• 한국한의학연구원논문집
• /
• 제14권3호
• /
• pp.89-95
• /
• 2008

A tongue shows physiological and clinicopathological changes of inner organs. Visual inspection of a tongue is not only convenient but also non-invasive. To develop an automat ic tongue diagnosis system for an objective and standardized diagnosis, the separation of the tongue are a from a facial image and the detection of coatings, spots and cracks are inevitable but difficult since the colors of a tongue, lips, and skin in a mouth as well as those of tongue furs and body are similar. The propose d method includes preprocessing with down-sampling and edge enhancement, over-segmentation, detecting positions with a local minimum over shading from the structure of a tongue, and correcting local minima or detecting edge with color difference. The proposed method produces the region of a segmented tongue, and then decomposes the color components of the region into hue, saturation and brightness, resulting in classifying the regions of tongue furs(coatings) into kinds of coatings and substance and segmenting them. Spots are detected by using local maxima and the variation of saturation, and cracks are searched by using local minima and the directivity of dark areas in brightness. The results illustrate the segmented region with effective information, excluding a non-tongue region and also give us accurate discrimination of coatings and the precise detection of spots and cracks. It can be used to make an objective and standardized diagnosis for an u-Healthcare system as well as a home care system.

• 대한의용생체공학회:의공학회지
• /
• 제42권5호
• /
• pp.201-210
• /
• 2021

In Korean medicine, tongue diagnosis is one of the important diagnostic methods for diagnosing abnormalities in the body. Representative features that are used in the tongue diagnosis include color, shape, texture, cracks, and tooth marks. When diagnosing a patient through these features, the diagnosis criteria may be different for each oriental medical doctor, and even the same person may have different diagnosis results depending on time and work environment. In order to overcome this problem, recent studies to automate and standardize tongue diagnosis using machine learning are continuing and the basic process of such a machine learning-based tongue diagnosis system is tongue segmentation. In this paper, image data is augmented based on the main tongue features, and backbones of various famous deep learning architecture models are used for automatic tongue segmentation. The experimental results show that the proposed augmentation technique improves the accuracy of tongue segmentation, and that automatic tongue segmentation can be performed with a high accuracy of 99.12%.

• 동의생리병리학회지
• /
• 제19권5호
• /
• pp.1437-1442
• /
• 2005

Tongue Diagnosis is the important traditional oriental medical diagnosis method that observes not only the general physiological state but also some kinds of disease. However, manual tongue diagnosis is much influenced by surrounding illumination. Therefore, Digital Tongue Inspection System(DigiTis) is needed for the quantification of objective tongue information, In this research, Tongue images of 98 malignant Neoplasm patients and 34 normal persons were collected by Digital Tongue Inspection System. Statistical analysis of tongue images and patient data indicates that cancer group has more blue-purple components in tongue body(舌質) and yellow components in tongue coating than normal group. Also, there are a lot of rose-pink components in the cancer group of second stage and blue-purple components in the cancer group of third or fourth stage. Our study shows that tongue image is a useful index for distinction between disease and health. Furthermore we need more extended research through the additional sampling and various disease.

• 전자공학회논문지SC
• /
• 제45권6호
• /
• pp.123-131
• /
• 2008

한의학에서 혀의 상태는 인체 내부의 생리적 병리적 변화와 같은 건강 상태를 진단하는 중요한 지표로 활용된다. 혀의 상태를 진단하는 방법(설진)은 편리할 뿐 아니라 비침습적이므로, 한의학에서 널리 활용되고 있다. 하지만, 설진은 광원이나 환자의 자세, 의사의 건강 조건과 같은 검사 환경에 따라 많은 영향을 받는다. 객관적이고 표준화된 진단을 위한 자동 설진 시스템을 개발하기 위하여 촬영된 얼굴 영상으로부터 혀를 영역분할하고 설태를 분류하는 것은 필수적이지만 혀와 입술, 입 근처의 피부색이 서로 유사하므로 쉽지 않은 일이다. 제안된 방법은 전처리 과정과 영역분할, 혀의 구조로부터 발생하는 음영 영역의 지역 최소값 위치 검색, 지역 최소값의 교정, 컬러의 차이를 최대로 하는 위치를 찾는 컬러 경계면 탐색, 척의 기하적인 특성에 일치하는 경계면 선택, 경계면 평활화로 구성되어 있으며, 여기서 전처리 과정은 계산량의 감소를 위한 부 표본화, 히스토그램 평활화, 경계면 강화를 수행한다. 이러한 시스템적인 과정을 거치면, 영역분할된 혀를 획득할 수 있게 된다. 제안된 방법으로 분할된 영역은 초과적으로 혀가 아닌 영역을 제외해 낼 뿐 아니라 정확한 진단을 위해 중요한 정보를 제공함을 한의사의 진단 유효도 평가점수를 통해 확인할 수 있었다. 제안된 방법은 진단의 객관화와 표준화에 기여할 뿐만 아니라 u-Healthcare 시스템에도 활용 가능하다.

• 전기학회논문지
• /
• 제56권11호
• /
• pp.2051-2057
• /
• 2007

In Oriental medicine, the status of a tongue is the important indicator to diagnose one's health like physiological and clinicopathological changes of inner parts of the body. The method of tongue diagnosis is not only convenient but also non-invasive and widely used in Oriental medicine. However, tongue diagnosis is affected by examination circumstances a lot like a light source, patient's posture and doctor's condition. To develop an automatic tongue diagnosis system for an objective and standardized diagnosis, segmenting a tongue is inevitable but difficult since the colors of a tongue, lips and skin in a mouth are similar. The proposed method includes preprocessing, graph-based over-segmentation, detecting positions with a local minimum over shading, detecting edge with color difference and estimating edge geometry from the probable structure of a tongue, where preprocessing performs down-sampling to reduce computation time, histogram equalization and edge enhancement. A tongue was segmented from a face image with a tongue from a digital tongue diagnosis system by the proposed method. According to three oriental medical doctors' evaluation, it produced the segmented region to include effective information and exclude a non-tongue region. It can be used to make an objective and standardized diagnosis.

• 한국정보전자통신기술학회논문지
• /
• 제13권5호
• /
• pp.313-322
• /
• 2020

많은 양의 데이터는 딥 러닝 모델의 견고성을 향상시키고 과적합 문제를 방지할 수 있게 해준다. 자동 혀 분할에서, 혀 영상 데이터 세트를 실제로 수집하고 라벨링하는 데에는 많은 어려움이 수반되므로 많은 양의 혀 영상 데이터를 사용하기 쉽지 않다. 데이터 증강은 새로운 데이터를 수집하지 않고 레이블 보존 변환을 사용하여 학습 데이터 세트를 확장하고 학습 데이터의 다양성을 증가시킬 수 있다. 이 논문에서는 이미지 자르기, 회전, 뒤집기, 색상 변환과 같은 7 가지 데이터 증강 방법을 사용하여 확장된 혀 영상 학습 데이터 세트를 생성하였다. 데이터 증강 방법의 성능을 확인하기 위하여 InceptionV3, EfficientNet, ResNet, DenseNet 등과 같은 전이 학습 모델을 사용하였다. 실험 결과 데이터 증강 방법을 적용함으로써 혀 분할의 정확도를 5~20% 향상시켰으며 기하학적 변환이 색상 변환보다 더 많은 성능 향상을 가져올 수 있음을 보여주었다. 또한 기하학적 변환 및 색상 변환을 임의로 선형 조합한 방법이 다른 데이터 증강 방법보다 우수한 분할 성능을 제공하여 InveptionV3 모델을 사용한 경우에 94.98 %의 정확도를 보였다.

• 동의생리병리학회지
• /
• 제22권1호
• /
• pp.262-266
• /
• 2008

We plan to make the standardization of the pattern identifications for stroke and differentiate them by tongue diagnosis. We make a case report form which has questionnaires for tongue diagnosis in stroke patients. And we collected cases from the multi center network which consists of twelve university hospitals and one local hospital. The cases confirmed by diagnosis of medical specialists and residents are 321 cases. They are divided into Qi Defficiency 30.84%, Dampness& Phlegm 25.55%, Fire & Heat 22.43%, Eum Defficiency 18.69% and Blood Stasis 2.49%. We analyzed the markers which classified into the color of tongue body, the color of fur, the quality of fur, the dryness of tongue, the shape of tongue. To make a stroke pattern identification standard, we must try variable ways.

• 전자공학회논문지
• /
• 제51권11호
• /
• pp.221-228
• /
• 2014

혀의 색상 및 형태는 신체의 생리적이고 임상 병리적인 상태를 반영한다. 최근에는 정량적이고 객관화된 설 진단을 위해 다양한 설 영상 측정 장치가 개발되고 있다. 설 진단의 대부분은 혀의 색상 정보를 활용하기 때문에 설 영상 획득 장치에서 조명환경의 성능은 매우 중요하다. 본 연구에서는 좁은 시스템 내부 구조에서 설 표면에 조명이 고르게 비춰질 수 있도록 간접조명을 고안하였고, 그 성능을 평가하였다. 간접 조명환경 구현을 위해 타원체 형태의 반사 구조를 시스템 내부에 위치시키고, 타원체 내부에 높은 조도의 LED 두 개를 통해 정면 카메라 아래 방향으로 빛을 조사하도록 배치시켰다. 혀 위치 영역에는 반사 구조에 의해 반사된 빛만이 조사될 수 있도록 하였다. 조명의 균질도는 5개 영역에서 밝기를 측정하여 변동계수로 평가하였고, 직접조명과 확산판조명에서 각각 0.16, 0.13으로 나타난 반면 간접조명에서는 0.01미만으로 나타났다. 혀 모형을 통해 조명에 의한 빛 반사 영역의 비율을 계산한 결과는 직접조명, 확산판조명, 간접조명에서 각각 5.76%, 4.22%, 1.79%로 나타났다. 혀 모형을 측정한 영상에서 6영역의 변동계수를 계산해 색상 균질도를 평가한 결과는 간접조명에서 0.06 미만으로 가장 우수한 것으로 나타났다. 본 논문에서 구현한 조명방식을 설진 시스템에 적용하여 진단 지표 측정의 재현성 및 반복성이 향상될 것으로 기대된다.

• 대한한의학회지
• /
• 제20권2호
• /
• pp.187-197
• /
• 1999

To assess the usefulness of tongue inspection for evaluating the Pattern identification in oriental medicine, we observed stroke patient's tongue and tongue coat and compared it with Pattern identification. The test group was composed of 85 acute stroke stage patients(within 72 hours of onset). Subjects were randomly selected from stroke patients admitted in the KyungHee University, Hospital of Oriental Medicine from December 1 1998 to June 30 1999. We took pictures of patient's tongue and tongue coat within 72hours from onset and checked Pattern identification at the same time. Tongues colored pale rose or red greatly outnumbered other colors. Tongue shape tended to be prickly or fissured, and tongue condition tended to be unflexible or deviated. Regarding tongue coat color, there were great amounts of yellow or clark yellow tongue coats, which were moist, thick or greasy in substance. The red tongue was significantly related to Fire-heat and deficiency of Yin syndrome, while faint white tongue to Damp syndrome(P=0.006). In terms of tongue coat, thin coat was related to Wind and Fire-heat syndromes, thick coat to Damp and Blood stasis syndrome, respectively (P=0.002). In conclusion, we thought that tongue inspection could be a useful Oriental medicine diagnosis in stroke.

• Imaging Science in Dentistry
• /
• 제48권1호
• /
• pp.45-49
• /
• 2018

Purpose: The aim of this study was to evaluate the quantitative strain elastography of tongue carcinoma using intraoral ultrasonography. Materials and Methods: Two patients with squamous cell carcinoma (SCC) who underwent quantitative strain elastography for the diagnosis of tongue lesions using intraoral ultrasonography were included in this prospective study. Strain elastography was performed using a linear 14 MHz transducer (Aplio 300; Canon Medical Systems, Otawara, Japan). Manual light compression and decompression of the tongue by the transducer was performed to achieve optimal and consistent color coding. The variation in tissue strain over time caused by the compression exerted using the probe was displayed as a strain graph. The integrated strain elastography software allowed the operator to place circular regions of interest (ROIs) of various diameters within the elastography window, and automatically displayed quantitative strain (%) for each ROI. Quantitative indices of the strain (%) were measured for normal tissues and lesions in the tongue. Results: The average strain of normal tissue and tongue SCC in a 50-year-old man was 1.468% and 0.000%, respectively. The average strain of normal tissue and tongue SCC in a 59-year-old man was 1.007% and 0.000%, respectively. Conclusion: We investigated the quantitative strain elastography of tongue carcinoma using intraoral ultrasonography. Strain elastography using intraoral ultrasonography is a promising technique for characterizing and differentiating normal tissues and SCC in the tongue.