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

Abstract

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.

The Role of AI in Cervical Cancer Screening

“…Without going into too many details, which are published elsewhere [21], our study showed high agreement rate for normal cytology grade between AI and manual reading. We showed that well-"trained AI system" can accurately classify normal cytology.…”

Methodologies of Primary HPV Testing Currently Applied for Cervical Cancer Screening

“…This technique relies on deep learning algorithms that have been developed in order to deal with a large amount data, to segment cytoplasm, and detect cervical dysplasia [ 72 ]. Even though cytological readings assisted by artificial intelligence have been shown to have similar accuracy as cytological analyses performed by capable cytologists, they are still in the early stages and require further investigation before they can be reliably used in screening programs [ 72 , 76 ]. Similarly, with DNA methylation and biomarker detection, large-scale and long-term prospective studies are required to clarify their role in screening for cervical cancer.…”

Cervical cancer: Epidemiology, risk factors and screening

“…In recent years, with the rapid development of science and technology, the application of artificial intelligence (AI) based products is booming. In cervical cancer prevention and control, AI also showed to be promising in cytology-based screening and colposcopy examination based on the image pattern recognition ( 59 , 60 ). These AI-based technology or system can intelligently identify lesions and assist medical staff in clinical examination and diagnosis which could alleviate difficulties in diagnosis in primary clinics.…”