백태 중 후태 및 박태 분류 판별함수 설계

최은지(Choi Eun-Ji),김근호(Kim Keun Ho),유현희(Ryu Hyun-Hee),이혜정(Lee Hae-Jung),김종열(Kim Jong-Yeol) 한국한의학연구원 2007 한국한의학연구원논문집 Vol.13 No.3

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.

딥러닝을 이용한 WTCI 설태량 평가를 위한 유효성 검증

이우범 한국융합신호처리학회 2019 융합신호처리학회 논문지 (JISPS) Vol.20 No.4

A WTCI is an important criteria for evaluating an mount of patient’s tongue coating in tongue diagnosis. However, Previous WTCI tongue coating evaluation methods is a most of quantitatively measuring ration of the extracted tongue coating region and tongue body region, which has a non-objective measurement problem occurring by exposure conditions of tongue image or the recognition performance of tongue coating. Therefore, a WTCI based on deep learning is proposed for classifying an amount of tonger coating in this paper. This is applying the AI deep learning method using big data. to WTCI for evaluating an amount of tonger coating. In order to verify the effectiveness performance of the deep learning in tongue coating evaluating method, we classify the 3 types class(no coating, some coating, intense coating) of an amount of tongue coating by using CNN model. As a results by testing a building the tongue coating sample images for learning and verification of CNN model, proposed method is showed 96.7% with respect to the accuracy of classifying an amount of tongue coating. 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.

설태의 형광특성 - 설태 형광현상의 발현기전 소개 및 제안 -

김지혜 ( Ji-hye Kim ),남동현 ( Dong-hyun Nam ) 대한한의진단학회 2011 大韓韓醫診斷學會誌 Vol.15 No.1

In traditional Korean medicine, inspection of the tongue is an important method of making medical diagnoses and determining prognosis. We surveyed the fluorescence characteristics of the tongue coat in the ultraviolet light. The tongue coat comprises micro-organisms, blood metabolites, leukocytes from periodontal pockets, large amounts of desquamated epithelial cells released from the oral mucosa and different nutrients. In the ultraviolet light tissues of the oral cavity generally emit weak red or green fluorescence, which is not easily seen by the human eye, but is readily detected. This fluorescence has been proved to be due to the production of porphyrins by oral micro-organisms. While the composition of motile micro-organisms on the dorsum of the tongue is not constant, variations also occur persistingly in the fluorescence characteristics of the tongue coat. But because live bacteria contain a variety of intracellular biomolecules that have specific excitation and emission wavelength spectra characterizing their intrinsic fluorescence, the tongue coat emits fluorescence. the tongue itself, on the other hand, emits very weak or not fluorescence. In conclusion, we suggests that the uncoated tongue area be eliminated from the coated tongue area with the difference between the fluorescence characteristics of the tongue and that of the tongue coat.

설태의 자외선 형광 반응을 이용한 설태 영역 추출

최창열,이우범,홍유식,이상석,남동현 한국인터넷방송통신학회 2012 한국인터넷방송통신학회 논문지 Vol.12 No.4

본 논문에서는 한방 의료의 설진에서 진단 지표로 활용될 수 있는 효과적인 설태 영역 추출 방법을 제안한다. 제안한 방법은 설태의 자외선 광원에 의한 형광 반응 특성을 이용하여 기존의 설태 추출 방법의 단점으로 지적되었던 진료 환경의 제약성 및 진료 결과의 객관성 부족에 대한 문제점을 해결할 수 있다. 처리 과정으로는 자외선 광원을 사용하여 설진 영상을 획득하고, 설질(Tongue body)과 설태(Tongue coating) 영역의 색차 크기에 상응하는 히스토그램(Histogram) 상의 골-포인트(Valley-points)를 임계 처리하여 이진화(Binarization)를 수행한다. 최종적으로 설진을 위하여 한의사에게 제공되는 진단 영상은 이진 영상에 케니-에지(Canny-Edge) 알고리즘을 사용하여 설태 윤곽 정보를 추출한 후에 환자의 원 혀 영상에 부과하여 제시한다. 제안한 방법의 성능 평가를 위해서는 다양한 혀 영상을 수집하고, 한의사가 수작업으로 설정한 설태 영역을 참영상(True image)으로 하여 제안한 방법으로 추출한 설태 영역과 비교하였다. 그 결과 제안한 방법은 87.87%의 추출률을 나타냈으며, 추출된 설태 영역의 형태 유사도도 높게 나타났다. An effective extraction method for extracting a coated tongue is proposed in this paper, which is used as the diagnostic criteria in the tongue diagnosis. Proposed method uses the fluorescence response characteristics of the coated tongue that is occurred by using the ultraviolet light. Specially, this method can solved the previous problems including the issue in the limits of the diagnosis environment and in the objectivity of the diagnosis results. In our method, original tongue image is acquired by using the ultraviolet light, and binarization is performed by thresholding a valley-points in the histogram that corresponds to the color difference of tongue body and tongue coating. Final view image is presented to the oriental doctor, after applying the canny-edge algorithm to the binary image, and edge image is added to the original image. In order to evaluate the performance of the our proposed method, after building a various tongue image, we compared the true region of coated tongue by the oriental doctor’s hand with the extracted region by the our method. As a result, the proposed method showed the average 87.87% extraction ratio. The shape of the extracted coated tongue region showed also significantly higher similarity.

설진(舌診)의 임상활용에 관한 연구

김빛나라 ( Bin Na Ra Kim ),오민석 ( Min Seok Oh ) 한방재활의학과학회 2013 한방재활의학과학회지 Vol.23 No.3

ObjectivesThis study was designed to: (1) investigate the clinical feature of tongue diagnosis, (2) make an observation of significant changes in tongue diagnosis according to the patient`s physical condition and laboratory result and (3) identify clinical efficacy of tongue diagnosis. Methods300 patients` tongue diagnosis results were analyzed and the patients were divided to each group according to the physical condition and laboratory result. Then, chi-square test was performed to assess statistical significance between tongue diagnosis results of each group. ResultsAs a result of analyzing the spread of tongue diagnosis according to the patient`s physical condition and laboratory result, 18 groups had statistical significance related to specific tongue color and tongue coating. ConclusionsEven if there would be possible misinterpretations in one-to-one match between the tongue diagnosis and certain diseases, we identified that tongue diagnosis results were changed somewhat related to patient`s physical condition with some tendency and tongue diagnosis could be used for meaningful clinical diagnostic tool. (J Korean Med Rehab 2013;23(3):149-157)

기능성소화불량 환자에서 변증유형과 설 지표의 상관성 연구

이하늘,정해인,이현진,조윤재,금창열,한아람,하나연,김진성 대한한방내과학회 2021 大韓韓方內科學會誌 Vol.42 No.6

Objectives: The aim of this study was to analyze the correlation between patterns determined by pattern identification of functional dyspepsia (FD) and tongue features, including tongue coating and tooth marks, in FD patients. Methods: We reviewed the clinical records of 68 FD patients who visited the Department of Digestive Diseases of Kyung Hee University Korean Medicine Hospital from September 1, 2020 to August 31, 2021. The subjects were evaluated with a computerized tongue image acquisition system (CTIS) and by pattern identification of FD. Measurement included the percentage of tongue coating, tooth mark levels, and pattern scores. Results: Statistically significant negative correlations were noted between the scores of the pattern of ‘spleen and stomach deficiency and cold' (SSDC) and the percentage of tongue coating in whole, center, and root of the tongue body. However, no other patterns were correlated with any parameter measured by CTIS. No significant difference was noted in the percentage of tongue coating and the tooth mark level between the patterns. Conclusions: This study demonstrated that the pattern of SSDC was significantly associated with the percentage of tongue coating. We suggest that the percentage of tongue coating could be a useful indicator for identifying the degree of patterning of SSDC in patients with FD.

Clinical assessment of oral malodor using autofluorescence of tongue coating

Lee, Eun-Song,Yim, Hyun-Kyung,Lee, Hyung-Suk,Choi, Jong-Hoon,Lee, Ji Hyun,Kim, Baek-Il Elsevier 2016 PHOTODIAGNOSIS AND PHOTODYNAMIC THERAPY Vol.13 No.-

<P><B>Abstract</B></P> <P><B>Objectives</B></P> <P>The aim of this study was to evaluate whether a new method using quantitative light-induced fluorescence-digital (QLF-D) was appropriate for the diagnosis of oral malodor by quantifying the fluorescence of tongue coating.</P> <P><B>Methods</B></P> <P>This study examined 103 healthy subjects who have an oral malodor as a main complaint. The levels of oral malodor were measured by organoleptic scores (OLS) and volatile sulfur compound (VSC) levels. The fluorescent tongue coating images captured by QLF-D were quantified as the integrated fluorescence score (IF score) by multiplying the intensity and area of fluorescence. The correlations between the fluorescence parameters and OLS as well as VSC levels and the diagnostic accuracy of the IF score were evaluated.</P> <P><B>Results</B></P> <P>The IF score of tongue coating showed a significant positive correlation with the OLS (<I>r</I> =0.54, <I>p</I> <0.01) and the VSC levels (<I>r</I> =0.49, <I>p</I> <0.01). This score was significantly differed with the level of oral malodor (<I>p</I> <0.001), and its AUC was 0.72 in identifying the patient with definite oral malodor (≥OLS 2).</P> <P><B>Conclusions</B></P> <P>A new method quantifying tongue coating fluorescence detected by QLF-D can be used to diagnose oral malodor and assess its severity in the clinical practice.</P> <P><B>Highlights</B></P> <P> <UL> <LI> QLF-D can visualize and detect tongue coating as red fluorescence. </LI> <LI> Tongue fluorescence detected by QLF-D is correlated to the severity of oral malodor. </LI> <LI> IF score can be used to evaluate oral malodor by quantifying tongue coating fluorescence. </LI> </UL> </P>

Exploring the oral microflora of preschool children

Wen Ren,Qun Zhang,Xuenan Liu,Shuguo Zheng,Lili Ma,Feng Chen,Tao Xu,Baohua Xu 한국미생물학회 2017 The journal of microbiology Vol.55 No.7

The oral cavity is one of the most important and complicated habitats in our body and supports diverse microbial communities. In this study, we aimed to determine the bacterial diversity and composition of various oral micro-niches. Samples were collected from supragingival plaque, saliva, and tongue coating from 10 preschool children (30 samples total). 16S rRNA gene pyrosequencing dataset generated 314,639 clean reads with an average of 10,488 ± 2,787 reads per sample. The phyla Firmicutes, Proteobacteria, Actinobacteria, Bacteroidetes, and Fusobacteria were predominant, accounting for more than 90% of the total sequences. We found the highest α diversity, microbial richness, and evenness in plaque, compared with saliva and tongue coating. Plaque was also distinguished from saliva and tongue coating by phylogenetic distances (weighted UniFrac). Taxa with different relative abundances were further identified, confirming the existence of microbial differences across the three niches. Core microbiomes were defined of each niche; however, only a small proportion of operational taxonomic units (8.07%) were shared by the three niches. Coaggregation between Actinomyces spp. and Streptococcus spp. and other correlations among periodontal pathogens, such as Prevotella, Fusobacteria, Capnocytophaga, and Tannerella, were shown by a co-occurrence network. In summary, our study provides a framework of oral microbial communities in the population of preschool children as a baseline for further studies of oral diseases related to microbes.

다차원 컬러벡터 기반 백태 및 황태 분류 판별함수 설계

이전(Lee Jeon),최은지(Choi Eun-Ji),유현희(Ryu Hyun-Hee),이혜정(Lee Hae-Jung),이유정(Lee Yu-jung),박경모(Park Kyung-Mo),김종열(Kim Jong-Yeol) 한국한의학연구원 2007 한국한의학연구원논문집 Vol.13 No.2

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 I-I 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.

RGB 컬러모델에서 자외선 조명하 박락태(剝落苔)의 설태와 설질 사이의 색 강도 차이에 관한 연구

남동현 ( Dong-hyun Nam ),김지혜 ( Ji-hye Kim ),이우범 ( Woo-beom Lee ),이상석 ( Sang-suk Lee ),홍유식 ( You-sik Hong ) 대한한의진단학회 2011 大韓韓醫診斷學會誌 Vol.15 No.2

Objectives The objective of this study is to compare the colour intensity of tongue body and that of tongue coat under the visible light and the ultraviolet light. Methods We selected 7 subjects with completely or partially peeled tongue coat among the recruited 94 adults for the experiment. We took each tongue picture under the visible light and the ultraviolet light (315-400 nm) and then extracted sample images from the tongue body and tongue coat regions. Mean, median and mode of colour intensity from the sample images were calculated in 256 RGB system. Results The green and the blue colour intensities of the tongue coats were significantly higher than those of the tongue bodies under the visible light. In all channels, the red, green and blue, the colour intensities of the tongue coats were significantly higher than those of the tongue bodies under the ultraviolet light. The colour differences between tongue coats and tongue bodies under the ultraviolet light were significantly higher than the colour differences under the visible light. Especially the colour difference under the ultraviolet light was highest in the green channel. Conclusions We suggested that green colour image of the RGB system taken under the ultraviolet light could be used for more easy separating tongue coat region from tongue body.