• 제목/요약/키워드: uterine cervical pap smears

검색결과 15건 처리시간 0.027초

Nucleus Recognition of Uterine Cervical Pap-Smears using FCM Clustering Algorithm

  • Kim, Kwang-Baek
    • Journal of information and communication convergence engineering
    • /
    • 제6권1호
    • /
    • pp.94-99
    • /
    • 2008
  • Segmentation for the region of nucleus in the image of uterine cervical cytodiagnosis is known as the most difficult and important part in the automatic cervical cancer recognition system. In this paper, the region of nucleus is extracted from an image of uterine cervical cytodiagnosis using the HSI model. The characteristics of the nucleus are extracted from the analysis of morphemetric features, densitometric features, colormetric features, and textural features based on the detected region of nucleus area. The classification criterion of a nucleus is defined according to the standard categories of the Bethesda system. The fuzzy C-means clustering algorithm is employed to the extracted nucleus and the results show that the proposed method is efficient in nucleus recognition and uterine cervical Pap-Smears extraction.

자궁 경부진 핵 추출에 관한 연구 (A Study on Nucleus Extraction of Uterine Cervical Pap-Smears)

  • 김광백
    • 한국정보통신학회논문지
    • /
    • 제13권8호
    • /
    • pp.1699-1704
    • /
    • 2009
  • 자궁경부암은 다른 암과 달리 전암(前癌) 단계가 존재하므로 조기 발견할 경우에 생존율이 높다. 그러나 의사나 병리학자가 하루에 검진할 수 있는 양은 제한되어 있다. 따라서 본 논문에서는 세포 도말 검사에 사용되는 자궁 경부진 세포에서 핵을 추출하는 방법을 제안한다. 조기 자궁 경부 세포진 영상에서 핵의 추출은 영상의 배경 그리고 핵과 세포질 영역의 구분이 중요하기 때문에 Lighting Compensation을 적용하여 영상을 보정하고, 명암도의 분포가 가장 작은 B채널에서 $3{\times}3$ 마스크를 이용하여 잡음을 제거한다. 잡음이 제거된 영상을 이진화하고 Grassfire 알고리즘을 적용하여 세포 객체를 추출한다. 추출된 세포 객체 중에서 군집화된 세포 영역에 대해서는 R 채널의 명암도 값을 반복 이진화에 적용하여 핵 영역을 추출한다. 실제 진단 세포학에서 사용하는 자금경부 세포진 400 배율 영상을 대상으로 실험한 결과, 45개의 세포 영역 중에서 40개의 핵이 추출되었다.

개선된 퍼지 ART 알고리즘을 이용한 자궁 경부 세포진 핵 분할 및 인식 (Nucleus Segmentation and Recognition of Uterine Cervical Pap-Smears using Enhanced Fuzzy ART Algorithm)

  • 김광백
    • 한국지능시스템학회논문지
    • /
    • 제16권5호
    • /
    • pp.519-524
    • /
    • 2006
  • 자궁 경부암 세포진 영상의 영역 분할은 슬라이드의 상태나 정상 및 비정상에 따라 많은 차이를 보여 자궁경부암 세포진 인식 시스템의 가장 어렵고도 중요한 분야로 알려져 있다. 본 논문에서는 자궁 경부 세포진 영상에서 퍼지 그레이 모폴로지 연산을 이용하여 핵을 추출하고, 추출된 세포진 핵 영역은 형태학적 정보와 명암 정보, 색상 정보 및 질감 정보를 분석하여 핵의 특징을 추출한다. 또한 Bethesda System에서의 분류 기준에 따라 핵의 분류 기준을 정하고 추출된 핵의 특징들을 개선된 퍼지 ART 알고리즘에 적용하여 실험한 결과, 제안된 방법이 자궁 세포진 핵의 추출과 인식에 있어서 효율적임을 확인하였다.

자궁목세포진에서의 AutoPap Primary Screening System with Location-Guided Screening의 민감도 검사 (Sensitivity of AutoPap Primary Screening System with Location-Guided Screening in Uterine Cervical Cytology)

  • 최종순;장회숙;김희숙;전이경;김혜선;박지영;박인서;홍성란
    • 대한세포병리학회지
    • /
    • 제14권2호
    • /
    • pp.60-65
    • /
    • 2003
  • Objective: The sensitivity of the AutoPap Primary Screening System with Location-Guided Screening (AutoPap LGS) for Identifying atypical cells in cervicovaginal smears was evaluated. Methods: Two hundred forty one slides with atypical cervical cytology randomly sampled were rescreened both manually and by the AutoPap LGS. The AutoPap LGS localized the atypical cells as 15 fields of view(FOVs), which were reexamined by manual review. The sensitivity was also evaluated in accordance with the cellularity of the smears. Results: The AutoPap LGS successfully processed 232 out of 241 slides. The sensitivity of the AutoPap LGS identifying the atypical cells in successfully processed slides was 97.4%(226/232). The false negative rate was 2.6%(6/232). There was no false negative case on high grade squamous intraepithelial lesion (HSIL) or squamous cell carcinoma(SCC) smears in the AutoPap LGS. The FOVs localized the diagnostic-atypical cells in 97.8%(221/226). The number of diagnostic-atypical FOVs was increased in higher-degree of atypical cytology. The AutoPap LGS localized the atypical cells in 100% of adequately cellular smears and in 92.5% even in low cellular smears. Conclusion: The AutoPap LGS showed relatively good sensitivity to detect atypical cells. It can be a valuable system to localize atypical cells, especially in HSIL or cancer slides, even in smears with low cellularity.

Expression of P-glycoprotein is Positively Correlated with p53 in Human Papilloma Virus Induced Squamous Intraepithelial Lesions of Uterine Cervix: Poor Prognosis Association

  • Singh, Madhulika;Singh, Uma;Mathur, Neeraj;Shukla, Yogeshwer
    • Asian Pacific Journal of Cancer Prevention
    • /
    • 제13권12호
    • /
    • pp.6039-6045
    • /
    • 2012
  • This study was conducted to assess the predictive value of p-glycoprotein (p-gp) and p53 immunoexpression in human papillomavirus (HPV) infected cases of cervical dysplasia. Expression of both p-gp and p53 proteins was detected in cervical smears from 177 squamous intraepithelial lesions (SIL) cases along with 183 "atypical squamous cells of unknown significance" (ASCUS) and 150 normal cases. HPV 16 and 18 infection was detected by polymerase chain reaction using type-specific primers for HPV sub-types. There were no significant detectable p53 and p-gp expression in the normal cervix smears (p>0.05). In the ASCUS group 10 cases were positive for both p53 and p-gp immunoreactivity. In cervical dysplasia cases, p53 was positive in 86 (48.58%) while p-gp was positive in 93 (52.54%) and the two markers showed a highly significant correlation (r=0.92, p<0.001). Expression of p53 and p-gp was associated with grade of SIL (p<0.001). A positive correlation between the presence of HPV and expression of proteins p53 and p-gp in smears of patients with cervical lesions was also noted (p<0.001). Thus, p53 and p-gp immunostaining in cervical smears may act as an auxiliary biomarker for detection of HPV-associated cervical lesions. Additionally, a significant positive correlation between ascending grades of SIL and labeling indices of markers suggests that p53 and p-gp can be used as an adjunct to cytomorphological interpretation of conventional cervical Pap smears.

Knowledge, Attitude and Practice of the Pap Smear as a Screening Procedure Among Nurses in a Tertiary Hospital in North Eastern India

  • Thippeveeranna, Chamaraja;Mohan, Surekha Sadhana;Singh, Laiphrakpam Ranjit;Singh, Naorem Nabakishore
    • Asian Pacific Journal of Cancer Prevention
    • /
    • 제14권2호
    • /
    • pp.849-852
    • /
    • 2013
  • Background: Cancer of the uterine cervix is one of the most common cancers among women worldwide. Industrialized countries have dramatically reduced the incidence of mortality from cervical carcinoma in the last 50 years through aggressive screening programs utilizing pelvic examinations and Papanicolaou (Pap) smears but it still remains a major problem in the developing world. Objectives: This study was performed to determine knowledge, attitude and practice of Pap smear as a screening procedure among nurses in a tertiary hospital in north eastern India. Material and Methods: This cross sectional study was carried out with a questionnaire survey covering the socio demographic factors, knowledge, attitude and practices about Pap smear screening among 224 nurses in Regional Institute of Medical Sciences, Imphal, Manipur, India during December 2011. Results: Two hundred and twenty one participants (98.6%) had heard about cervical carcinoma but 18.3% lacked adequate knowledge regarding risk factors. Knowledge about the Pap smear was adequate in 88.8% of the respondents. Out of these, only 11.6% had Pap smear at least once previously. The most common reasons for non-participation in screening were lack of any symptoms (58.4%), lack of counselling (42.8%), physician does not request (29.9%) and fear of vaginal examination (20.5%). Conclusion: Although knowledge of Pap smear as a screening procedure for cervical cancer is high, practice is still low. The nurses who should be responsible for opportunistic screening of women they care for are not keen on getting screened themselves. If we can improve the practice of Pap smear screening in such experts, they should be able to readily provide appropriate and accurate information and motivate the general population to join screening programs.

Kapur 방법과 형태학적 특징을 이용한 자궁경부암 세포 추출 및 인식 (Detection and Recognition of Uterine Cervical Carcinoma Cells in Pap Smear Using Kapur Method and Morphological Features)

  • 김광백
    • 한국정보통신학회논문지
    • /
    • 제11권10호
    • /
    • pp.1992-1998
    • /
    • 2007
  • 자궁 경부 세포진 영상의 효과적인 세포핵 영역 추출과 인식 및 분류를 위해서는 세포진 영상의 배경 그리고 세포핵과 세포질 영역의 정확한 구분이 중요하다. 본 논문에서는 자궁 경부 세포진 영상에서 세포핵 영역과 배경을 효과적으로 분할하기 위 해 Median 필터를 적용하여 전체적인 영상의 명암값을 보정한 후, Gaussian 필터를 적용하여 그레이 영상에서 존재하는 잡음을 제거한다. Kapur 방법을 통해 배경과 세포의 엔트로피 누적 확률을 이용하여 영상을 이진화 한다. 자궁 경부진 영상에서는 군집화된 세포 영 역 이 빈번하게 나타난다. 군집화가 심화된 세포영역에서는 그 영역의 평균 명암도 값을 이용하여 세밀하게 영역을 재분할 한다. 그런 후, 미세잡음을 제거하기 위해 $3{\times}3$ 마스크를 적용하여 미세한 잡음을 제거 한 후, 8 방향 윤곽선 추적 알고리즘을 적용하여 분할된 영역에서 세포들의 후보영역을 추출한다. 추출된 세포영역은 크기, 면적 비율, 핵 외곽의 방향성 정보를 이용하여 정상 세포와 암세포를 인식 및 분류한다. 실험 결과에서는 제안된 방법의 성능이 전문의와 소견과 비교적 근접한 것을 보여준다.

신경 회로망을 이용한 자궁 경부 세포진 영상의 영역 분할에 관한 연구 (A Study on Segmentation of Uterine Cervical Pap-Smears Images Using Neural Networks)

  • 김선아;김백섭
    • 대한의용생체공학회:의공학회지
    • /
    • 제22권3호
    • /
    • pp.231-239
    • /
    • 2001
  • This paper proposes a region segmenting method for the Pap-smear image. The proposed method uses a pixel classifier based on neural network, which consists of four stages : preprocessing, feature extraction, region segmentation and postprocessing. In the preprocessing stage, brightness value is normalized by histogram stretching. In the feature extraction stage, total 36 features are extracted from $3{\times}3$ or $5{\times}5$ window. In the region segmentation stage, each pixel which is associated with 36 features, is classified into 3 groups : nucleus, cytoplasm and background. The backpropagation network is used for classification. In the postprocessing stage, the pixel, which have been rejected by the above classifier, are re-classified by the relaxation algorithm. It has been shown experimentally that the proposed method finds the nucleus region accurately and it can find the cytoplasm region too.

  • PDF

Distribution of Human Papilloma Virus Infections of Uterine Cervix among Women of Reproductive Age - a Cross Sectional Hospital-Based Study from North East India

  • Sarma, Usha;Mahanta, Jagadish;Borkakoty, Biswajyoti;Sarmah, Bidula
    • Asian Pacific Journal of Cancer Prevention
    • /
    • 제16권4호
    • /
    • pp.1519-1523
    • /
    • 2015
  • Infection of the uterine cervix by human papilloma viruses (HPV) may be associated with cervical pre-cancer and invasive cervical carcinoma if left untreated. With advance in molecular techniques, it has become easier to detect the resence of HPV DNA long before the appearance of any lesion. This study concerned cervical scrape samples of 310 married non-pregnant women attending a gynecology outpatient department for both Pap and PCR testing to detect HPV DNA. Nested PCR using primers for L1 consensus gene with My9/My11 and GP6+/GP5+followed by multiplex PCR were carried out to detect HPV 16 and HPV18. Result: HPV prevalence was 11.9% out of which 3.67% cases of negative for intra-epithelial lesion or malignancy (NILM) and in 71.1% (27/38) of atypical cervical smears were HPV positive. There was increasing trend of high-risk-HPV positivity (HR HPV 16 and 18), from 20% in benign cytology (NILM) to 42.9 % in LSIL, 71.41% in HSIL and 100% in SCC. There was highly significant association of HPV infection with cervical lesion ($x^2=144.0$, p<0.01) and also with type specific HPV prevalence ($x^2=7.761^*$, p<0.05).

퍼지 추론 규칙을 이용한 자궁 경부진 핵 인식 (Nucleus Recognition of Uterine Cervical Pap-Smears using Fuzzy Reasoning Rule)

  • 김광백;송두헌
    • 한국컴퓨터정보학회논문지
    • /
    • 제13권3호
    • /
    • pp.179-187
    • /
    • 2008
  • 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 세포핵영역과 세포질을 분류하여 세포핵 영역을 추출한다. 그리고 Kapur 방법을 적용하여 세포핵 영역의 엔트로피 누적확률을 구한 후, 영상을 이진화한다. Kapur 방법이 적용된 이진화 영상에서 세포핵 영역의 중심과 주위 화소를 비교하는 $3{\times}3$ 마스크를 적용하여 영상의 미세한 잡음을 제거 한 후, 8 방향 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 퍼지추론 규칙을 적용하여 자궁 경부 세포진 영상에서 정상 세포핵 및 암종 세포핵을 인식한다.

  • PDF