Comparison of visual inspection and Papanicolau (PAP) smears for cervical cancer screening in Honduras: should PAP smears be abandoned?

Artificial Intelligence in Cervical Cancer Screening and Diagnosis

Cervical cancer remains a leading cause of cancer death in women, seriously threatening their physical and mental health. It is an easily preventable cancer with early screening and diagnosis. Although technical advancements have significantly improved the early diagnosis of cervical cancer, accurate diagnosis remains difficult owing to various factors. In recent years, artificial intelligence (AI)-based medical diagnostic applications have been on the rise and have excellent applicability in the screening and diagnosis of cervical cancer. Their benefits include reduced time consumption, reduced need for professional and technical personnel, and no bias owing to subjective factors. We, thus, aimed to discuss how AI can be used in cervical cancer screening and diagnosis, particularly to improve the accuracy of early diagnosis. The application and challenges of using AI in the diagnosis and treatment of cervical cancer are also discussed.

A review of image analysis and machine learning techniques for automated cervical cancer screening from pap-smear images

BACKGROUND AND OBJECTIVE

Early diagnosis and classification of a cancer type can help facilitate the subsequent clinical management of the patient. Cervical cancer ranks as the fourth most prevalent cancer affecting women worldwide and its early detection provides the opportunity to help save life. To that end, automated diagnosis and classification of cervical cancer from pap-smear images has become a necessity as it enables accurate, reliable and timely analysis of the condition's progress. This paper presents an overview of the state of the art as articulated in prominent recent publications focusing on automated detection of cervical cancer from pap-smear images.

METHODS

The survey reviews publications on applications of image analysis and machine learning in automated diagnosis and classification of cervical cancer from pap-smear images spanning 15 years. The survey reviews 30 journal papers obtained electronically through four scientific databases (Google Scholar, Scopus, IEEE and Science Direct) searched using three sets of keywords: (1) segmentation, classification, cervical cancer; (2) medical imaging, machine learning, pap-smear; (3) automated system, classification, pap-smear.

RESULTS

Most of the existing algorithms facilitate an accuracy of nearly 93.78% on an open pap-smear data set, segmented using CHAMP digital image software. K-nearest-neighbors and support vector machines algorithms have been reported to be excellent classifiers for cervical images with accuracies of over 99.27% and 98.5% respectively when applied to a 2-class classification problem (normal or abnormal).

CONCLUSION

The reviewed papers indicate that there are still weaknesses in the available techniques that result in low accuracy of classification in some classes of cells. Moreover, most of the existing algorithms work either on single or on multiple cervical smear images. This accuracy can be increased by varying various parameters such as the features to be extracted, improvement in noise removal, using hybrid segmentation and classification techniques such of multi-level classifiers. Combining K-nearest-neighbors algorithm with other algorithm(s) such as support vector machines, pixel level classifications and including statistical shape models can also improve performance. Further, most of the developed classifiers are tested on accurately segmented images using commercially available software such as CHAMP software. There is thus a deficit of evidence that these algorithms will work in clinical settings found in developing countries (where 85% of cervical cancer incidences occur) that lack sufficient trained cytologists and the funds to buy the commercial segmentation software.

Comparing the results of Pap smear and Direct Visual Inspection (DVI) with 5% acetic acid in cervical cancer screening

Background:

Cervical cancer is the most second common cancer among Iranian women. This study was carried out to compare the results of Pap smear method and Direct Visual Inspection (DVI) with 5% acetic acid in cervical cancer screening in Tabriz, Iran.

Material and Methods:

This cross-sectional study was carried out in Alzahra Therapeutic-Educational Centre, Tabriz, Iran in 2013 on 1000 women. First, Pap smear was done for all women, and then the cervix exposed with 5% acetic acid by cotton swab for 30 seconds and observed under adequate light. At the end, women with abnormal results in Pap smear or DVI method were referred to colposcopy and biopsy. Test's sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV), LR+, LR- and confidence interval (CI) were determined (P < 0.05).

Results:

Nine-hundred and seventy-four (94.7%) cases were normal and had no abnormal findings and 26 (2.6%) participants had positive results in Pap smear or DVI test. Twelve women had abnormal Pap smear (nine women with atypical squamous cells of undetermined significance, ASCUS, three women with dysplasia, atypical endocervical, and low-grade squamous intraepithelial lesion, LSIL results) and 14 women had positive DVI (four women with human papillomavirus, HPV or koilocyte,) and one women with abnormality in both method had carcinoma in biopsy that referred to oncologist. In this study the sensitivity, specificity, PPV and NPV for DVI were 71.4%, 50%, 35.7%, and 81.8% respectively in comparison with 14.3%, 50%, 10%, and 60% for Pap smear.

Conclusion:

As the DVI method has higher sensitivity and positive predictive value than Pap smear, it could be used as a useful method beside the Pap smear.

Race, ethnicity, and income factors impacting human papillomavirus vaccination rates

BACKGROUND

Human papillomavirus (HPV) infection and cervical cancer disproportionately affect low-income and minority women. HPV vaccines have the potential to either reduce or exacerbate racial disparities in HPV-related diseases and cervical cancers, depending on the equitability of vaccine uptake.

OBJECTIVES

This review aims to identify barriers and facilitators of equitable uptake of HPV vaccination among low-income and minority girls. This review discusses factors related to race, ethnicity, and income that are associated with initiation and completion rates of the 3-dose HPV vaccine series and presents targets for intervention.

METHODS

We reviewed relevant English-language literature to identify current vaccination rates and factors associated with vaccine uptake. Study findings related to race (black, Latino, Asian), and incomes were summarized.

RESULTS

Current trends in the United States indicate low uptake among all adolescents, and that rates stagnated between 2011 and 2012. Low-income and minority adolescents are equally or more likely to start the HPV vaccination series than are white and higher-income adolescents, but are less likely to complete all 3 shots. Provider recommendation is a key factor in HPV vaccination, and minorities are less likely to report receiving recommendations for HPV vaccination.

CONCLUSIONS

As black, Hispanic, and Asian populations continue to grow in the United States over the next several decades, it is imperative that we not only improve HPV vaccination rates overall, but also focus on high-risk populations to prevent an increase in cervical cancer disparities.

Major challenges to scale up of visual inspection-based cervical cancer prevention programs: the experience of Guatemalan NGOs

Scale up of visual inspection with acetic acid (VIA) in Guatemala encountered major challenges, including high attrition of people trained, didactic training without hands-on skills building, lack of continued supervision, and provision of VIA alone without immediate on-site provision of cryotherapy.

Background:

Like many other low- and middle-income countries, Guatemala has adopted visual inspection with acetic acid (VIA) as a low-resource alternative to the Pap smear for cervical cancer screening. Nongovernmental organizations (NGOs) introduced VIA to Guatemala in 2004, and a growing number of NGOs, working both independently and in collaboration with the Guatemalan Ministry of Health, employ VIA in cervical cancer prevention programs today. While much research describes VIA efficacy and feasibility in Latin America, little is known about NGO involvement with VIA programming or experiences with VIA outside the context of clinical trials and pilot projects in the region.

Methods:

To explore challenges faced by NGOs implementing VIA programs in Guatemala, we conducted semi-structured interviews with 36 NGO staff members involved with 20 VIA programs as direct service providers, program administrators, and training course instructors. Additionally, we collected data through observation at 30 NGO-sponsored cervical cancer screening campaigns, 8 cervical cancer prevention conferences, and 1 week-long NGO-sponsored VIA training course.

Results:

Frequently highlighted challenges included staff turnover, concerns over training quality, a need for opportunities for continued supervision, and problems with cryotherapy referrals when immediate treatment for VIA-positive women was unavailable.

Conclusions:

Reducing staff turnover, budgeting to train replacement providers, standardizing training curricula, and offering continued supervision are key strategies to improve VIA service quality and program sustainability. Alternative training methods, such as on-the-job mentoring and course prerequisites of online learning, could help increase training time available for clinical supervision. Efforts should be made to ensure that VIA testing is coupled with immediate cryotherapy, that providers trained in VIA are also trained in cryotherapy, and that cryotherapy supplies and equipment are maintained. Where this is not possible and only VIA screening is available, referral systems must be strengthened.

Race, ethnicity and income as factors for HPV vaccine acceptance and use

If distributed equitably, Human Papillomavirus (HPV) vaccines have the potential to reduce racial disparities in HPV-related diseases and cervical cancers. However, current trends in the US indicate low uptake among all adolescents, with persistent disparities among minority and low-income adolescents despite largely positive views of vaccination among their parents. As Black, Hispanic, and Asian populations continue to grow in the US over the next 40 y, it is imperative that we not only improve HPV vaccination rates overall, but focus on high-risk populations to prevent an increase in cervical cancer disparities. This review discusses initiation and completion rates of the three-dose HPV vaccine series among adolescents in high-risk groups and describes cultural similarities and differences in motivation and barriers to vaccination. The goal of this review is to highlight factors leading to vaccination in different adolescent racial groups and to help guide the development of strategies to increase rates of vaccine initiation and completion among groups at the highest risk for developing cervical cancer.

Awareness, knowledge and beliefs about HPV, cervical cancer and HPV vaccines among nurses in Cameroon: an exploratory study

BACKGROUND

While it is known that sub-Saharan African countries face multiple obstacles such as cost in adopting vaccination against human papillomavirus (HPV), the crucial role nurses can play in implementing such programs has not been adequately examined.

OBJECTIVES

To investigate the knowledge and awareness of HPV, primary cause of cervical cancer and HPV vaccine among nurses working at four Cameroon Baptist Convention Health Services facilities, and to explore what factors influence nurses' willingness to inform and recommend HPV vaccine to adolescents and parents attending clinics.

DESIGN AND SETTING

A structured questionnaire survey was administered to a convenience sample of nursing staff working at the four health facilities.

RESULTS

Of 192 eligible nurses 76 (39.6%) participated in the study. There were moderately low levels of knowledge about HPV infection and prevention of cervical cancer, but a moderately high level of knowledge about HPV vaccine. Although 90.8% acknowledged that cervical cancer is directly linked to HPV infection, nearly 32% failed to identify it as a sexually transmitted infection (STI), while 43.4% believed it is an uncommon infection. Willingness to recommend the HPV vaccine was moderate, with 69.7% intentionally initiating discussions with patients about the subject. The most important factors considered when deciding to recommend the vaccine included effectiveness (56.6%) and side effects/safety (11.8%). Cost was less of a concern (6.6%), likely due to the availability of donated vaccine.

CONCLUSION

Despite high awareness about HPV, more education about the virus, cervical cancer and the vaccine are required to further increase nurses' willingness to recommend the vaccine and strengthen strategies for reaching adolescents through nurses in Cameroon.

Cervical cancer screening in primary health care setting in Sudan: a comparative study of visual inspection with acetic acid and Pap smear

OBJECTIVE

To determine the feasibility of visual inspection with the use of acetic acid (VIA) as a screening method for cervical cancer, an alternative to the Pap smear used in primary health care setting in Sudan, and to compare sensitivity, specificity, positive and negative predictive values, and histological diagnosis of positive cases of both tests.

METHODS

A cross-sectional study of 934 asymptomatic women living in Khartoum, Sudan, was conducted during 2009-2010. A semi-structured questionnaire containing socio-economic and reproductive variables was used to collect data from each participant. Methods of screening used were VIA and conventional Pap smear, followed by colposcopy and biopsy for confirmation of the positive results of both screening tests.

RESULTS

The tests identified altogether 119 (12.7%) positive women. VIA detected significantly more positive women than Pap smear (7.6% versus 5.1%; P = 0.004), with an overlap between the two screening tests in 19% of positive results. There was no significant difference between VIA and Pap smear findings and sociodemographic and reproductive factors among screened women. Use of colposcopy and biopsy for positive women confirmed that 88/119 (73.9%) were positive for cervical intraepithelial neoplasia. VIA had higher sensitivity than Pap smear (74.2% versus 72.9%; P = 0.05) respectively. Out of 88 confirmed positive cases, 22 (25.0%) cases were invasive cervical cancer in stage 1, of which 19 versus three were detected by VIA and Pap smear respectively (P = 0.001). VIA had higher sensitivity and lower specificity than Pap smear (60.2% versus 47.7%) and (41.9% versus 83.8%) respectively. The combination of VIA/Pap has better sensitivity and specificity than each independent test (82.6% and 92.2%).

CONCLUSION

The findings of this study showed that VIA has higher sensitivity and lower specificity compared to Pap smear, but a combination of both tests has greater sensitivity and specificity than each test independently. It indicates that VIA is useful for screening of cervical cancer in the primary health care setting in Sudan, but positive results need to be confirmed by colposcopy and biopsy.

Cervical cancer prevention in the 21st century: cost is not the only issue

The wide publicity related to human papillomavirus (HPV) vaccines has led to a sense that HPV vaccine programs are inevitable in both developed and developing countries, whereas 2 existing methods of screening-visual inspection with ascetic acid (VIA) and DNA testing-have received much less attention. These screening methods detect cervical lesions better than does the Papanicolaou test and allow immediate treatment, minimizing loss to follow-up. These advantages may outweigh the strengths of HPV vaccines. Priority should be given to improving screening coverage with VIA and DNA tests, focusing on women older than 30 years and underserved populations in all countries. This approach will save the lives of millions of women who have already been exposed to HPV and will develop cervical cancer during the next 20 years.

Barriers to follow-up of abnormal Papanicolaou smears among women in Leon, Nicaragua

Cervical cancer screening programmes only succeed when the coverage, screening, treatment and follow-up of any abnormal results are of high quality. This study investigates the screening coverage and the quality of the follow-up of cervical cancer screening of women in León, Nicaragua, as well as the factors affecting coverage and barriers to follow-up. Two hundred and thirty-four sexually active women attending a public health centre (54), a public health post (63), or the gynaecology department of the public HEODRA hospital (117), were invited to answer an orally administered questionnaire. The screening coverage of cervical cancer was calculated and the follow-up after finding an abnormal screening result was assessed. The coverage was 60.6% (95% confidence interval 54.4–66.8%). One hundred and sixty-eight women (87%) were informed about the results. Eighteen (10, 7%) of the women who were informed about the results, were advised to have follow-up and 12 (66, 7%) of them did. Barriers to follow-up were financial constraints, pregnancy, postponement and absence of instruments/electricity. This study shows that the screening coverage and cytology services are adequate, but that there is insufficient follow-up and/or treatment after an abnormal screening result. In order to achieve a lower incidence and mortality of cervical cancer, follow-up and treatment after an abnormal screening result need to be improved. A visual inspection with acetic acid may be an attractive alternative.

Impact of patient adherence and test performance on the cost-effectiveness of cervical cancer screening in developing countries: the case of Honduras

OBJECTIVE

We examined the impact of patient adherence and screening test performance on the cost-effectiveness of visual inspection with acetic acid (VIA) and Pap smears when used with colposcopy for diagnosis.

MATERIALS AND METHODS

Cost-effectiveness analysis was performed using computer modeling. The primary outcome was cancer prevalence in the 10 years after screening. Three hypothetical populations of 35-year-old women were compared: never-screened women, women screened with VIA, and women screened with Pap smears. We used community-based data from our screening program in Honduras to estimate screening test sensitivity and specificity, adherence to follow-up, and costs of screening and colposcopy services. Published data were used to model disease outcomes.

RESULTS

VIA was more sensitive than Pap smears (70% vs. 4%), less expensive (U.S. 0.23 dollars vs. 3.17 dollars), and the 2-vist VIA system had a higher rate of adherence to follow-up than the 3-visit Pap smear system (84% vs. 38%). VIA had a higher false-positive rate than Pap smears resulting in higher colposcopy referral rates, but more dysplasia was detected and treated. Cost-effectiveness analysis revealed that screening with VIA would cost U.S. 3,198 dollars per cancer case avoided and reduce cancer cases by 42%, versus U.S. 36,802 dollars and 2% for Pap screening. Although Pap smear quality was low in Honduras, sensitivity analysis showed that VIA was more cost-effective than Pap smears, even when test accuracy was equivalent.

CONCLUSION

In developing countries, systems barriers can limit the cost-effectiveness of Pap smears. VIA may be a cost-effective alternative for some resource-poor settings, although systems barriers, quality control, and feasibility issues must be considered.