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 (P < 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.
Download full-text PDF |
Source |
|---|---|
| http://www.ncbi.nlm.nih.gov/pmc/articles/PMC7520355 | PMC |
| http://dx.doi.org/10.1002/cam4.3296 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
Delineation of reduced CTV2 on the basis of the characteristics and distribution of cervical lymph node metastasis in nasopharyngeal carcinoma.
BMC Cancer
January 2025
Department of Radiation Oncology, First Affiliated Hospital of Kunming Medical University, 295 Xichang Road, Kunming, 650032, P. R. China.
Introduction: The core objective of this study was to precisely locate metastatic lymph nodes, identify potential areas in nasopharyngeal carcinoma patients that may not require radiotherapy, and propose a hypothesis for reduced target volume radiotherapy on the basis of these findings. Ultimately, we reassessed the differences in dosimetry of organs at risk (OARs) between reduced target volume (reduced CTV2) radiotherapy and standard radiotherapy.
Methods And Materials: A total of 209 patients participated in the study.
Reverse-engineering the FLT3-PI3K/AKT axis to enhance TILs function and improve prognosis in ovarian and cervical cancers.
J Ovarian Res
January 2025
Department of Gynecology, Obstetrics and Gynecology Hospital of Fudan University, #128 Shenyang Road, Shanghai, 200090, People's Republic of China.
Background: Ovarian cancers (OC) and cervical cancers (CC) have poor survival rates. Tumor-infiltrating lymphocytes (TILs) play a pivotal role in prognosis, but shared immune mechanisms remain elusive.
Methods: We integrated single-cell RNA sequencing (scRNA-seq) and spatial transcriptomics (ST) to explore immune regulation in OC and CC, focusing on the PI3K/AKT pathway and FLT3 as key modulators.
An automatic cervical cell classification model based on improved DenseNet121.
Sci Rep
January 2025
Department of Biomedical Engineering, School of Life Science and Technology, Changchun University of Science and Technology, Changchun, 130022, China.
The cervical cell classification technique can determine the degree of cellular abnormality and pathological condition, which can help doctors to detect the risk of cervical cancer at an early stage and improve the cure and survival rates of cervical cancer patients. Addressing the issue of low accuracy in cervical cell classification, a deep convolutional neural network A2SDNet121 is proposed. A2SDNet121 takes DenseNet121 as the backbone network.
View Article and Find Full Text PDFHow can cervical screening meet the needs of vulnerable women? A qualitative comparative study with stakeholder perspectives from seven European countries.
BMJ Open
January 2025
University Research Clinic for Cancer Screening, Randers Regional Hospital, Randers, Denmark.
Objective: This study explored and compared stakeholder perspectives on enhancements to cervical cancer screening for vulnerable women across seven European countries.
Design: In a series of Collaborative User Boards, stakeholders were invited to collaborate on identifying facilitators to improve cervical cancer screening.
Setting: This study was part of the CBIG-SCREEN project which is funded by the European Union and targets disparities in cervical cancer screening for vulnerable women (www.
Racial and ethnic enrollment disparities in clinical trials leading to FDA approvals for gynecologic malignancies.
Am J Obstet Gynecol
January 2025
Division of Gynecologic Oncology, Mount Sinai Medical Center, Miami Beach, Florida, USA.
Background: Black women and other minorities have higher age adjusted incidence risk for cervical and endometrial cancer than White women. However, the extent of racial and ethnic disparities in clinical trial enrollment among studies performed mainly in North America and Europe for gynecologic malignancy is unknown.
Objective: This study analyzed enrollment rates by race/ethnicity in trials that led to Food and Drug Administration (FDA) approvals for gynecological cancers from 2010 to 2024.
Want AI Summaries of new PubMed Abstracts delivered to your In-box?
Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!