Accuracy and Efficiency of Deep-Learning-Based Automation of Dual Stain Cytology in Cervical Cancer Screening.

BACKGROUND: With the advent of primary human papillomavirus testing followed by cytology for cervical cancer screening, visual interpretation of cytology slides remains the last subjective analysis step and suffers from low sensitivity and reproducibility. METHODS: We developed a cloud-based whole-slide imaging platform with a deep-learning classifier for p16/Ki-67 dual-stained (DS) slides trained on biopsy-based gold standards. We compared it with conventional Pap and manual DS in 3 epidemiological studies of cervical and anal precancers from Kaiser Permanente Northern California and the University of Oklahoma comprising 4253 patients. All statistical tests were 2-sided. RESULTS: In independent validation at Kaiser Permanente Northern California, artificial intelligence (AI)-based DS had lower positivity than cytology (P < .001) and manual DS (P < .001) with equal sensitivity and substantially higher specificity compared with both Pap (P < .001) and manual DS (P < .001), respectively. Compared with Pap, AI-based DS reduced referral to colposcopy by one-third (41.9% vs 60.1%, P < .001). At a higher cutoff, AI-based DS had similar performance to high-grade squamous intraepithelial lesions cytology, indicating a risk high enough to allow for immediate treatment. The classifier was robust, showing comparable performance in 2 cytology systems and in anal cytology. CONCLUSIONS: Automated DS evaluation removes the remaining subjective component from cervical cancer screening and delivers consistent quality for providers and patients. Moving from Pap to automated DS substantially reduces the number of colposcopies and also achieves excellent performance in a simulated fully vaccinated population. Through cloud-based implementation, this approach is globally accessible. Our results demonstrate that AI not only provides automation and objectivity but also delivers a substantial benefit for women by reduction of unnecessary colposcopies.

Clinical Evaluation of Human Papillomavirus Screening With p16/Ki-67 Dual Stain Triage in a Large Organized Cervical Cancer Screening Program.

Importance: As cervical cancer screening transitions from Papanicolaou cytologic screening to primary human papillomavirus (HPV) testing worldwide, effective triage tests are needed to decide who among the HPV-positive women should receive further diagnostic evaluation to avoid unnecessary colposcopies and biopsies. Objective: To evaluate the performance of the p16/Ki-67 dual stain (DS) and HPV16/18 genotyping for the triage of HPV-positive women. Design, Setting, and Participants: A prospective observational study was conducted within the cervical cancer screening program at Kaiser Permanente Northern California of 3225 HPV-positive women undergoing HPV and Papanicolaou cytologic testing with a valid DS result from September 16 to October 31, 2015, with follow-up through December 31, 2018. Exposures: Human papillomavirus screening with partial genotyping and cytologic triage compared with DS triage. Main Outcomes and Measures: Cervical intraepithelial neoplasia grade 3 or more severe (CIN3+) and grade 2 or more severe (CIN2+), diagnosed within 3 years after sample collection. Results: A total of 3225 women (mean [SD] age, 37.9 [11.3] years) participated in the study. For triage of HPV-positive women with partial genotyping, DS showed better risk stratification for CIN3+ than did Papanicolaou cytologic testing, with women with positive DS results having a higher risk than women with positive Papanicolaou test results for CIN3+ (218 of 1818 [12.0%; 95% CI, 10.5%-13.5%] vs 219 of 2128 [10.3%; 95% CI, 9.0%-11.6%]; P = .005). Similarly, DS showed better risk stratification for CIN3+ compared with Papanicolaou cytologic testing in HPV-positive women, irrespective of genotyping. The greatest reassurance against CIN3+ was observed in HPV16/18-negative women with negative DS results, with a risk low enough to extend retesting intervals. Dual stain triage strategies required substantially fewer colposcopies per detection of CIN3+ compared with Papanicolaou cytologic testing, with a 32.1% (859 of 2677) reduction of colposcopies compared with the currently recommended triage strategy of HPV screening with Papanicolaou cytologic testing. Results for CIN2+ were very similar. Conclusions and Relevance: Triage of HPV-positive women with DS was superior to Papanicolaou cytologic testing in this study, demonstrating equal immediate detection of precancerous lesions and substantially reduced referral to colposcopy. These findings suggest that DS can safely replace Papanicolaou cytologic testing as a triage strategy for primary HPV screening, and that retesting intervals in HPV16/18-negative women with negative DS results can be safely extended to 3 years.