE were detected by radioimmunoassay. RESULTS: The levels of blood CD4(+) and CCR-3 of children with asthma and exfoliative fur were higher than those in the asthma with non-exfoliative fur group and the normal control group (P<0.05). The serum level of cortisol in the groups of asthma with exfoliative fur and non-asthma with exfoliative fur were lower than that in the other groups (P<0.05). The serum levels of IgE in asthma with exfoliative fur or with non-exfoliative fur groups were higher than that in the other groups (P<0.05). Concentrations of keratin 13 in the cells exfoliated from tongue fur in the groups of asthma or non-asthma with exfoliative fur were lower than that of the other groups (P<0.05). There was no significant difference of expression level of bcl-2 in the cells exfoliated from tongue fur among these five groups. CONCLUSION: There is a reasonably close relationship between the formation of exfoliative tongue fur and the immune system such as low level of serum cortisol and high levels of blood CD4(+) and CCR-3, which may all promote the formation of exfoliative fur. The disability of keratinization and apoptosis of epithelial cells of tongue may also be one cause for its formation.

To explore the changes in metabolites in the greasy tongue coating in patients with chronic gastritis.

OBJECTIVE: To explore microcosmic information in chronic gastritis dampness syndrome by using serum proteomics of patients with chronic gastritis dampness syndrome. METHODS: Serum proteomics of 18 dampness syndrome cases, 17 non-dampness syndrome cases in chronic gastritis patients and 8 normal controls were analyzed by surface enhanced laser desorption/ionization-time of flight (SELDI-TOF) protein-chip. RESULTS: There was a high expression trend in three ratios of charge (of an electron) to mass (M/S) of 3.2 kD, 6.4 kD and 8.1 kD of protein expression spectrum from patients with chronic gastritis dampness syndrome, and the wave peak value was over 10 units. There was a low expression trend in above-mentioned sites of protein expression spectrum from patients with chronic gastritis non-dampness syndrome and normal group. The wave peak value of patients with chronic gastritis non-dampness syndrome was about or below 10 units, and the wave peak value in normal group was below 5 units. CONCLUSION: There exists a certain significance to explore biologic theory basis of chronic gastritis dampness syndrome by analyzing the serum proteomics.

Abstract: In this paper, factors contributing to the formation of pulse wave were analyzed based on hemodynamic principles. It is considered that formation of pulse wave was related to its propagation and reflection characteristics. Propagation of the pulse wave was characterized by pulse wave velocity, and reflection of the pulse wave was characterized by reflection coefficient. Pulse wave velocity and reflection coefficient were proposed as the eigenvectors of pulse wave in pulse diagnosis of traditional Chinese medicine, and support vector machine (SVM) was used to recognize slippery pulse, stringy pulse and plain pulse. Pulse wave velocity and reflection coefficient of the slippery, stringy and plain pulses in healthy people were calculated in this study, and SVM with Gaussian radial basis function was used for classifying. Results showed that pulse wave velocity and reflection coefficient with physiological and pathological significance had advantages in distinguishing slippery pulse, stringy pulse and plain pulse, which offered a new idea for recognizing pulse condition.

This article was aimed to study the proteomic spectra expression of traditional Chinese medicine (TCM) cold and heat constitution rats with two-dimensional gel electrophoresis (2-DE), in order to search for the cold and heat-associated proteins for the investigation of the biological basis of TCM cold and heat body constitution formation. The total protein in rat’s liver cell was extracted. The 2-DE and MALDI-TOF/TOF mass spectrometry (MS) were used in the screening and identification of differentially expressed proteins of cold and heat constitution rats. The results showed that a total of 10 different points in the protein expression were obtained with statistical significance after screening and MS, which were carbamoyl-phosphate synthase, protein disulfide isomerase associated 3, catalase, hydroperoxide isomerase, cytosol aminopeptidase, glutamate dehydrogenase 1, 3-hydroxy-3-methylglutaryl-coenzyme A synthase 2, heat shock protein 60 (Hsp60) precursor, homocysteine, 78 kDa glucose-regulated protein precursor. It was concluded that some differences were existed in the proteomic spectra expression of TCM cold and heat constitution rats. The abnormality of enzyme protein metabolism may be one of the material bases for the formation of cold and heat constitution.

Objective To Screen serum protein markers related to CRF and establish a diagnosis model,exploring and discussing its significance in serodiagnosis by comparing differences of serum protein spectrum expression between patients with chronic renal failure (CRF) and control group.Methods The trial included 62 CRF patients and 28 control ones.Serum samples were tested by surface enhanced laser desorption/ionization-time of flight-mass spectrometry (SELDI-TOF-MS).The data were analyzed to screen serum proteomic biomarkers.By bioinformatics analysis,decision classification tree models were to be established and tested.Results A total of 19 effective protein peaks were significantly different between CRF and normal control (P＜0.001) at m/z range of 1 500 to 30 000,among which 18 showed low expression and 1 showed high expression in CRF.CRF and normal control were obviously different in the clustering;By bioinformatics analysis,a CRF-normal controls of the diagnostic decision tree model was developed,which was 87.8% in with prediction accuracy rate of 87.8% sensitivity of 87.1% and a specificity of 89.3%.Condusion Diagnostic decision tree model provides a more accurate prediction and solid experimental evidence for early clinical diagnosis.

Objective To summarize and analyze relevant literature on image feature extraction,segmentation,and classification of tongue and facial diagnosis,we explore the research hotspots and development trends in this field and provide ideas for future research on image processing of tongue and facial diagnosis.Methods China National Knowledge Infrastructure was used as the data source,and 439 papers were included according to the exclusion criteria,the inclusion criteria,and the search strategy.Finally,Gephi software was applied to visualize and analyze the co-word network of authors,research institutions,and keywords of relevant literature.Results The overall number of articles issued is low as seen in the annual volume,but the overall trend is steadily increasing.The research team is mainly represented by the team of Li Fufeng,Zhang Xinfeng,Xu Jiatuo,Wang Yiqin,and Wang Hongwu.Most of the research institutes are regional medical-industrial crossover collaborations.Conclusion Hot research trends gradually toward deep learning for image processing.Meanwhile,teamwork across regions and institutions needs to be strengthened.It is recommended to further promote the development of multidisciplinary cross-fertilization and intelligent and objective quantification of Traditional Chinese Medicine diagnosis(tongue and face diagnosis).

The lip color of a person is closely related to his or her health in the visual diagnosis of traditional Chinese medicine (TCM). The traditional method to judge the color of lips is through observing by a TCM doctor. The diagnosis result is affected not only by the doctor's knowledge and diagnosis experience, but also by the light, temperature and other environmental impacts. For these reasons, sometimes different doctors may make different judgement for the same lips. So it is urgently needed that an objective evaluation as reference for doctors can be obtained. A method based on support vector machine (SVM) that classifies lip color by computer automatically is presented in the present paper. Firstly, nine features of lip color in Hue, Saturation and Intensity (HSI) color space were extracted. Then, according to different combinations of these features five different experiments were conducted. By comparing the results of these experiments, it was discovered that the mean value is one of the most important features for the lip color. The overall effect of classification is better when the mean value and variance of HSI were chosen than other characteristics. In addition, experiments results demonstrated that the accuracy rate of classification is not improved when more features were adopted. The objective of the present paper is to select the appropriate characteristics and to combine them effectively to classify lip colors.
Color ; Diagnosis, Differential ; Lip ; Medicine, Chinese Traditional ; methods ; Pattern Recognition, Automated ; methods ; Support Vector Machine