A public health approach to cervical cancer screening in Africa through community-based self-administered HPV testing and mobile treatment provision
Authors: Nakalembe, Miriam; Makanga, Philippa; Kambugu, Andrew; Laker-Oketta, Miriam; Huchko, Megan J.; Martin, Jeffrey
The World Health Organization (WHO) refers to cervical cancer as a public health problem, and sub-Saharan Africa bears the world's highest incidence. In the realm of screening, simplified WHO recommendations for low-resource countries now present an opportunity for a public health approach to this public health problem. We evaluated the feasibility of such a public health approach to cervical cancer screening that features community-based self-administered HPV testing and mobile treatment provision. In two rural districts of western-central Uganda, Village Health Team members led community mobilization for cervical cancer screening fairs in their communities, which offered self-collection of vaginal samples for high-risk human papillomavirus (hrHPV) testing. High-risk human papillomavirus-positive women were re-contacted and referred for treatment with cryotherapy by a mobile treatment unit in their community. We also determined penetrance of the mobilization campaign message by interviewing a probability sample of adult women in study communities about the fair and their attendance. In 16 communities, 2142 women attended the health fairs; 1902 were eligible for cervical cancer screening of which 1892 (99.5%) provided a self-collected vaginal sample. Among the 393 (21%) women with detectable hrHPV, 89% were successfully contacted about their results, of which 86% returned for treatment by a mobile treatment team. Most of the women in the community (93%) reported hearing about the fair, and among those who had heard of the fair, 68% attended. This public health approach to cervical cancer screening was feasible, effectively penetrated the communities, and was readily accepted by community women. The findings support further optimization and evaluation of this approach as a means of scaling up cervical cancer control in low-resource settings.
Artificial intelligence-assisted cytology for detection of cervical intraepithelial neoplasia or invasive cancer: A multicenter, clinical-based, observational study
Authors: Bao, Heling; Bi, Hui; Zhang, Xiaosong; Zhao, Yun; Dong, Yan; Luo, Xiping; Zhou, Deping; You, Zhixue; Wu, Yinglan; Liu, Zhaoyang; Zhang, Yuping; Liu, Juan; Fang, Liwen; Wang, Linhong
Objective. Artificial intelligence (AI) could automatedly detect abnormalities in digital cytological images, however, the effect in cervical cancer screening is inconclusive. We aim to evaluate the performance of AI-assisted cytology for the detection of histologically cervical intraepithelial lesions (CIN) or cancer. Methods. We trained a supervised deep learning algorithm based on 188,542 digital cytological images. Between Mar 13, 2017, and Oct 20, 2018, 2145 referral women from organized screening were enrolled in a multicenter, clinical-based, observational study. Cervical specimen was sampled to generate two liquid-based slides: one random slide was allocated to AI-assisted reading, and the other to manual reading conducted by skilled cytologists from senior hospital and cytology doctors from primary hospitals. HPV testing and colposcopy-directed biopsy was performed, and histological result was regarded as reference. We calculated the relative sensitivity and relative specificity of Al-assisted reading compared to manual reading for CIN2+. This trial was registered, number ChiCTR2000034131. Results. In the referral population, Al-assisted reading detected 92.6% of CIN 2 and 96.1% of CIN 3+, significantly higher than or similar to manual reading. AI-assisted reading had equivalent sensitivity (relative sensitivity 1.01, 95%CI, 0.97-1.05) and higher specificity (relative specificity 1.26, 1.20-1.32) compared to skilled cytologists; whereas higher sensitivity (1.12, 1.05-1.20) and specificity (1.36, 1.25-1.48) compared to cytology doctors. In HPV-positive women, AI-assisted reading improved specificity for CIN1 or less at no expense of reduction of sensitivity compared to manual reading. Conclusions. AI-assisted cytology may contribute to the primary cytology screening or triage. Further studies are needed in general population. (C) 2020 Published by Elsevier Inc.