• Journal of information and communication convergence engineering
• /
• v.6 no.1
• /
• 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.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.13 no.8
• /
• pp.1699-1704
• /
• 2009

If detected early enough, cervical cantor may have a good survival rate due to its preneoplastic state. However, the process is so time consuming that a medical expert can handle only a small amount of such examinations. In this paper, we propose a new nucleus extraction algorithm for uterine cervical pap smears in order to mitigate such burdens of medical experts. In the preneoplastic state cytodiagnosis images, it is important to differentiate three main areas - background, cytoplasm and nucleus. Thus, we apply lighting compensation and $3{\times}3$ mask of B channel in order to restore damaged image and remove noises respectively. The cell object is obtained from those clean binarized images with Grossfire algorithm. When there are clusters of cells, the target nucleus can be obtained with repetitive binarization of R channel brightness. In our experiment of using uterine cervical pap smears of 400 magnifications that is common in the diagnostic cytology, our method is able to extract 40 nucleus out of 45 population successfully.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.16 no.5
• /
• pp.519-524
• /
• 2006

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 fuzzy grey morphology operation. 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 enhanced fuzzy ART algorithm is used to the extracted nucleus and the results show that the proposed method is efficient in nucleus recognition and uterine cervical Pap-Smears extraction.

• The Korean Journal of Cytopathology
• /
• v.14 no.2
• /
• 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.

• Asian Pacific Journal of Cancer Prevention
• /
• v.13 no.12
• /
• 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.

• Asian Pacific Journal of Cancer Prevention
• /
• v.14 no.2
• /
• 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.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.11 no.10
• /
• pp.1992-1998
• /
• 2007

It is important to obtain conn cytodiagnosis to classify background, cytoplasm, and nucleus from the diagnostic image. This study mose an algorithm that detects and classifies carcinoma cells of the uterine cervix in Pap smear using features of cervical cancer. It applies Median filter and Gaussian filter to get noise-removed nucleus area and also applies Kapur method in binarization of the resultant image. We apply 8-directional contour tracking algorithm and stretching technique to identify and revise clustered cells that often hinder to obtain correct analysis. The resulted nucleus area has distinguishable features such as cell size, integration rate, and directional coefficient from normal cells so that we can detect and classify carcinoma cells successfully. The experiment results show that the performance of the algorithm is competitive with human expert.

• Journal of Biomedical Engineering Research
• /
• v.22 no.3
• /
• 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.

• Asian Pacific Journal of Cancer Prevention
• /
• v.16 no.4
• /
• 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).

• Journal of the Korea Society of Computer and Information
• /
• v.13 no.3
• /
• pp.179-187
• /
• 2008

In this paper, we apply a set of algorithms to classily normal and cancer nucleus from uterine cervical pap-smear images. First, we use lightening compensation algorithm to restore color images that have defamation through the process of obtaining $1{\times}400$ microscope magnification. Then, we remove the background from images with the histogram distributions of RGB regions. We extract nucleus areas from candidates by applying histogram brightness, Kapur method, and our own 8-direction contour tracing algorithm. Various binarization, cumulative entropy, masking algorithms are used in that process. Then, we are able to recognize normal and cancer nucleus from those areas by using three morphological features - directional information, the size of nucleus, and area ratio - with fuzzy membership functions and deciding rules we devised. The experimental result shows our method has low false recognition rate.