Cervical cancer screening aided by artificial intelligence, China.

Objective: To implement and evaluate a large-scale online cervical cancer screening programme in Hubei Province, China, supported by artificial intelligence and delivered by trained health workers. Methods: The screening programme, which started in 2017, used four types of health worker: sampling health workers, slide preparation technicians, diagnostic health workers and cytopathologists. Sampling health workers took samples from the women on site; slide preparation technicians prepared slides for liquid-based cytology; diagnostic health workers identified negative samples and classified positive samples based on the Bethesda System after cytological assessment using online artificial intelligence; and cytopathologists reviewed positive samples and signed reports of the results online. The programme used fully automated scanners, online artificial intelligence, an online screening management platform, and mobile telephone devices to provide screening services. We evaluated the sustainability, performance and cost of the programme. Results: From 2017 to 2021, 1 518 972 women in 16 cities in Hubei Province participated in the programme, of whom 1 474 788 (97.09%) had valid samples for the screening. Of the 86 648 women whose samples were positive, 30 486 required a biopsy but only 19 495 had one. The biopsy showed that 2785 women had precancerous lesions and 191 had invasive cancers. The cost of screening was 6.31 United States dollars (US$) per woman for the public payer: US$ 1.03 administrative costs and US$ 5.28 online screening costs. Conclusion: Cervical cancer screening using artificial intelligence in Hubei Province provided a low-cost, accessible and effective service, which will contribute to achieving universal cervical cancer screening coverage in China.

The artificial intelligence-assisted cytology diagnostic system in large-scale cervical cancer screening: A population-based cohort study of 0.7 million women.

BACKGROUND: Adequate cytology is limited by insufficient cytologists in a large-scale cervical cancer screening. We aimed to develop an artificial intelligence (AI)-assisted cytology system in cervical cancer screening program. METHODS: We conducted a perspective cohort study within a population-based cervical cancer screening program for 0.7 million women, using a validated AI-assisted cytology system. For comparison, cytologists examined all slides classified by AI as abnormal and a randomly selected 10% of normal slides. Each woman with slides classified as abnormal by either AI-assisted or manual reading was diagnosed by colposcopy and biopsy. The outcomes were histologically confirmed cervical intraepithelial neoplasia grade 2 or worse (CIN2+). RESULTS: Finally, we recruited 703 103 women, of whom 98 549 were independently screened by AI and manual reading. The overall agreement rate between AI and manual reading was 94.7% (95% confidential interval [CI], 94.5%-94.8%), and kappa was 0.92 (0.91-0.92). The detection rates of CIN2+ increased with the severity of cytology abnormality performed by both AI and manual reading (Ptrend  < 0.001). General estimated equations showed that detection of CIN2+ among women with ASC-H or HSIL by AI were significantly higher than corresponding groups classified by cytologists (for ASC-H: odds ratio [OR] = 1.22, 95%CI 1.11-1.34, P < .001; for HSIL: OR = 1.41, 1.28-1.55, P < .001). AI-assisted cytology was 5.8% (3.0%-8.6%) more sensitive for detection of CIN2+ than manual reading with a slight reduction in specificity. CONCLUSIONS: AI-assisted cytology system could exclude most of normal cytology, and improve sensitivity with clinically equivalent specificity for detection of CIN2+ compared with manual cytology reading. Overall, the results support AI-based cytology system for the primary cervical cancer screening in large-scale population.

Detection of lung cancer by automated sputum cytometry.

INTRODUCTION: Biomarkers may prove to be valuable tools to manage those at risk of lung cancer. Sputum analysis using DNA cytometry has shown promise, but an automated, objective sputum analysis test has yet to be developed. This study evaluated the performance characteristics of the LungSign test for lung cancer and compared them to conventional cytology METHODS: A multicenter validation trial was conducted in which sputum specimens were prospectively collected from subjects suspected of having lung cancer during diagnostic workup. Specimens were placed on slides, DNA stained using Feulgen thionin, and analyzed using an automated cytometry-based scoring system. Smears were also prepared from the sputum specimens, stained by the Papanicolaou procedure, and analyzed using conventional cytology. LungSign scores and conventional cytology results were compared with the subject diagnoses. RESULTS: A total of 1235 high-risk subjects were enrolled at nine clinical sites. Of 1123 subjects included for analysis, 370 were found to have lung cancer--a 33% prevalence. The a priori selected LungSign score threshold detected 40% of all lung cancers and 35% of stage I lung cancers with 91% specificity. Test performance was statistically equivalent across cancer stages, histologic types, and localizations for 330 analyzable lung cancer subjects. LungSign receiver operating characteristic area under the curve measure for the test was 0.692. Conventional cytology detected 16% of lung cancers with 99% specificity. CONCLUSIONS: DNA cytometry of sputum using the LungSign test detects stage I lung cancer and may provide a new tool to manage high-risk individuals.