• 융합신호처리학회논문지
• /
• 제20권4호
• /
• pp.226-231
• /
• 2019

한방 설진에서 WTCI(Winkel Tongue Coating Index) 설태 평가는 환자의 설태량 측정을 위한 중요한 객관적인 지표 중의 하나이다. 그러나 이전의 WTCI 설태 평가는 혀영상으로부터 설태 부분을 추출하여 전체 혀 영역에서 추출된 설태 영역의 비율을 정량적으로 측정하는 방법이 대부분으로 혀영상의 촬영 조건이나 설태 인식 성능에 의해서 비객관적 측정의 문제점이 있었다. 따라서 본 논문에서는 빅데이터를 기반으로 하는 인공지능의 딥러닝 방법을 적용하여 설태량을 분류하여 평가하는 딥러닝 기반의 WTCI 평가 방법을 제안하고 검증한다. 설태 평가 방법에 있어서 딥러닝의 유효성 검증을 위해서는 CNN을 학습 모델로 사용하여 소태, 박태, 후태의 3가지 유형의 설태량을 분류한다. 설태 샘플 영상을 학습 및 검증 데이터로 구축하여 CNN 기반의 딥러닝 모델로 학습한 결과 96.7%의 설태량 분류 정확성을 보였다.

• 융합신호처리학회논문지
• /
• 제16권3호
• /
• pp.96-101
• /
• 2015

본 논문에서는 한방 의료의 설진에 있어서 객관적인 진단 지표의 생성을 위해 자외선 혀 영상 채널 분석과 설태 검출에 의한 WTCI(Winkel Tongue Coating Index) 설태 평가 방법을 제안한다. 제안한 방법은 설태 영역 검출을 위하여 자외선 광원에 의해 생성된 혀 영상의 칼라 모델별 각 색상 채널의 히스토그램을 분석한다. 그리고 선택된 혀 영상 채널을 이용하여 설태 검출에서의 성능 검증 실험을 수행한다. 또한 WTCI 설태 지표 생성을 위한 테스트 샘플과 실영상 검증 실험을 실시하여 설진 지표의 객관성을 검증한다. 제안한 컴퓨터 지원 WTCI 설태 평가 방법의 성능 평가를 위해서 샘플 영상을 이용하여 계산의 정확성을 검증하고, 다양한 실제 피실험자의 혀 영상에 적용한 결과 성공적인 결과를 보였다.

• 대한한방내과학회지
• /
• 제35권2호
• /
• pp.157-174
• /
• 2014

Objectives : The aims of this study were to evaluate the diagnostic values of tongue coating thickness and sterno-costal angle as the quantitative diagnostic indicators in functional dyspepsia. Methods : We surveyed 60 functional dyspepsia patients recruited by the clinical trial, 'Clinical Trial for Evaluation on Availability of tongue diagnosis system (CTS-1000) : a Pilot study'. The patients were classified into three groups according to Rome III criteria for functional dyspepsia, and categorized into five groups according to Instrument of pattern identification for functional dyspepsia. Nepean dyspepsia index-Korean version (NDI-K) score, tongue coating thickness (percentage of tongue coating by tongue diagnosis system (CTS-1000), and weight of tongue coating by microbalance), sterno-costal angle, duration of illness and body mass index (BMI) were investigated. Results : Among the 5 types by instrument of pattern identification for functional dyspepsia, a significant difference of percentage of tongue coating was found. Percentage of tongue coating and weight of tongue coating showed significant correlation with total NDI-K score. Sterno-costal angle showed strong positive correlation with BMI and also showed significant difference between the non-overweight (BMI<23, n=32) and overweight ($BMI{\geq}23$, n=28) groups. Conclusions : Tongue coating thickness showed its potential as a new quantitative diagnostic indicator of functional dyspepsia. Further studies on the sterno-costal angle are anticipated to evaluate its potential as a new quantitative diagnostic indicator.

• 한국한의학연구원논문집
• /
• 제13권3호
• /
• pp.119-124
• /
• 2007

Introduction: In Oriental medicine, the status of tongue is the important indicator to diagnose one's health, because it represents physiological and clinicopathological changes of inner parts of the body. The method of tongue diagnosis is not only convenient but also non-invasive, so tongue diagnosis is most widely used in Oriental medicine. By the way, since tongue diagnosis is affected by examination circumstances a lot, its performance depends on a light source, degrees of an angle, a medical doctor's condition etc. Therefore, it is not easy to make an objective and standardized tongue diagnosis. In order to solve this problem, in this study, we tried to design a discriminant function for thick and thin coating with color vectors of preprocessed image. Method: 52 subjects, who were diagnosed as white-coated tongue, were involved. Among them, 45 subjects diagnosed as thin coating and 7 subjects diagnosed as thick coating by oriental medical doctors, and then their tongue images were obtained from a digital tongue diagnosis system. Using those acquired tongue images, we implemented two steps: Preprocessing and image analyzing. The preprocessing part of this method includes histogram equalization and histogram stretching at each color component, especially, intensity and saturation. It makes the difference between tongue substance and tongue coating was more visible, so that we can separate tongue coating easily. Next part, we analyzed the characteristic of color values and found the threshold to divide tongue area into coating area. Then, from tongue coating image, it is possible to extract the variables that were important to classify thick and thin coating. Result : By statistical analysis, two significant vectors, associated with G, were found, which were able to describe the difference between thick and thin coating very well. Using these two variables, we designed the discriminant function for coating classification and examined its performance. As a result, the overall accuracy of thick and thin coating classification was 92.3%. Discussion : From the result, we can expect that the discriminant function is applicable to other coatings in a similar way. Also, it can be used to make an objective and standardized diagnosis.

• 대한의용생체공학회:의공학회지
• /
• 제44권4호
• /
• pp.242-254
• /
• 2023

Although upper respiratory tract infections (URTIs) are common diseases, there have been no studies of their relationship with the indices obtained from tongue image analyses. The purpose of this study was to identify a tongue index through an analysis of tongue images (TIs) showing significant changes before and after treatment in patients with URTIs. A computerized tongue image acquisition system was developed to acquire TIs from subjects in the same environment. An image was taken from each of 39 URTI patients and 39 healthy controls. For the patients, images were acquired before and after treatment to identify changes. The tongue area was classified into a tongue body and a tongue coating, and the coating ratio between the two areas, the average value of the colour of each area, and teeth marks were calculated. No significant difference was observed in age or sex between the URTI patients and control participants. Heart rates were slightly different. The analysis of TIs showed that the luminance of the tongue coating and the coating area ratio were decreased, while the reddish value of the tongue body at the centre area increased as the treatment progressed. Tongue coating and body in URTIs had different colour and shape from those in the normal. It is expected that this result will contribute not only to the objectification of traditional Chinese medicine but also to diagnostic methods that do not involve face-to-face physician visit during the pandemic.

• 대한한방내과학회지
• /
• 제29권1호
• /
• pp.258-264
• /
• 2008

Objectives : The aim of this study was to confirm the characteristics of oral malodor patients by evaluating the differences of salivary flow rate, secretory immunoglobulin A (sIgA) level in saliva between the patient and control groups, and the correlation with the tongue coating, volatile sulfur compound (VSC), salivary flow rate and sIgA level in saliva in the patients group. Methods : Forty-seven patients with oral malodor and twenty healthy volunteers were included in this study. Their tongue coating was assessed with the Winkel tongue coating index, and salivary flow rate, sIgA concentrations in saliva and the level of VSC in oral cavity were measured. Results : There were no significant differences of the salivary flow rate and the sIgA level in saliva between the patient and control groups, but there was a significant relationship between the accumulation of tongue coating and the level of VSC in oral cavity. Conclusions : Our results suggest that tongue coating is closely related to oral malodor, but further studies are needed to confirm the relationship between tongue coating and sIgA level in saliva.

• 대한한방내과학회지
• /
• 제39권4호
• /
• pp.637-644
• /
• 2018

Objectives: In this study, the tongue features of patients with functional dyspepsia (FD) were compared with those of healthy controls. Methods: This prospective, case-control study was conducted on patients with FD and controls recruited at a single center. After screening, the subjects were allocated to the patient or control groups (patients=42, controls=40). Tongue images were acquired using a computerized tongue image acquisition system (CTIS). An independent t-test was conducted to compare the measurements from patients and controls. Binary logistic regression was performed to determine significant differences between the two groups after adjusting for age and sex. Results: The CIE $a^*$ color value in the tongue coating area was significantly lower in the patients with FD than in the controls (p=0.001). The tongue coating ratios were also significantly higher in the FD group than in the control group (p=0.003). We found that the CIE $a^*$ color value in the tongue coating area and the tongue coating ratios were significant predictive factors in both groups, based on binary regression analysis (p=0.016, 0.044, respectively). Conclusions: This study found that FD was significantly associated with CIE $a^*$ color value in the tongue coating area and tongue coating ratios. We suggest that these factors could be used as objective indicators of FD.

• 한국한의학연구원논문집
• /
• 제13권2호통권20호
• /
• pp.47-52
• /
• 2007

In Oriental medicine, the status of tongue is the important indicator to diagnose one's health, because it represents physiological and clinicopathological changes of inner parts of the body. The method of tongue diagnosis is not only convenient but also non-invasive, therefore, tongue diagnosis is one of the most widely used in Oriental medicine. But tongue diagnosis is affected by examination circumstances a lot. It depends on a light source, degrees of an angle, doctor's condition and so on. So it is not easy to make an objective and standardized tongue diagnosis. As part of way to solve this problem, in this study, we tried to design a discriminant function for white and yellow coating with multi-dimensional color vectors. There were 62 subjects involved in this study, among them 48 subjects diagnosed as white-coated tongue and 14 subjects diagnosed as yellow-coated tongue by oriental doctors. And their tongue images were acquired by a well-made Digital Tongue Diagnosis System. From those acquired tongue images, each coating section were extracted by oriental doctors, and then mean values of multi -dimensional color vectors in each coating section were calculated. By statistical analysis, two significant vectors, R in RGB space and H in HSV space, were found that they were able to describe the difference between white coating section and yellow coating section very well. Using these two values, we designed the discriminant function for coating classification and examined how good it works. As a result, the overall accuracy of coating classification was 98.4%. We can expect that the discriminant function for other coatings can be obtained in a similar way. Furthermore, if an automated segmentation algorithm of tongue coating is combined with these discriminant functions, an automated tongue coating diagnosis can be accomplished.

• 동의생리병리학회지
• /
• 제23권1호
• /
• pp.97-103
• /
• 2009

The status and the property of a tongue are the important indicators to diagnose one's health like physiological and clinicopathological changes of inner organs. However, the tongue diagnosis is affected by examination circumstances like a light source, patient's posture, and doctor's condition. To develop an automatic tongue diagnosis system for an objective and standardized diagnosis, classifying tongue coating is inevitable but difficult since the features like color and texture of the tongue coatings and substance have little difference, especially in the neighborhood on the tongue surface. The proposed method has two procedures; the first is to acquire the color table to classify tongue coatings and substance by automatically separating coating regions marked by oriental medical doctors, decomposing the color components of the region into hue, saturation and brightness and obtaining the 2nd order discriminant with statistical data of hue and saturation corresponding to each kind of tongue coatings, and the other is to apply the tongue region in an input image to the color table, resulting in separating the regions of tongue coatings and classifying them automatically. As a result, kinds of tongue coatings and substance were segmented from a face image corresponding to regions marked by oriental medical doctors and the color table for classification took hue and saturation values as inputs and produced the classification of the values into white coating, yellow coating and substance in a digital tongue diagnosis system. The coating regions classified by the proposed method were almost the same to the marked regions. The exactness of classification was 83%, which is the degree of correspondence between what Oriental medical doctors diagnosed and what the proposed method classified. Since the classified regions provide effective information, the proposed method can be used to make an objective and standardized diagnosis and applied to an ubiquitous healthcare system. Therefore, the method will be able to be widely used in Oriental medicine.

• 전자공학회논문지
• /
• 제51권6호
• /
• pp.175-182
• /
• 2014

한방에서 설진은 초기 병증을 진단할 수 있는 방법으로 객관적인 진단 지표의 개발은 중요한 연구 분야 가운데 하나이다. 그러나 이전의 대부분의 설진 시스템은 한의사의 간섭을 배제한 자동 진단을 위한 전문가 시스템으로서 진료를 위한 객관화된 진단 지표의 생성에 있어서 어려움이 있었다. 따라서 본 논문에서는 한방 설진에 있어서 한의사의 진료 행위에 의해서 최적화된 설진을 위한 진단 지표를 계산하는 컴퓨터 지원 진단 소프트웨어를 제안한다. 개발한 소프트웨어는 반자동 방식으로 설질 추출을 위해서는 한의사의 매뉴얼 방식을 이용하고, 설태 영역을 자동 분할하여 비설태와 설태의 색상, WTCI 등에 대한 수치적 진단 지표를 한의사에게 실시간으로 제공한다. 또한, 설태 비율을 이용하여 소태, 박태, 후태의 분류 확률 추정 값과 진료 편의를 위한 전자의무기록 차트 기능도 제공한다. 구현된 컴퓨터 지원 진단 소프트웨어의 유효성 평가를 위해서는 60명의 피실험자를 대상으로 혀 영상을 구축하고, 설진 소프트웨어를 실험한 결과 피실험자의 95%가 소프트웨어 사용-유효성을 나타냈다.