• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.10 no.6
• /
• pp.1153-1158
• /
• 2006

The classification of the background and cell areas is very important research area because of the ambiguous boundary. In this paper, the region of cell is extracted from an image of uterine cervical cytodiagnosis using the region growing method that increases the region of interest based on similarity between pixels. Segmented image from background and cell areas is binarized using a threshold value. And then 8-directional tracking algorithm for contour lines is applied to extract the cell area. First, the extracted nucleus is transformed to RGB color that is the original image. Second, the K-means clustering algorithm is employed to classify RGB pixels to the R, G, and B channels, respectively. Third, the Hue information of nucleus is extracted from the HSI models that is the transformation of the clustering values in R, G, and B channels. The backpropagation algorithm is employed to classify and identify the normal or abnormal nucleus.

• The Korean Journal of Cytopathology
• /
• v.9 no.2
• /
• pp.139-146
• /
• 1998

The AutoPap 300 QC System is an automated device for the analysis and classification of conventional cervical cytology slides for quality control purpose. These studies evaluated the sensitivity of the AutoPap 300 QC System, and estimated morphologic features other than epithelial abnormality to identify a high quality control(QC) score with the AutoPap 300 QC System. The sensitivity of the AutoPap 300 QC System at 10% review rate for 210 cases of cervicovaginal cytology with low grade squamous intraepithelial lesion(LSIL) and higher grade lesion was assessed, and compared with a 10% random rescreening. The morphologic features, such as presence of endocervical component, dirty background, atrophy, abnormal ceil size, and celluiarity of single atypical cells were estimated in 45 cases of no review and 30 cases of QC review cases. The AutoPap 300 QC System identified 119(56.7%) out of 210 cases with LSIL and higher grade lesion at 10% review rate. It was more sensitive to squamous cell lesions$(50{\sim}62%)$ than to glandular lesions(10%). The dirty background and the scanty cellularity of single atypical cells were significantly related to low QC score. Conclusively, AutoPap 300 QC System is superior to human random rescreen for the identification of false negative smears. The upgrading of this device is required to enhance the defection of glandular lesion and certain Inadequate conditions of the slides.

• The Korean Journal of Cytopathology
• /
• v.11 no.1
• /
• pp.47-52
• /
• 2000

Diffuse sclerosing papillary carcinoma(DSPC), a variant of papillary carcinoma of the thyroid, is characterized by diffuse involvement of one or both thyroid lobes, and histologic features such as prominent sclerosis, intense lymphocytic infiltrate, numerous psammoma bodies, and squamous metaplasia together with the characteristic cytoarchitectural pattern of classical papillary carcinoma. We experienced a case of fine needle aspiration cytologic(FNAC) findings of DSPC, which was confirmed by histologic examination of the thyroidectomy specimens. The patient was 26 years old female who presented with diffuse firm enlargement of the thyroid gland with enlargement of many cervical lymph nodes. FNAC smears showed numerous psammoma bodies, many lymphocytes, metaplastic squamous cells, absence of stringy colloid, and epithelial cells showing classical features of papillary carcinoma, such as nuclear grooves, intranuclear unclusions, and ground glass chromatin pattern.

• The Korean Journal of Cytopathology
• /
• v.4 no.2
• /
• pp.127-132
• /
• 1993

Ki-1 lymphoma is a sort of high grade large cell lymphoma and defined on the basis of the reactivity of the tumor cells with monoclonal antibody Ki-1. On fine needle aspiration cytology, the reported case is rare and the differential diagnosis is not easy, especially from undifferentiated carcinoma and Hodgkin's lymphoma. We experienced a case of fine needle aspiration cytology of Ki-1 positive large cell lymphoma in a 61-year old male patient. Fine needle aspiration cytology from the cervical lymph node disclosed hypercellular smears with large single cells on polymorphous lymphoid background. The tumor cells had abundant dense cytoplasm and large nuclei with Irregular profiles. Although most cells were mononuclear binucleated and multilobed/multinucleated cells were also seen Immunohistochemistry was done and revealed strong positive staining for Ki-1 antigen.

• The Korean Journal of Cytopathology
• /
• v.6 no.2
• /
• pp.209-213
• /
• 1995

Primary malignant melanoma of vagina is a rare tumor which is easily misinterpretated in routine cytologic examination. We lately experienced a case of primary malignant melanoma of the vagina with direct cervical extension diagnosed by Pap smear. The cervicovaginal smear showed variable sized clusters of epithelial cells or singly scattered abnormal epithelial cells. Most of the tumor cells had round hyperchromatic nuclei with prominent nucleoli and brownish pigments in cytoplasm. The cytologic findings are compared with histologic features of resected specimen.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2007.06a
• /
• pp.241-247
• /
• 2007

자궁 경부 세포진 영상의 핵 추출을 위해서는 영상의 배경과 핵 그리고 세포질 영역의 구분이 중요하다. 또한 정상 세포핵과 암종 세포핵의 구분 및 인식을 위해서는 세포핵들의 형태학적 특징을 이용한 분류 기준을 세워야한다. 본 논문에서는 자궁 경부 세포진 영상에서 세포핵의 후보 영역과 핵을 추출하기 위해 현미경 400배율 확대 사진을 획득하는 과정에서 훼손된 컬러 영상을 복원하기 위한 방법으로 Lighting Compensation을 적용하여 영상을 보정한다. 그리고 배경 영역과 세포핵 영역을 구분하기 위해 영상의 R,G,B 영역의 히스토그램의 분포를 이용하여 배경을 제거한다. 배경이 제거된 영상을 그레이 영상으로 변환 한 후, 히스토그램 명암도의 값을 이용하여 세포핵 영역과 세포질을 분류하여 세포핵 영역을 추출한다. 그리고 Kapur 방법을 적용하여 세포핵 영역의 엔트로피 누적확률을 구한 후, 영상을 이진화 한다. Kapur 방법이 적용된 이진화 영상에서 세포핵 영역의 중심과 주위 화소를 비교하는 $3\times3$ 마스크를 적용하여 영상의 미세한 잡음을 제거 한 후, 8방향 윤곽선 추적 알고리즘을 적용하여 최종적으로 세포핵 영역을 추출한다. 추출된 세포핵의 영역을 분류 및 인식하는 과정으로 세포의 외각의 방향성 정보, 핵의 크기, 그리고 면적 비율의 특징을 이용하여 퍼지 소속 함수를 설계한 후, 소속 함수의 소속도를 구하고 퍼지 추론 규칙을 적용하여 자궁 경부 세포진 영상에서 정상 세포핵 및 암종 세포핵을 인식한다.

• The Korean Journal of Cytopathology
• /
• v.5 no.2
• /
• pp.113-119
• /
• 1994

Thirty cases of Kikuchi's lymphadenitis, diagnosed by fine needle aspiration cytology, were reviewed to determine the main cytologic features helpful in reaching a diagnosis. The patients(mean age 26.6 years, male: female = 1:3.8) presented with lymphadenopathy (cervical 24, submandibular 3, and axillary 1) with or without fever and local tenderness. Excisional biopsy was done for confirmation in 5 cases and the remaining 25 cases showed the similar cytologic and clinical features. In the aspiration smears of all cases, there was a heterogenous celluar mixture including frequent extracellular karyorrhectic nuclear debris, phagocytic histiocytes, plasmacytoid monocytes, and a variable number of polymorphous lymphocytes such as immunoblasts, activated large lymphocytes, and small mature lymphocytes. The characteristic cytologic features of Kikuchi's lymphadenitis were the following: (1) frequent extracelluar karyorrhectic nuclear debris in the background : (2) phagocytic histiocytes with eccentrically placed crescentic nuclei and abundant pale cytoplasm containing phagocytized karyorrhectic debris : (3) plasmacytoid monocytes, which were medium-sized cells with eccentrically placed round nuclei and amphophilic cytoplasm : (4) no neutrophilic background.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2006.05a
• /
• pp.335-339
• /
• 2006

자궁 경부 세포진 영상의 핵 영역 분할은 자궁 경부암 자동화 검색 시스템의 가장 어렵고도 중요한 분야로 알려져 있다. 자궁 경부 세포진 영상은 배경과 세포의 영역이 확실히 구분되지 않는 경우가 많기 때문에 이들을 확실히 구분하는 것이 매우 중요하다. 본 논문에서는 이러한 문제점을 해결하기 위해 자궁 경부 세포진 영상에서 Region growing 기법을 적용하여 세포 영상을 분할한다. Region growing 기법은 화소간의 유사도를 측정하여 영역을 확장하여 분할하는 방법이다. 세포와 배경이 분할된 영상을 일정 임계값을 이용하여 영상을 이진화 한 후, 8방향 윤곽선 추적 알고리즘을 이용해 세포 영역을 추출한다. 추출된 세포 영역을 원 영상인 RGB 컬러로 변환한 후에 K-means 알고리즘을 적용하여 각 세포 영역의 RGB 화소를 R, G, B 채널로 각각 분리하여 클러스터링한다. 클러스터링된 각각의 R, G, B 채널의 클러스터 값을 이용하여 HSI 모델로 변환시킨 후에 세포핵 영역의 Hue 정보를 추출한다. 추출된 세포핵의 특징을 오류 역전파 알고리즘을 적용하여 정상 세포와 비정상 세포를 분류하고 인식한다.

• Asian Pacific Journal of Cancer Prevention
• /
• v.13 no.4
• /
• pp.1151-1158
• /
• 2012

High-risk human papillomavirus (HPV) genotypes are the major cause of cervical cancer. Hence, HPV genotype detection is a helpful preventive measure to combat cervical cancer. Recently, several HPV detection methods have been developed, each with different sensitivities and specificities. The objective of this study was to compare HPV high risk genotype detection by an electrochemical DNA chip system, a line probe assay (INNO-LiPA) and sequencing of the L1, E1 regions. A total of 361 cervical smears with different cytological findings were subjected to polymerase chain reaction-sequencing and electrochemical DNA chip assessment. Multiple infections were found in 21.9% (79/361) of the specimens, most prevalently in 20-29-year olds while the highest prevalence of HPV infection was found in the 30-39-year age group. The most prevalent genotype was HPV 16 at 28.2% (138/489) followed by HPV 52 at 9.6% (47/489), with the other types occurring at less than 9.0%. The electrochemical DNA chip results were compared with INNO-LiPA and sequencing (E1 and L1 regions) based on random selection of 273 specimens. The results obtained by the three methods were in agreement except for three cases. Direct sequencing detected only one predominant genotype including low risk HPV genotypes. INNO-LiPA identified multiple infections with various specific genotypes including some unclassified-risk genotypes. The electrochemical DNA chip was highly accurate, suitable for detection of single and multiple infections, allowed rapid detection, was less time-consuming and was easier to perform when compared with the other methods. It is concluded that for clinical and epidemiological studies, all genotyping methods are perfectly suitable and provide comparable results.

• The Korean Journal of Cytopathology
• /
• v.9 no.1
• /
• pp.37-44
• /
• 1998

OBJECTIVE: False negatives of cervical smears due to screening errors pose a significant and persistent problem. AutoPap 300 QC System, an automated screening device, is designed to rescreen conventionally prepared Pap smears initially screened by cytotechnologists as normal. Clinical experience and sensitivity of the AutoPap 300 QC System were assessed and compared with current 10% random qualify control technique. MATERIALS AND METHODS: In clinical practice, a total of 18,592 "within normal limits" or "benign cellular changes" cases classified by The Bethesda System were rescreened by the Autopap System. In study for sensitivity of The AutoPap System to detect false negatives, a total of 1,680 "within normal limits" or "benign cellular changes" cases were rescreened both manually and by the AutoPap System. The sensitivity of the AutoPap System to these false negatives was assessed at 10% review rate to compare 10% random manual rescreen. RESULTS: In clinical practice, 38 false negatives were identified by the AutoPap System and we had achieved 0.2% reduction in the false negative rate of screening error. In study for sensitivity, 37 false negatives were identified by manual rescreening, and 23 cases(62.2%) of the abnormal squamous cytology were detected by the AutoPap System at 10% review rate. CONCLUSONS: The AutoPap 300 QC System is a sensitive automated rescreening device that can detect potential false negatives prior to reporting and can reduce false negative rates in the laboratory. The device is confirmed to be about eight times superior to the 10% random rescreen in detecting false negatives.