Scrutinizing high-risk patients from ASC-US cytology via a deep learning model.

BACKGROUND: Atypical squamous cells of undetermined significance (ASC-US) is the most frequent but ambiguous abnormal Papanicolaou (Pap) interpretation and is generally triaged by high-risk human papillomavirus (hrHPV) testing before colposcopy. This study aimed to evaluate the performance of an artificial intelligence (AI)-based triage system to predict ASC-US cytology for cervical intraepithelial neoplasia 2+ lesions (CIN2+). METHODS: More than 60,000 images were used to train this proposed deep learning-based ASC-US triage system, where both cell-level and slide-level information were extracted. In total, 1967 consecutive ASC-US Paps from 2017 to 2019 were included in this study. Histological follow-ups were retrieved to compare the triage performance between the AI system and hrHPV in 622 patients with simultaneous hrHPV testing. RESULTS: In the triage of women with ASC-US cytology for CIN2+, our system attained equivalent sensitivity (92.9%; 95% confidence interval [CI], 75.0%-98.8%) and higher specificity (49.7%; 95% CI, 45.6%-53.8%) than hrHPV testing (sensitivity: 89.3%; 95% CI, 70.6%-97.2%; specificity: 34.3%; 95% CI, 30.6%-38.3%) without requiring additional patient examination or testing. Additionally, the independence of this system from hrHPV testing (κ = 0.138) indicated that these 2 different methods could be used to triage ASC-US as an alternative way. CONCLUSION: This de novo deep learning-based system can triage ASC-US cytology for CIN2+ with a performance superior to hrHPV testing and without incurring additional expenses.

Atypical squamous cells of undetermined significance cervical cytology in the Chinese population: Age-stratified reporting rates, high-risk HPV testing, and immediate histologic correlation results.

BACKGROUND: The US American Society of Colposcopy and Cervical Pathology guidelines for cervical cancer screening have been largely adopted worldwide. Pooled high-risk human papillomavirus (hrHPV) testing has been routinely used to risk-stratify women who have atypical squamous cells of undetermined significance (ASC-US) cytology. However, it has been reported that there are distinguished differences in the distribution of hrHPV genotypes between the Chinese and American populations. METHODS: The objective of this study was to analyze the age-stratified reporting rates, hrHPV-positive rates, and genotyping by different cytology preparation methods and hrHPV testing assays, along with the immediate histopathologic correlation of ASC-US cytology, in the Chinese population. RESULTS: The ASC-US reporting rate of 1,597,136 Papanicolaou (Pap) tests was 4.2%, and the overall hrHPV-positive rate was 48.7% in the ASC-US cases. In total, 25,338 women with ASC-US Pap tests had immediate histologic follow-up, and the detection rate for cervical intraepithelial neoplasia 2 and higher lesions (CIN2+) was 7.1%, including 0.6% carcinomas. Among the women who underwent hrHPV testing, CIN2+ lesions were identified in 657 of 6154 (10.7%) who had hrHPV-positive results and in only 1.5% those who had hrHPV-negative results. Further genotyping analysis revealed that HPV types 16 and/or 18 were commonly identified genotypes among the Chinese women who had ASC-US cytology. CONCLUSIONS: This large-scale study demonstrated that the hrHPV-positive rate, the CIN2+ detection rate, and the distribution of hrHPV genotypes in Chinese women with ASC-US cytology were essentially consistent with those from the American population, further supporting that the current and newly released 2019 American Society of Colposcopy and Cervical Pathology guidelines should be applicable to the Chinese population.