Pap Smear Analysis Research Articles

Prevalence of Human Papillomavirus (HPV) Infection and its Association With Pap Smear Findings Among Women Attending a Gynecology Clinic in Khorasan Razavi-Iran.

Human papillomavirus (HPV) infection is the most common sexual transmitted disease and Pap smears and HPV testing are crucial for early detection. Advancements in HPV testing improve accuracy, but optimal screening strategies are still debated. This cross-sectional study explores HPV genotypes and predictors of infection among Iranian women undergoing gynecological screening. Study Design: A retrospective cross-sectional study. Women undergoing their initial cervical screening enrolled in this study. Cervical cytology samples for Pap smear analysis were collected from women referred to the genetic laboratory of Academic Center for Education Culture and Research (ACECR), Khorasan Razavi, during gynecological visits, adhering to standardized liquid-based cytology protocols. These samples were obtained over a one-year period since January 2023. Statistical analyses were conducted using SPSS version 21.0, with a significance level set at P<0.05. A total of 328 women enrolled in this study. The mean age of participants was 36±11 years and the overall HPV prevalence was 37.5% (n=123). Among HPV-positive women, nearly half (48.7%) had a single HPV genotype. Genotypes 6 (13%), 16 (12.3%), and 53 (6.7%) were the most prevalent types. Notably, high-risk HPV genotypes (16 and 18 among all) were identified in one-fourth of the study population. Women with endocervical/transformation zone cells had 25% higher odds of having HPV infection, and having mild, moderate, and severe inflammation increased the odds of having HPV infection by 14%, 11%, and 20%, respectively. The considerably high prevalence of HPV infection highlights the significance of HPV prevention programs in this population. Neither bacterial vaginosis nor candida infection showed a direct link to HPV positivity.

CINNAMON-GUI: Revolutionizing Pap Smear Analysis with CNN-Based Digital Pathology Image Classification

Background Medical imaging has seen significant advancements through machine learning, particularly convolutional neural networks (CNNs). These technologies have transformed the analysis of pathological images, enhancing the accuracy of diagnosing and classifying cellular anomalies. Digital pathology methodologies, including image analysis, have improved cervical cancer diagnostics. However, existing commercial platforms are often costly and restrictive, limiting customization and scalability. Methods CINNAMON-GUI is an open-source digital pathology tool based on CNNs for classifying Pap smear images. Transitioning to a Shiny app in Python, it offers enhanced user interface and interactivity. The application supports dynamic web interactions, advanced features for image analysis, and state-of-the-art CNN models tailored for digital pathology. Key features include intuitive UI components, real-time image and plot generation, memory-efficient data handling, and robust training capabilities with customizable CNN architectures. The tool also integrates with Labelme for defining regions of interest and allows testing on external biospecimens. Results Model A (seed 42, 100 epochs) and Model B (same architecture with adjusted augmentation parameters) were compared. Model A stabilized with training accuracy around 0.88 and validation accuracy around 0.913. Model B showed improved performance with training accuracy around 0.91 and validation accuracy around 0.95. Feature mapping highlighted critical morphological aspects, improving classification accuracy. Model B reduced misclassification errors significantly compared to Model A. Conclusions CINNAMON-GUI demonstrates the potential of an open-source platform in digital pathology, providing transparency and collaborative opportunities. The tool enhances diagnostic accuracy through feature map analysis and optimized CNN training. Future development aims to extend its application to other cancer types, leveraging its dynamic and user-friendly interface for broader use in diagnostics.

Deep Reinforcement Learning for Efficient Digital Pap Smear Analysis

In August 2020, the World Health Assembly launched a global initiative to eliminate cervical cancer by 2030, setting three primary targets. One key goal is to achieve a 70% screening coverage rate for cervical cancer, primarily relying on the precise analysis of Papanicolaou (Pap) or digital Pap smears. However, the responsibility of reviewing Pap smear samples to identify potentially cancerous cells primarily falls on pathologists—a task known to be exceptionally challenging and time-consuming. This paper proposes a solution to address the shortage of pathologists for cervical cancer screening. It leverages the OpenAI-GYM API to create a deep reinforcement learning environment utilizing liquid-based Pap smear images. By employing the Proximal Policy Optimization algorithm, autonomous agents navigate Pap smear images, identifying cells with the aid of rewards, penalties, and accumulated experiences. Furthermore, the use of a pre-trained convolutional neuronal network like Res-Net50 enhances the classification of detected cells based on their potential for malignancy. The ultimate goal of this study is to develop a highly efficient, automated Papanicolaou analysis system, ultimately reducing the need for human intervention in regions with limited pathologists.

Validity and acceptance of self vs conventional sampling for the analysis of human papillomavirus and Pap smear

The newest high-risk human papillomavirus (HPV) detection techniques were included for cervical cancer primary screening under the Spanish National Health System in 2019. These analyses allow changing population approaches to foster adherence to screening. Therefore, the validity of self versus conventional sampling for HPV and cytology analyses was appraised. Women's preferences concerning samples and devices were also evaluated. This is a diagnostic accuracy cross-sectional study among 120 women recruited from a colposcopy clinic at a general hospital in Illes Balears, Spain. Participants were given written information and asked for a self-sample. One of two sets containing two devices each were handed. One set was transported dry and the second in liquid medium. Next, clinicians collected vaginal samples that were our gold standards. The agreement between both techniques was examined with the Kappa coefficient (κ). Self-sampling evaluation and preferences for different vaginal devices were also surveyed. The agreement between self and conventional samples concerning HPV positivity was very good (κ 0.86 for Mía by XytoTest® and 0.83 for Viba-Brush®) or reasonable (κ 0.73 for Iune and 0.68 for viscose swab). Pap smears from self-samples exhibited moderate agreement (κ 0.41 for Mía® and 0.51 for Viba-Brush® respectively) for negative versus ASC-US and worse results. Most of the participants considered self-sampling as beneficial (110 or 91.7%) and the advantages were, in decreasing order, scheduling, comfort, intimacy and less fear for pain or disturbance. The priority of choice for the devices was Mía® and viscose swab (chosen in first or second place) in opposition to Iune and Viba-Brush® (chosen in third or fourth place). If Viba-Brush® was to collect the best quality samples, 108 women (94.7%) switched their decisions. Our agreement between self and conventional samples was very good or reasonable for HPV, with the best values for devices in a liquid medium, and moderate for cytology. Even so, reflex cytology on self-samples is a valuable tool in promoting adherence. Self-sampling was widely accepted for smooth and thin devices. However, there is no resistance to change to others if a higher quality of the sample is obtained.

Hybrid Decision Fusion based Multimodal Ensemble Framework for Cervical Cancer Detection

Cervical cancer is fourth in the list of cancers that affect women. It has remained the main cause of death for women in developing nations. The cancer is spread through human papilloma virus (HPV), which is sexually transmitted. Pap smear and colposcopy image analysis remain prominent methods of diagnosis. These screening tests require skilled diagnostic experts, a scarce resource in developing countries thus restricting the effectiveness of the cancer detection process in large scale. Machine learning and deep learning are branches of artificial intelligence that are being used increasingly in cancer diagnosis. This study proposes a novel hybrid intelligent system for cervical cancer detection. A hybrid model of feature extraction and feature fusion is proposed for merging the two-state image and clinical data. Subsequently a machine learning ensemble learner is assembled to classify the features. The model performed with a satisfactory accuracy of 96.16%. Our results show that our method outperforms state of the art approaches and archives better, dependable accuracy.

DESEMPENHO DO EXAME CITOPATOLÓGICO NO DIAGNÓSTICO DE VAGINOSE BACTERIANA

ABSTRACT Objective: to assess Pap smear performance in bacterial vaginosis diagnosis in women of childbearing age. Method: a cross-sectional, retrospective study carried out in a health unit in a city in the interior of São Paulo. The study included information from 1,173 women who underwent collection of Pap smear and Gram-stained vaginal smears (reference standard test for bacterial vaginosis diagnosis) and analysis based on the Nugent score, from January 2013 to June 2020. Secondary data collected from the information and internal control systems were used. Results: the prevalence of bacterial vaginosis in the sample was 31.8%. The degree of agreement between the two diagnostic methods by the Kappa index was 0.54, considered moderate, with a value &lt;0.001. Sensitivity was 55.2% and specificity was 94.1%, with accuracy of 81.7% and positive predictive value of 81.4% and negative of 81.8%. Conclusion: Pap smear showed agreement with the reference standard of 0.77, however, does not replace the Gram-stained vaginal smear, but can be used as an auxiliary method for bacterial vaginosis diagnosis.

The Role of p16/Ki-67 Immunostaining, hTERC Amplification and Fibronectin in Predicting Cervical Cancer Progression: A Systematic Review.

Simple SummaryHuman papillomaviruses (HPV) are common sexually transmitted infections and they are responsible for cervical cancer (CC), as well as for several other anogenital cancers. CC is the fourth leading cause of death in women with cancer, although it could be preventable by enforcement of optimal screening programs. The Pap smear is the standard screening test for CC and precancerous lesions, and a combination of Pap smear and HPV testing is generally recommended as a triage step before colposcopy. However, these tests cannot predict lesion progression, which is why several adjunctive biomarkers have been studied. Our aim was to summarize current scientific data on the role of these biomarkers, with a view to determining which biomarkers could help to more accurately establish the need for colposcopy and at the same time, to limit the number of unnecessary colposcopy referrals.Human papillomaviruses (HPVs) are common sexually transmitted infectious agents responsible for several anogenital and head and neck cancers. Cervical cancer (CC) is the fourth leading cause of death in women with cancer. The progression of a persistent HPV infection to cancer takes 15–20 years and can be preventable through screening. Cervical cytology (Pap smear) is the standard screening test for CC and precancerous lesions. For ASC-US and ASC-H lesions, a combination of Pap smear and HR-HPV analysis is recommended as a triage step before colposcopy. However, these tests cannot predict progression to CC. For this purpose, we summarized current scientific data on the role of p16/Ki-67 immunohistostaining, telomerase and fibronectin in predicting progression to CC. p16 and p16/Ki-67 dual staining (DS) were more specific than HR-HPV DNA testing for the detection of CIN2+/CIN3+ in women with ASC-US and LSIL. Similarly, hTERC FISH analysis significantly improved the specificity and positive predictive value of HPV DNA testing in differentiating CIN2+ from CIN2 cytological samples. In conclusion, p16 IHC, p16/Ki-67 DS and hTERC FISH amplification are all valid adjunctive biomarkers which significantly increase the sensitivity and specificity of cervical dysplasia diagnosis, especially when combined with HPV DNA testing. However, considering the global socioeconomic background, we can postulate that p16 and p16/ Ki-67 IHC can be used as a next step after positive cytology for ASC-US or LSIL specimens in low-income countries, instead of HPV DNA testing. Alternatively, if HPV DNA testing is covered by insurance, p16 or p16/Ki-67 DS and HPV DNA co-testing can be performed. In middle- and high-income countries, hTERC amplification can be performed as an adjunctive test to HPV DNA testing in women with ASC-US and LSIL.

The structure of cervical diseases in women suffering from pelvic floor dysfunction

Background. The prevalence of pelvic floor dysfunction (PFD) is soaring steadily. The protrusion of the cervix beyond vaginal opening when exposed to environmental factors can lead to the development of dystrophic, sclerotic and neoplastic processes of the cervix, which are mediated by changes in the pH, biocenosis of the vagina and environmental factors.&#x0D; Aim. To study the pathogenesis of cervical diseases in patients with PFD.&#x0D; Materials and methods. The study design is an open-label prospective observational study. The study included 40 patients of reproductive age: 26 patients with cervical disease with PFD (PFD group), 14 patients without cervical disease and PFD made up the second group.&#x0D; Results. The patients included in the study were comparable in terms of age and body mass index. Pap smear analysis revealed that the average number of leukocytes is significantly higher in patients with PFD compared to patients in the group without PFD 5.5 (1.520.0) and 1.5 (1.56.5) respectively (p=0.040). In PFD group, a high prevalence of the following conditions was observed: cervical leukoplakia (15%), CIN1 (38.5%), CIN2 (8%), chronic cervicitis (38.5%). Onco-cytological test results reviewed where the high prevalence of parakeratosis and hyperkeratosis (15%), ASCUS (15%), LSIL (23%) and HSIL (8%) were also noteworthy. It was observed that human papillomavirus type 16 was predominant in PFD patient group.&#x0D; Conclusion. The data obtained indicates an increased risk of developing cervical diseases in patients with PFD.

A Deep Learning Ensemble Method to Assist Cytopathologists in Pap Test Image Classification.

In recent years, deep learning methods have outperformed previous state-of-the-art machine learning techniques for several problems, including image classification. Classifying cells in Pap smear images is very challenging, and it is still of paramount importance for cytopathologists. The Pap test is a cervical cancer prevention test that tracks preneoplastic changes in cervical epithelial cells. Carrying out this exam is important in that early detection. It is directly related to a greater chance of curing or reducing the number of deaths caused by the disease. The analysis of Pap smears is exhaustive and repetitive, as it is performed manually by cytopathologists. Therefore, a tool that assists cytopathologists is needed. This work considers 10 deep convolutional neural networks and proposes an ensemble of the three best architectures to classify cervical cancer upon cell nuclei and reduce the professionals’ workload. The dataset used in the experiments is available in the Center for Recognition and Inspection of Cells (CRIC) Searchable Image Database. Considering the metrics of precision, recall, F1-score, accuracy, and sensitivity, the proposed ensemble improves previous methods shown in the literature for two- and three-class classification. We also introduce the six-class classification outcome.

Automated Cell Nuclei Segmentation on Cervical Smear Images Using Structure Analysis

Cervical cancer is a common cancer that affects women around the world, and it is also the most common cancer in the developing countries. The cancer burden has increased due to several factors, such as population growth and ageing. In the early century, the systematization of cervical cancer cells takes some time to process manually, and the result that comes out is also inaccurate. This article presents a new nucleus segmentation on pap smear cell images based on structured analysis or morphological approach. Morphology is a broad set of image processing operations that process images based on shape, size and structure. This operation applies a structural element of the image to create an output image of the same size. The most basic of these operations are dilation and erosion. The results of the numerical analysis indicate that the proposed method achieved about 94.38% (sensitivity), 82.56% (specificity) and 93% (accuracy). Also, the resulting performance was compared to a few existing techniques such as Bradley Method, Nick Method and Sauvola Method. The results presented here may facilitate improvements in the detection method of the pap smear cell image to resolve the time-consuming issue and support better system performance to prevent low precision result of the Human Papilloma Virus (HPV) stages. The main impact of this paper is will help the doctor to identify the patient disease based on Pap smear analysis such as cervical cancer and increase the percentages of accuracy compared to the conventional method. Successful implementation of the nucleus detection techniques on Pap smear image can become a standard technique for the diagnosis of various microbiological infections such as Malaria and Tuberculosis.

Cervical cancer detection in pap smear whole slide images using convNet with transfer learning and progressive resizing.

Cervical intraepithelial neoplasia (CIN) and cervical cancer are major health problems faced by women worldwide. The conventional Papanicolaou (Pap) smear analysis is an effective method to diagnose cervical pre-malignant and malignant conditions by analyzing swab images. Various computer vision techniques can be explored to identify potential precancerous and cancerous lesions by analyzing the Pap smear image. The majority of existing work cover binary classification approaches using various classifiers and Convolution Neural Networks. However, they suffer from inherent challenges for minute feature extraction and precise classification. We propose a novel methodology to carry out the multiclass classification of cervical cells from Whole Slide Images (WSI) with optimum feature extraction. The actualization of Conv Net with Transfer Learning technique substantiates meaningful Metamorphic Diagnosis of neoplastic and pre-neoplastic lesions. As the Progressive Resizing technique (an advanced method for training ConvNet) incorporates prior knowledge of the feature hierarchy and can reuse old computations while learning new ones, the model can carry forward the extracted morphological cell features to subsequent Neural Network layers iteratively for elusive learning. The Progressive Resizing technique superimposition in consultation with the Transfer Learning technique while training the Conv Net models has shown a substantial performance increase. The proposed binary and multiclass classification methodology succored in achieving benchmark scores on the Herlev Dataset. We achieved singular multiclass classification scores for WSI images of the SIPaKMed dataset, that is, accuracy (99.70%), precision (99.70%), recall (99.72%), F-Beta (99.63%), and Kappa scores (99.31%), which supersede the scores obtained through principal methodologies. GradCam based feature interpretation extends enhanced assimilation of the generated results, highlighting the pre-malignant and malignant lesions by visual localization in the images.

Clinico-pathological Analysis of Cervical Pap Smear in Patients Attending Gynecology OPD of a Medical College

Background: Cervical cancer ranks the most common cancer among Nepalese women. Cervical and vaginal infections constitute the most common gynecological problems. Through Pap smear screening, early diagnosis, follow up and treatment, morbidity and mortality can be reduced by 70% and 80% respectively. &#x0D; Methods: This retrospective study was conducted to know the incidence of abnormal cervical epithelial lesions and cervico-vaginal infections. It was carried out in the Outpatient Department of Gynecology at Chitwan Medical College from April 2018 to March 2019. The data were collected and standard statistical analysis done using Microsoft Excel 2007. &#x0D; Results: The most prevalent cervical epithelial cell abnormality was atypical squamous cells of undetermined significance (3.43%) whereas the least common was low grade squamous intraepithelial lesion (0.21%). The most prevalent cervical vaginal infection was Bacterial vaginosis (12.30%) whereas the least prevalent was Trichomoniasis (0.29%). The majority of the women with epithelial cell abnormality were in the age group of 31-40 years whereas the lowest number in the age group less than 20 years. The highest prevalence of cervical vaginal infection was in the reproductive age group (31-50 years) and the lowest in the age above 51 years. Most of the patients had multiple symptoms like vaginal discharge, genital itching, whereas only (20.17%) visited for routine screening. &#x0D; Conclusion: Atypical squamous cells of undetermined significance and Bacterial vaginosis were the most common finding in Pap smear test representing abnormal cytology of cervix and cervicovaginal infection respectively.

Analysis of Pap smears in a cytopathology lab of a teaching hospital

Aims: This study was done to find out age wise distribution pattern, cellular abnormality and adequacy of Pap smears.&#x0D; Methods: A retrospective study of 470 Pap smears based on laboratory record was done from September 2019 to April 2020 at B and C Medical College Teaching Hospital, Birtamod, Jhapa, Nepal. Descriptive analysis performed using MS Excel and SPSS 16.&#x0D; Results: Out of 470 analyzable data 2.55% had abnormal cytology, all high-grade lesions were in 30-49 age group and 0.21% were detected as carcinoma. Mean age of women was 39.2±10.5 years. Age distribution follows the normal Gaussian curve. Age group of 30-60 years consists of four-fifth (75.5%, n=355) and Two-third of cases (66.4%, n=312) were of age group 30-49 years.&#x0D; Conclusions: Pap samples were normally distributed by age. Test requisition forms lack adequate clinical information. Even the inadequately sampled Pap smears were satisfactory for evaluation.&#x0D; Keywords: cancer, cervix, intraepithelial lesion, Pap smear, screening

A Review: Pap Smear Analysis Based on Image Processing Approach

Nowadays, in the hospital, cervical cancer is in the higher rank (number 2) of the most popular cancer among ladies in the world. This cancer develops in the woman’s cervix which the womb is the entrance. Mostly, doctors in the hospital having trouble to identify the cancer cell because the nucleus of the cell is sometimes slightly hard to observe with eyes. The nucleus of the normal cell is in a smaller size compared to the abnormal nucleus. The abnormal nucleus has a bigger size, which sometimes, the size cannot be identified accurately by seeing with bare eyes to classify the stages of cervical cancer. This is because every doctor has different perspectives to observe the classification of the stages of cancer by observing the nucleus without accurate dimensionality reduction in the accuracy of the classifier. Recently, many researchers proposed a method to detect and classify the Pap smear cell images for cervical cancer diagnosis. This approach may improve the accuracy of the detection and the classification which to show better performance with the balance data and samples precisely. Some of the patients got the result that they are on stage 2, however after re-testing, they actually on stage 4 which the chance to heal is very low. This happens because the doctor can’t find the accurate balance data and sample precisely. In this paper, a comprehensive review of cervical detection based on segmentation nucleus and classification was studied.

Estimation of a point along overlapping cervical cell nuclei in Pap smear image using colour space conversion

The identification of normal and abnormal cells is considered as one of the most challenging task for computer assisted Pap smear analysis system especially when abnormal cells are hidden behind overlapped cells. The complexity of the problem depends on whether only cytoplasm of two cells are overlapped, or only nuclei are overlapped with disjoint cytoplasm, and in some case both cytoplasm and nuclei are overlapped. Sometimes, Pap smear sample contains mixture of cells with disjoint/overlapped cytoplasm and nuclei. Hence, there is need for algorithm which segments cells from the cluster of overlapped cells. In case of overlapped nuclei, identifying the point of overlapping accurately is one of the significant steps in segmenting overlapped cells. This paper discusses image processing-based method which segment disjoint nuclei and identifies the point of intersection called as concavity point in the cluster of cells where only nuclei are overlapped.

Estimation of a point along overlapping cervical cell nuclei in Pap smear image using colour space conversion

The identification of normal and abnormal cells is considered as one of the most challenging task for computer assisted Pap smear analysis system especially when abnormal cells are hidden behind overlapped cells. The complexity of the problem depends on whether only cytoplasm of two cells are overlapped, or only nuclei are overlapped with disjoint cytoplasm, and in some case both cytoplasm and nuclei are overlapped. Sometimes, Pap smear sample contains mixture of cells with disjoint/overlapped cytoplasm and nuclei. Hence, there is need for algorithm which segments cells from the cluster of overlapped cells. In case of overlapped nuclei, identifying the point of overlapping accurately is one of the significant steps in segmenting overlapped cells. This paper discusses image processing-based method which segment disjoint nuclei and identifies the point of intersection called as concavity point in the cluster of cells where only nuclei are overlapped.

A pap-smear analysis tool (PAT) for detection of cervical cancer from pap-smear images

BackgroundCervical cancer is preventable if effective screening measures are in place. Pap-smear is the commonest technique used for early screening and diagnosis of cervical cancer. However, the manual analysis of the pap-smears is error prone due to human mistake, moreover, the process is tedious and time-consuming. Hence, it is beneficial to develop a computer-assisted diagnosis tool to make the pap-smear test more accurate and reliable. This paper describes the development of a tool for automated diagnosis and classification of cervical cancer from pap-smear images.MethodScene segmentation was achieved through a Trainable Weka Segmentation classifier and a sequential elimination approach was used for debris rejection. Feature selection was achieved using simulated annealing integrated with a wrapper filter, while classification was achieved using a fuzzy C-means algorithm.ResultsThe evaluation of the classifier was carried out on three different datasets (single cell images, multiple cell images and pap-smear slide images from a pathology lab). Overall classification accuracy, sensitivity and specificity of ‘98.88%, 99.28% and 97.47%’, ‘97.64%, 98.08% and 97.16%’ and ‘95.00%, 100% and 90.00%’ were obtained for each dataset, respectively. The higher accuracy and sensitivity of the classifier was attributed to the robustness of the feature selection method that accurately selected cell features that improved the classification performance and the number of clusters used during defuzzification and classification. Results show that the method outperforms many of the existing algorithms in sensitivity (99.28%), specificity (97.47%), and accuracy (98.88%) when applied to the Herlev benchmark pap-smear dataset. False negative rate, false positive rate and classification error of 0.00%, 10.00% and 5.00%, respectively were obtained when applied to pap-smear slides from a pathology lab.ConclusionsThe major contribution of this tool in a cervical cancer screening workflow is that it reduces on the time required by the cytotechnician to screen very many pap-smears by eliminating the obvious normal ones, hence more time can be put on the suspicious slides. The proposed system has the capability of analyzing a full pap-smear slide within 3 min as opposed to the 5–10 min per slide in the manual analysis. The tool presented in this paper is applicable to many pap-smear analysis systems but is particularly pertinent to low-cost systems that should be of significant benefit to developing economies.

Cervical cancer classification from Pap-smears using an enhanced fuzzy C-means algorithm

Abstract Globally, cervical cancer ranks as the fourth most prevalent cancer affecting women. However, it can be successfully treated if detected at an early stage. The Pap smear is a good tool for initial screening of cervical cancer, but there is the possibility of error due to human mistake. Moreover, the process is tedious and time-consuming. The objective of this study was to mitigate the risk of mistake by automating the process of cervical cancer classification from Pap smear images. In this research, contrast local adaptive histogram equalization was used for image enhancement. Cell segmentation was achieved through a Trainable Weka Segmentation classifier, and a sequential elimination approach was used for debris rejection. Feature selection was achieved using simulated annealing integrated with a wrapper filter, while classification was achieved using a fuzzy c-means algorithm. The evaluation of the classifier was carried out on three different datasets (single cell images, multiple cell images and Pap smear slide images from a pathology unit). An overall classification accuracy, sensitivity and specificity of ‘98.88%, 99.28% and 97.47%‘, ‘97.64%, 98.08% and 97.16%’ and ‘96.80%, 98.40% and 95.20%’ were obtained for each dataset respectively. The higher accuracy and sensitivity of the classifier was attributed to the robustness of the feature selection method that was utilized to select cell features that would improve the classification performance, and the number of clusters used during defuzzification and classification. The evaluation and testing conducted confirmed the rationale of the approach taken, which is based on the premise that the selection of salient features embeds sufficient discriminatory information that leads to an increase in the accuracy of cervical cancer classification. Results show that the method outperforms many of the existing algorithms in terms of the false negative rate (0.72%), false positive rate (2.53%), and classification error (1.12%), when applied to the DTU/Herlev benchmark Pap smear dataset. The approach articulated in this paper is applicable to many Pap smear analysis systems, but is particularly pertinent to low-cost systems that should be of significant benefit to developing economies.

Prevalence and analysis of abnormal Pap smear: Prospective study of 752 patients in a tertiary care hospital of South India

Prevalence and analysis of abnormal Pap smear: Prospective study of 752 patients in a tertiary care hospital of South India

Analysis of Cytology and Histopathology Results in an Immunocompromised Population [13E

INTRODUCTION: HIV and Renal Transplant patients are in general at higher risk for cervical dysplasia and cancer due to their immunocompromised status. However, the literature is not clear if these patients are at equal risk. The objective of the study is to compare PAP smear results as well has histopathology findings in these two populations. METHODS: A retrospective chart review of colposcopy patients seen at SUNY Downstate Medical Center with a history of HIV or Renal Transplant was performed. Each patient’s index PAP and colposcopy results were reviewed. RESULTS: A total of 61 HIV patients and 11 Renal Transplant patients were included. 29.5% (18/61) of HIV patients had an initial PAP result of ASCUS and 33% (6/18) of these patients had biopsies positive for precancerous lesions ranging from CIN 1 - 3. 54% (33/61) of HIV patients had an initial PAP of LSIL and 42% (14/33) of these patients had positive biopsy results. 10% (6/61) had an initial PAP of HSIL or ASC-H and 100% of these patients had precancerous lesions (CIN 1-3) or cervical cancer (1/6). Of the 11 Renal Transplant patients, 5/11 presented with ASCUS and 6/11 had LSIL. Only 3/11 had histopathology and all had CIN 1. CONCLUSION: An analysis of PAP smear results in these two populations reveals that HIV patients tend to have PAP smears of a higher grade with a higher incidence of dysplasia as compared to Renal Transplant patients. The reason for this is unclear but may be due to the underlying reasons for the immunocompromised state.