Assessing generalizability of an AI-based visual test for cervical cancer screening.

A number of challenges hinder artificial intelligence (AI) models from effective clinical translation. Foremost among these challenges is the lack of generalizability, which is defined as the ability of a model to perform well on datasets that have different characteristics from the training data. We recently investigated the development of an AI pipeline on digital images of the cervix, utilizing a multi-heterogeneous dataset of 9,462 women (17,013 images) and a multi-stage model selection and optimization approach, to generate a diagnostic classifier able to classify images of the cervix into "normal", "indeterminate" and "precancer/cancer" (denoted as "precancer+") categories.

Squamocolumnar junction visibility, age, and implications for cervical cancer screening programs.

Visual assessment is currently used for primary screening or triage of screen-positive individuals in cervical cancer screening programs. Most guidelines recommend screening and triage up to at least age 65 years old. We examined cervical images from participants in three National Cancer Institute funded cervical cancer screening studies: ALTS (2864 participants recruited between 1996 to 1998) in the United States (US), NHS (7548 in 1993) in Costa Rica, and the Biopsy study (684 between 2009 to 2012) in the US.

Design of the HPV-automated visual evaluation (PAVE) study: Validating a novel cervical screening strategy.

Background: The HPV-automated visual evaluation (PAVE) Study is an extensive, multinational initiative designed to advance cervical cancer prevention in resource-constrained regions. Cervical cancer disproportionally affects regions with limited access to preventive measures. PAVE aims to assess a novel screening-triage-treatment strategy integrating self-sampled HPV testing, deep-learning-based automated visual evaluation (AVE), and targeted therapies.

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.

Validation in Zambia of a cervical screening strategy including HPV genotyping and artificial intelligence (AI)-based automated visual evaluation.

Background: WHO has recommended HPV testing for cervical screening where it is practical and affordable. If used, it is important to both clarify and implement the clinical management of positive results. We estimated the performance in Lusaka, Zambia of a novel screening/triage approach combining HPV typing with visual assessment assisted by a deep-learning approach called automated visual evaluation (AVE).

A rapid HPV typing assay to support global cervical cancer screening and risk-based management: A cross-sectional study.

The World Health Organization recommends human papillomavirus (HPV) testing for cervical screening. Extended genotyping can identify the highest-risk HPV-positive women. An inexpensive, rapid, mobile isothermal amplification assay (ScreenFire HPV RS test) was recently redesigned to yield four channels ordered by cancer risk (ie, hierarchical approach): HPV16, HPV18/45, HPV31/33/35/52/58 and HPV39/51/56/59/68.

Artificial intelligence-based image analysis in clinical testing: lessons from cervical cancer screening.

Novel screening and diagnostic tests based on artificial intelligence (AI) image recognition algorithms are proliferating. Some initial reports claim outstanding accuracy followed by disappointing lack of confirmation, including our own early work on cervical screening. This is a presentation of lessons learned, organized as a conceptual step-by-step approach to bridge the gap between the creation of an AI algorithm and clinical efficacy.

Design of the HPV-Automated Visual Evaluation (PAVE) Study: Validating a Novel Cervical Screening Strategy.

Objective: To describe the HPV-Automated Visual Evaluation (PAVE) Study, an international, multi-centric study designed to evaluate a novel cervical screen-triage-treat strategy for resource-limited settings as part of a global strategy to reduce cervical cancer burden. The PAVE strategy involves: 1) screening with self-sampled HPV testing; 2) triage of HPV-positive participants with a combination of extended genotyping and visual evaluation of the cervix assisted by deep-learning-based automated visual evaluation (AVE); and 3) treatment with thermal ablation or excision (Large Loop Excision of the Transformation Zone). The PAVE study has two phases: efficacy (2023-2024) and effectiveness (planned to begin in 2024-2025).

Use of risk-based cervical screening programs in resource-limited settings.

Cervical cancer screening and management in the U.S. has adopted a risk-based approach.

Estimating human papillomavirus vaccine efficacy from a single-arm trial: proof-of-principle in the Costa Rica Vaccine Trial.

Background: The World Health Organization recommends a 1- or 2-dose human papillomavirus (HPV) vaccination schedule for females aged 9 to 20 years. Studies confirming the efficacy of a single dose and vaccine modifications are needed, but randomized controlled trials are costly and face logistical and ethical challenges. We propose a resource-efficient single-arm trial design that uses untargeted and unaffected HPV types as controls.

REPRODUCIBLE AND CLINICALLY TRANSLATABLE DEEP NEURAL NETWORKS FOR CANCER 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.

Improving the repeatability of deep learning models with Monte Carlo dropout.

The integration of artificial intelligence into clinical workflows requires reliable and robust models. Repeatability is a key attribute of model robustness. Ideal repeatable models output predictions without variation during independent tests carried out under similar conditions.

Image Quality Classification for Automated Visual Evaluation of Cervical Precancer.

Image quality control is a critical element in the process of data collection and cleaning. Both manual and automated analyses alike are adversely impacted by bad quality data. There are several factors that can degrade image quality and, correspondingly, there are many approaches to mitigate their negative impact.

Inflammatory biomarkers and risk of breast cancer among young women in Latin America: a case-control study.

Background: Breast cancer incidence is increasing rapidly in Latin America, with a higher proportion of cases among young women than in developed countries. Studies have linked inflammation to breast cancer development, but data is limited in premenopausal women, especially in Latin America.

Methods: We investigated the associations between serum biomarkers of chronic inflammation (interleukin (IL)-6, IL-8, IL-10, tumor necrosis factor-α (TNF-α), interferon-γ (IFN-γ), leptin, adiponectin) and risk of premenopausal breast cancer among 453 cases and 453 matched, population-based controls from Chile, Colombia, Costa Rica, and Mexico.

Analysis of cervical HPV infections among unvaccinated young adult women to inform vaccine strategies in this age group: the Costa Rica HPV Vaccine Trial.

Introduction: Human papillomavirus (HPV) vaccines protect against incident HPV infections, which cause cervical cancer.

Objectives: We estimated the prevalence and incidence of HPV infections in young adult women to understand the impact of an HPV vaccination programme in this population.

Methods: We collected cervical specimens from 6322 unvaccinated women, aged 18-37 years, who participated in the Costa Rica Vaccine Trial and its long-term follow-up.

Consumption of industrial processed foods and risk of premenopausal breast cancer among Latin American women: the PRECAMA study.

Ultra-processed food intake has been linked to an increased risk of breast cancer in Western populations. No data are available in the Latin American population although the consumption of ultra-processed foods is increasing rapidly in this region. We evaluated the association of ultra-processed food intake to breast cancer risk in a case-control study including 525 cases (women aged 20-45 years) and 525 matched population-based controls from Chile, Colombia, Costa Rica and Mexico.

Performance of Cervical Screening a Decade Following HPV Vaccination: The Costa Rica Vaccine Trial.

Background: We investigated the impact of human papillomavirus (HPV) vaccination on the performance of cytology-based and HPV-based screening for detection of cervical precancer among women vaccinated as young adults and reaching screening age.

Methods: A total of 4632 women aged 25-36 years from the Costa Rica HPV Vaccine Trial were included (2418 HPV-vaccinated as young adults and 2214 unvaccinated). We assessed the performance of cytology- and HPV-based cervical screening modalities in vaccinated and unvaccinated women to detect high-grade cervical precancers diagnosed over 4 years and the absolute risk of cumulative cervical precancers by screening results at entry.

Different human papillomavirus types share early natural history transitions in immunocompetent women.

Necessary stages of cervical carcinogenesis include acquisition of a carcinogenic human papillomavirus (HPV) type, persistence associated with the development of precancerous lesions, and invasion. Using prospective data from immunocompetent women in the Guanacaste HPV Natural History Study (NHS), the ASCUS-LSIL Triage Study (ALTS) and the Costa Rica HPV Vaccine Trial (CVT), we compared the early natural history of HPV types to inform transition probabilities for health decision models. We excluded women with evidence of high-grade cervical abnormalities at any point during follow-up and restricted the analysis to incident infections in all women and prevalent infections in young women (aged <30 years).

The development of "automated visual evaluation" for cervical cancer screening: The promise and challenges in adapting deep-learning for clinical testing: Interdisciplinary principles of automated visual evaluation in cervical screening.

There is limited access to effective cervical cancer screening programs in many resource-limited settings, resulting in continued high cervical cancer burden. Human papillomavirus (HPV) testing is increasingly recognized to be the preferable primary screening approach if affordable due to superior long-term reassurance when negative and adaptability to self-sampling. Visual inspection with acetic acid (VIA) is an inexpensive but subjective and inaccurate method widely used in resource-limited settings, either for primary screening or for triage of HPV-positive individuals.

Moving towards a strategy to accelerate cervical cancer elimination in a high-burden city-Lessons learned from the Amazon city of Manaus, Brazil.

The World Health Organization Call to Eliminate Cervical Cancer resonates in cities like Manaus, Brazil, where the burden is among the world's highest. Manaus has offered free cytology-based screening since 1990 and HPV immunization since 2013, but the public system is constrained by many challenges and performance is not well-defined. We obtained cervical cancer prevention activities within Manaus public health records for 2019 to evaluate immunization and screening coverage, screening by region and neighborhood, and the annual Pink October screening campaign.

Rethinking Cervical Cancer Screening in Brazil Post COVID-19: A Global Opportunity to Adopt Higher Impact Strategies.

The World Health Organization global call to eliminate cervical cancer encourages countries to consider introducing or improving cervical cancer screening programs. Brazil's Unified Health System (SUS) is among the world's largest public health systems offering free cytology testing, follow-up colposcopy, and treatment. Yet, health care networks across the country have unequal infrastructure, human resources, equipment, and supplies resulting in uneven program performance and large disparities in cervical cancer incidence and mortality.

Deep Metric Learning for Cervical Image Classification.

Cervical cancer is caused by the persistent infection of certain types of the Human Papillomavirus (HPV) and is a leading cause of female mortality particularly in low and middle-income countries (LMIC). Visual inspection of the cervix with acetic acid (VIA) is a commonly used technique in cervical screening. While this technique is inexpensive, clinical assessment is highly subjective, and relatively poor reproducibility has been reported.