Is It Time to Move Beyond Visual Inspection With Acetic Acid for Cervical Cancer Screening?

Cost-effectiveness analysis of alternative screening strategies for the detection of cervical cancer among women in rural areas of Western Kenya

While the incidence of cervical cancer has dropped in high-income countries due to organized cytology-based screening programs, it remains the leading cause of cancer death among women in Eastern Africa. Therefore, the World Health Organization (WHO) now urges providers to transition from widely prevalent but low-performance visual inspection with acetic acid (VIA) screening to primary human papillomavirus (HPV) DNA testing. Due to high HPV prevalence, effective triage tests are needed to identify those lesions likely to progress and so avoid over-treatment. To identify the optimal cost-effective strategy, we compared the VIA screen-and-treat approach to primary HPV DNA testing with p16/Ki67 dual-stain cytology or VIA as triage. We used a Markov model to calculate the budget impact of each strategy with incremental quality-adjusted life years and incremental cost-effectiveness ratios (ICER) as the main outcome. Deterministic cost-effectiveness analyses show that the screen-and-treat approach is highly cost-effective (ICER 2469 Int$), while screen, triage, and treat with dual staining is the most effective with favorable ICER than triage with VIA (ICER 9943 Int$ compared with 13,177 Int$). One-way sensitivity analyses show that the results are most sensitive to discounting, VIA performance, and test prices. In the probabilistic sensitivity analyses, the triage option using dual stain is the optimal choice above a willingness to pay threshold of 7115 Int$ being cost-effective as per WHO standards. The result of our analysis favors the use of dual staining over VIA as triage in HPV-positive women and portends future opportunities and necessary research to improve the coverage and acceptability of cervical cancer screening programs.

Reproducible and clinically translatable deep neural networks for cervical screening

Cervical cancer is a leading cause of cancer mortality, with approximately 90% of the 250,000 deaths per year occurring in low- and middle-income countries (LMIC). Secondary prevention with cervical screening involves detecting and treating precursor lesions; however, scaling screening efforts in LMIC has been hampered by infrastructure and cost constraints. Recent work has supported the development of an artificial intelligence (AI) pipeline on digital images of the cervix to achieve an accurate and reliable diagnosis of treatable precancerous lesions. In particular, WHO guidelines emphasize visual triage of women testing positive for human papillomavirus (HPV) as the primary screen, and AI could assist in this triage task. In this work, we implemented a comprehensive deep-learning model selection and optimization study on a large, collated, multi-geography, multi-institution, and multi-device dataset of 9462 women (17,013 images). We evaluated relative portability, repeatability, and classification performance. The top performing model, when combined with HPV type, achieved an area under the Receiver Operating Characteristics (ROC) curve (AUC) of 0.89 within our study population of interest, and a limited total extreme misclassification rate of 3.4%, on held-aside test sets. Our model also produced reliable and consistent predictions, achieving a strong quadratic weighted kappa (QWK) of 0.86 and a minimal %2-class disagreement (% 2-Cl. D.) of 0.69%, between image pairs across women. Our work is among the first efforts at designing a robust, repeatable, accurate and clinically translatable deep-learning model for cervical screening.

CervicoXNet: an automated cervicogram interpretation network

Visual inspection with acetic acid (VIA) is a pre-cancerous screening program for low-middle-income countries (LMICs). Due to the limited number of oncology-gynecologist clinicians in LMICs, VIA examinations are performed mainly by medical workers. However, the inability of the medical workers to recognize a significant pattern based on cervicograms, VIA examination produces high inter-observer variance and high false-positive rate. This study proposed an automated cervicogram interpretation using explainable convolutional neural networks named "CervicoXNet" to support medical workers decision. The total number of 779 cervicograms was used for the learning process: 487 with VIA ( +) and 292 with VIA ( -). We performed data augmentation process under a geometric transformation scenario, such process produces 7325 cervicogram with VIA ( -) and 7242 cervicogram with VIA ( +). The proposed model outperformed other deep learning models, with 99.22% accuracy, 100% sensitivity, and 98.28% specificity. Moreover, to test the robustness of the proposed model, colposcope images used to validate the model's generalization ability. The results showed that the proposed architecture still produced satisfactory performance, with 98.11% accuracy, 98.33% sensitivity, and 98% specificity. It can be proven that the proposed model has been achieved satisfactory results. To make the prediction results visually interpretable, the results are localized with a heat map in fine-grained pixels using a combination of Grad-CAM and guided backpropagation. CervicoXNet can be used an alternative early screening tool with VIA alone.

Visual inspection intelligent robot technology for large infusion industry

The application of intelligent technology has realized the transformation of people’s production and lifestyle, and it has also promoted the development of the field of medicine. At present, the intensity of intelligence in the field of medicine is increasing. By using its cash methods and techniques combined with the mechanical field, this article proposes to use visual inspection technology to understand the fusion of the medical field and the mechanical field. It is helpful to analyze and solve objective problems such as low efficiency in current infusion and insufficient rigidity of large infusion plastic bottles. Drawing on the principles and laws of deep learning algorithms and neural networks, the technical research of intelligent robots for visual inspection is carried out to realize the intelligence of infusion robots. In the research accuracy of detection, the detection rate of standard particles higher than 85 µM has reached almost 100%, and the rate of 50 µM standard particles is lower and unstable. The detection effect of the control light bulb control was different, and the detection rate was between 50 and 80%, which was obviously worse than the detection robot effect. Therefore, the current research on the technology of intelligent robots is very important.

Automated Precancerous Lesion Screening Using an Instance Segmentation Technique for Improving Accuracy

Precancerous screening using visual inspection with acetic acid (VIA) is suggested by the World Health Organization (WHO) for low-middle-income countries (LMICs). However, because of the limited number of gynecological oncologist clinicians in LMICs, VIA screening is primarily performed by general clinicians, nurses, or midwives (called medical workers). However, not being able to recognize the significant pathophysiology of human papilloma virus (HPV) infection in terms of the columnar epithelial-cell, squamous epithelial-cell, and white-spot regions with abnormal blood vessels may be further aggravated by VIA screening, which achieves a wide range of sensitivity (49-98%) and specificity (75-91%); this might lead to a false result and high interobserver variances. Hence, the automated detection of the columnar area (CA), subepithelial region of the squamocolumnar junction (SCJ), and acetowhite (AW) lesions is needed to support an accurate diagnosis. This study proposes a mask-RCNN architecture to simultaneously segment, classify, and detect CA and AW lesions. We conducted several experiments using 262 images of VIA+ cervicograms, and 222 images of VIA-cervicograms. The proposed model provided a satisfactory intersection over union performance for the CA of about 63.60%, and AW lesions of about 73.98%. The dice similarity coefficient performance was about 75.67% for the CA and about 80.49% for the AW lesion. It also performed well in cervical-cancer precursor-lesion detection, with a mean average precision of about 86.90% for the CA and of about 100% for the AW lesion, while also achieving 100% sensitivity and 92% specificity. Our proposed model with the instance segmentation approach can segment, detect, and classify cervical-cancer precursor lesions with satisfying performance only from a VIA cervicogram.

Smartphone-Based Visual Inspection with Acetic Acid: An Innovative Tool to Improve Cervical Cancer Screening in Low-Resource Setting

Visual inspection with acetic acid (VIA) is recommended by the World Health Organization for primary cervical cancer screening or triage of human papillomavirus-positive women living in low-resource settings. Nonetheless, traditional VIA with the naked-eye is associated with large variabilities in the detection of pre-cancer and with a lack of quality control. Digital-VIA (D-VIA), using high definition cameras, allows magnification and zooming on transformation zones and suspicious cervical regions, as well as simultaneously compare native and post-VIA images in real-time. We searched MEDLINE and LILACS between January 2015 and November 2021 for relevant studies conducted in low-resource settings using a smartphone device for D-VIA. The aim of this review was to provide an evaluation on available data for smartphone use in low-resource settings in the context of D-VIA-based cervical cancer screenings. The available results to date show that the quality of D-VIA images is satisfactory and enables CIN1/CIN2+ diagnosis, and that a smartphone is a promising tool for cervical cancer screening monitoring and for on- and off-site supervision, and training. The use of artificial intelligence algorithms could soon allow automated and accurate cervical lesion detection.

Removing global barriers to cervical cancer prevention and moving towards elimination

Cervical cancer is a disease of inequality. The majority of cervical cancer cases can be prevented through vaccination against the human papillomavirus (HPV) (primary prevention) and screening and early treatment of precancerous lesions caused by HPV infections (secondary prevention), and it can be controlled if treated in early stages (tertiary prevention). However, significant gaps in access to care have shifted the burden of disease to resource-poor countries in Africa, Asia and Latin America. The recent World Health Organization’s Call to Action to eliminate cervical cancer is a unique opportunity to galvanize change and remove barriers to prevention and care.

Feasibility and Acceptability of Smartphone-Based Cervical Cancer Screening Among HIV-Positive Women in Western Kenya

PURPOSE

Adjunct cervical cancer screening methods are under evaluation to improve the diagnostic accuracy of human papillomavirus (HPV)-based screening in low- and middle-income countries. We evaluated the feasibility and acceptability of smartphone-based cervicography among HPV-positive women living with HIV (WLWH) in Western Kenya.

METHODS

HPV-positive WLWH of 25-49 years of age enrolled in a clinical trial (ClinicalTrials.gov identifier: NCT04191967) had digital images of the cervix taken using a smartphone by a nonphysician provider following visual inspection with acetic acid. All participants had colposcopy-directed biopsy before treatment. Cervical images were evaluated by three off-site colposcopists for quality, diagnostic utility, and assigned a presumed diagnosis. We determined the proportion of images rates as low, medium, or high quality, interobserver agreement using Cohen’s Kappa statistic, and the off-site colposcopist’s sensitivity and specificity for diagnosis of cervical intraepithelial neoplasia grade 2 or worse (CIN2+) compared with histopathology. Acceptability was evaluated using a questionnaire.

RESULTS

One hundred sixty-four HPV-positive WLWH underwent cervicography during the study period. Mean age was 37.3 years. Images from the first 94 participants were evaluated by off-site colposcopists, with a majority (70.9%) rated as high quality. Off-site colposcopists had a sensitivity ranging from 21.4% (95% CI, 0.06 to 0.43) to 35.7% (95% CI, 0.26 to 0.46) and a specificity between 85.5% (95% CI, 0.81 to 0.90) to 94.9% (95% CI, 0.92 to 0.98) for diagnosis of CIN2+ based compared with histopathology. The majority of women, 99.4%, were comfortable having an image of their cervix taken as part of screening.

CONCLUSION

Cervicography by a nonphysician provider as an adjunct to HPV-based screening among WLWH in a low- and middle-income country setting is feasible and acceptable. However, low sensitivity for diagnosis of CIN2+ by off-site expert colposcopists highlights the limitations of cervicography.

Diagnostic accuracy of novel folate receptor-mediated staining solution detection (FRD) for CIN2+: A systematic review and meta analysis

BACKGROUND

Early detection and diagnosis of high-grade cervical intraepithelial neoplasia grade 2 or higher (CIN2+) is critical for a good prognosis and appropriate treatment. The chief aim of our study was to evaluate the diagnostic performance of folate receptor-mediated staining solution detection (FRD) for CIN2+.

METHODS

We conducted a systematic review and meta-analysis by searching the PubMed and EMBASE databases for studies published until May 2020, which assessed the diagnostic accuracy of FRD, human papilloma virus (HPV) testing, and ThinPrep cytology test (TCT) for the detection of CIN2+. Bivariate models were used to compare the diagnostic performance of FRD, HPV, and TCT.

RESULTS

Six studies involving 2817 patients were included in this meta-analysis. The pooled specificity of FRD was higher than that of HPV and TCT for detecting CIN2+ (0.65, 0.12, and 0.39, respectively). The summary area under the receiver operating characteristic curve values using FRD, HPV, and TCT for detecting CIN2+ were 0.79, 0.95, and 0.77, respectively, indicating that FRD was superior to TCT. The diagnostic odds ratios of FRD, HPV, and TCT were 6 (95% CI: 5-7), 3 (95% CI: 2-5), and 3 (95% CI: 2-4), respectively, demonstrating that FRD had good diagnostic accuracy.

CONCLUSION

FRD showed good diagnostic accuracy and higher specificity than HPV and TCT for detecting CIN2+. Based on our results, we propose that FRD could be a candidate for cervical screening, especially in underdeveloped countries.

Addressing cervical cancer screening disparities through advances in artificial intelligence and nanotechnologies for cellular profiling

Almost all cases of cervical cancer are caused by the human papilloma virus (HPV). Detection of pre-cancerous cervical changes provides a window of opportunity for cure of an otherwise lethal disease when metastatic. With a greater understanding of the biology and natural course of high-risk HPV infections, screening methods have shifted beyond subjective Pap smears toward more sophisticated and objective tactics. This has led to a substantial growth in the breadth and depth of HPV-based cervical cancer screening tests, especially in developed countries without constrained resources. Many low- and middle-income countries (LMICs) have less access to advanced laboratories and healthcare resources, so new point-of-care (POC) technologies have been developed to provide test results in real time, improve the efficiency of techniques, and increase screening adoption. In this Review, we will discuss how novel decentralized screening technologies and computational strategies improve upon traditional methods and how their realized promise could further democratize cervical cancer screening and promote greater disease prevention.

Novel concepts in cervical cancer screening: a comparison of VIA, HPV DNA test and p16INK4a/Ki-67 dual stain cytology in Western Kenya

Background

Screening of unvaccinated women remains essential to mitigate the high morbidity/mortality of cervical cancer. Here, we compared visual inspection with acetic acid (VIA), recommended by WHO as the most cost-effective screening approach in LMICs, with HPV-based screening, and usage of p16^INK4a/Ki-67 dual stain cytology.

Methods

We prospectively enrolled women participating in a VIA-based cervical cancer screening program in two peri-urban health centers of Kenya. Consenting women had a VIA examination preceded by collection of a liquid-based cytology sample from the cervix stored in PreservCyt medium (Hologic®). Analysis of all samples included a hrHPV DNA test and evaluation of a p16^INK4a /Ki-67 (CINtecPLUS®) dual stained slide that was prepared using the ThinPrep® 2000 Processor and evaluated by a pathologist trained in the methodology.

Results

In 701 of a total of 800 women aged 18–64 years, all three investigations were performed and data could be analyzed. The HPV, VIA and dual stain cytology positivity were 33%, 7%, and 2% respectively. The HPV positivity rate of VIA positive cases was 32%. The five most common HPV types were HPV16, 52, 68, 58 and 35. The OR among HIV infected women of an HPV infection, VIA positivity and positive dual stain cytology were 2.6 (95%CI 1.5–4.3), 1.9 (95%CI 0.89–4.4) and 3.4 (95%CI 1.07–10.9) respectively. The sensitivity of VIA to detect a p16^INK4a/Ki-67 positive transforming infection was 13% (95%CI 2–38).

Conclusions

Primary HPV testing appears feasible and should be considered as a primary screening test also in LMICs. The poor sensitivity of VIA renders it unsuitable as a triage test for HPV positive women. The utility of p16^INK4a/Ki-67 dual stain cytology as a triage test for HPV positive women in LMICs should be further studied.

Introduction of HPV testing for cervical cancer screening in Central America: The Scale-Up project

The Scale-Up project introduced vaginal self-sampling and low-cost human papillomavirus (HPV) testing as the primary approach for cervical cancer screening in selected public health centers in Guatemala, Honduras, and Nicaragua. We evaluate the country-specific accomplishments in screening: target-coverage, triage, and treatment. Between 2015 and 2018, cervical cancer screening was offered to women at least 30 years of age. Triage of HPV-positive women was based on visual inspection with acetic acid or Pap. Aggregated data included total women screened, use of self-sampling, age, time elapsed since last screening, HPV results, triage tests, triage results, and treatment. A total of 231,741 women were screened for HPV, representing 85.8% of the target populations within the project. HPV positivity was lower in Guatemala (12.4%) compared to Honduras and Nicaragua (14.5% and 14.2%, respectively, p < 0.05). A follow-up triage test was completed for 84.2%, 85.8%, and 50.1% of HPV-positive women in Guatemala, Nicaragua, and Honduras, respectively. Of those with a positive triage test, 84.7%, 67.1%, and 58.8% were treated in Guatemala, Nicaragua, and Honduras, respectively. First-time screening was highest in Nicaragua (55.8%) where self-sampling was also widely used (97.1%). The Scale-Up project demonstrated that large-scale cervical cancer screening and treatment intervention in a high-burden, low-resource setting can be achieved. Self-sampling and ablative treatment were key to the project's achievements. Data monitoring, loss to follow-up, and triage methods of screen- positive women remain critical to full success.

Home-based HPV self-sampling assisted by a cloud-based electronic data system: Lessons learnt from a pilot community cervical cancer screening campaign in rural Ethiopia

Primary HPV testing and triage of HPV-positive women is an effective cervical cancer screening strategy. Such a multi-visit screening algorithm is also promising for community-based screening in resource-poor communities, provided a robust tracking system is in place.

A cervical cancer screening campaign was conducted in a rural community in Ethiopia. All women aged 25–65 years were offered genital self-sampling using the Evalyn Brush®. Samples were HPV-DNA-tested at a central laboratory. Key indicators were captured on tablet computers and linked by a cloud-based information system. HPV-positive women were examined at the local clinic using portable colposcopy, p16/Ki-67 dual stain cytology and biopsy examination. CIN2+ women were referred for LEEP to the referral hospital.

Of 749 enumerated age-eligible women 634 (85%, (95% CI 82–88)) consented to screening, 429 samples were adequate for HPV testing, giving a total testing coverage of 57% (95% CI 53–62). The hrHPV prevalence was 14% (95% CI 5–22), 72% (95% CI 60–84) attended the clinic for a triage examination. Home-based HPV-DNA self-sampling and clinic-based triage assisted by cloud-based information technology is feasible in rural Ethiopia. Key components of such strategy are broad community awareness, high competency of community workers, and establishment of an adequate self-sampling and HPV-DNA testing platform.

Advances in technologies for cervical cancer detection in low-resource settings

Introduction: Cervical cancer mortality rates remain high in low- and middle-income countries (LMICs) and other medically underserved areas due to challenges with implementation and sustainability of routine screening, accurate diagnosis, and early treatment of preinvasive lesions. Areas covered: In this review, we first discuss the standard of care for cervical cancer screening and diagnosis in high- and low-resource settings, biomarkers that correlate to cervical precancer and cancer, and needs for new tests. We review technologies for screening and diagnosis with a focus on tests that are already in use in LMICs or have the potential to be adapted for use in LMICs. Finally, we provide perspectives on the next five years of technology development for improved cervical cancer screening and diagnosis in LMICs. Expert opinion: Innovation toward improved molecular and imaging tests is needed to enable effective, affordable see-and-treat approaches to detect and treat cervical precancer in a single visit. Current molecular tests remain too complex and/or costly for widespread use. Especially with imaging tests, decision support may improve performance of new technologies.

Performance of careHPV, hybrid capture 2 and visual inspection with acetic acid for detection of high-grade cervical lesion in Tanzania: A cross-sectional study

Objective

To examine the test performance of careHPV, Hybrid Capture2 (HC2) and visual inspection with acetic acid (VIA) for detection of cytologically diagnosed high-grade cervical lesions or cancer (HSIL+).

Design

Cross-sectional study.

Setting

Ocean Road Cancer Institute (ORCI) and Kilimanjaro Christian Medical Center (KCMC), Tanzania.

Population

Women attending routine cervical cancer screening.

Method

We enrolled 4080 women (25–60 years) in the study. The women were interviewed on lifestyle habits, and tested for HIV. A cervical specimen for careHPV testing (performed at ORCI and KCMC), and a liquid-based cytology sample for HPV DNA detection using HC2 (performed at Tuebingen University Hospital, Germany) and for cytology assessment (performed at Vejle Hospital, Denmark) were obtained at a gynecological examination. Subsequently, VIA was performed. With cytology as gold standard, the sensitivity and specificity of careHPV, HC2, and VIA for detection of HSIL+ were calculated.

Results

Altogether, 23.6% had a positive careHPV test, 19.1% had positive HC2 test, and 6.3% had a positive VIA test. The sensitivity/specificity was 88.9%/78.9% for careHPV and 91.1%/83.7%, for HC2. VIA showed a low sensitivity of 31.1% but a high specificity (94.6%) for detection of HSIL+. The sensitivity of careHPV, HC2 and VIA was higher among younger women, and among HIV positive women. VIA triage of careHPV positive women improved specificity, but sensitivity dropped to 27%.

Conclusion

Our results confirm the low sensitivity of VIA for detection of HSIL+ and further document that careHPV test is promising as a primary screening method for cervical-cancer prevention in low-resource regions. A suitable triage test has to be identified.

Reimbursement Incentives to Improve Adherence to Follow-Up of Cervical Cancer Cytology Screening Results in Peru

OBJECTIVE

The purpose of this study was to determine Peruvian women's attitudes toward novel reimbursement incentives used to improve adherence to obtaining cervical cytology test results.

MATERIALS AND METHODS

Women presenting for cervical cancer screening in Peru completed a 34-item Investigational Review Board-approved questionnaire. The questionnaire determined their attitudes toward various reimbursement incentives to improve adherence to obtaining cervical cytology results. Descriptive statistics, generalized linear models, and Kruskal-Wallis tests were used in the analyses.

RESULTS

Completed questionnaires were available for 997 women. Most women (51%) would be more likely to return for their Pap result if an incentive was provided, 79% (759/956) agreed that they would pay for the Pap test, and 51% (402/859) would be willing to pay 10 Soles or less. Quechua-speaking women considered follow-up more difficult (p < .0001) but were less likely to return for their Pap results (p < .0001), pay for the Pap test (p < .0001), and afford paying more than 5 Soles (p < .0001) than women who spoke Spanish or both languages. More women who earn 1000 Soles/year or less would likely return if incentivized (p < .0001), felt the incentive would help them remember to return (p = .0047), and would be willing to pay whether there was a rebate (p = .010) as compared with women earning more money.

CONCLUSIONS

A reimbursement incentive program designed to improve follow-up of cervical cytology test results was acceptable to most Peruvian women. Such a behavioral-modifying program may improve patient follow-up after cervical cytology testing. Implementation may reduce the morbidity and mortality of cervical cancer in remote regions of the country.

What is needed now for successful scale-up of screening?

Effective screening for pre-cancerous lesions of the cervix is the only protective intervention that can be offered to women that have not had the opportunity to be vaccinated. Elimination goals are being developed so that by 2030, 70% of women aged 35–45 years should have been screened at least once in a lifetime and 90% of all detected lesions should have been treated. These goals focus on a substantial reduction of cervical cancer burden in low- and middle-income countries (LMICs). Scaling-up screening in these settings may be substantially improved by using self-sampling (SS), human papillomavirus (HPV) testing, and managing screened-positive women with accessible treatment. The implementation of these tools requires minimal health information data for traceability, provider training, community education, operational management and quality control. Cost-effective algorithms tailored to country needs can greatly impact the burden of disease in a limited number of years.

[Use of human papilloma virus testing in primary cervical cancer screening in rural Madagascar]

BACKGROUND

Testing for high-risk human papilloma virus (HR-HPV) is an effective approach to the prevention of cervical cancer. This study in the Atsinanana area of Madagascar aimed to compare the management of women screened by visual inspection after coloration with acetic acid (VIA) and the management of women screened by HPV with VIA as a triage test.

METHOD

During the last two screening campaigns, the first patients (between 28 and 120 women par center) were sampled using a dry swab, just before the acetic acid application, to test 14 genotypes of HR-HPV using Roche Diagnostics Cobas^® Test. We compared current management practices based on primary VIA to those that would have been implemented if the clinician had followed the recommendations of the World Health Organization for HPV-based primary screening. We used a regression Poisson model with random effect and robust variance.

RESULTS

Among the 250 screened-women, 28 (11.2%) had acidophilic lesions of the uterine cervix or suspected lesions of invasive cancer (IVA +). The HPV test was positive in 62 cases (24.8%). The HPV-based screening strategy would have reduced by 52% the number of women needing thermo-coagulation treatment: 24 women (9.6%) with primary VIA-based screening vs. 13 women (5.2%) with primary HPV-based screening; RR: 0.52 and 95%CI: 0.27-1.02. The diagnosis of severe dysplastic lesion or invasive cancer would not have changed.

CONCLUSION

Primary HPV-based screening is a strategy that could be useful for low-resource countries like Madagascar. It would reduce the rate of false positives and unnecessary treatments compared to the current strategy based on primary IVA. The questions of the feasibility and cost-benefit of this strategy should be further explored.