摘要
目的 评估宫颈液基薄层细胞学计算机辅助分析(CAA)技术在提高宫颈癌筛查准确性和筛查效率方面的应用潜力。方法 利用人工智能深度学习模型分析了22万例宫颈液基薄层细胞学图像,通过统计分析结果的准确性和分析方法的效率来评估宫颈液基薄层细胞学计算机辅助分析技术对宫颈癌筛查的应用潜力。宫颈液基细胞学诊断结果采用了2014年宫颈细胞学报告系统(TBS)的阳性分级标准(ASC-US级别及以上级别视为阳性)。结果 对比了三组不同的宫颈癌筛查方法的准确性和效率:病理医师的敏感度为96.80%,特异度为93.61%,准确率为95.21%;AI辅助分析的敏感度为98.60%,特异度为79.61%,准确率为89.11%;AI分析系统辅助病理医师阅片的敏感度为100.00%,特异度为95.74%,准确率为97.87%。研究结果表明与传统的人工镜下阅片诊断方法相比,宫颈液基薄层细胞学计算机辅助分析技术能显著提高病理医师的阅片准确性。在阅片时间上,22万例宫颈液基细胞学样本由三名病理医师共同完成阅片工作,累计耗时约11 000 h;人工智能AI分析系统分析耗时为3 663 h;人工智能AI分析辅助病理医师阅片耗时约5 500 h。从阅片耗时可知,人工智能AI分析辅助病理医师阅片方法比病理医师在镜下阅片的工作效率提升了一倍。结论 宫颈液基薄层细胞学计算机辅助分析技术在宫颈癌筛查中有重大的应用价值,能够有效提升宫颈癌筛查的准确性和效率,减轻病理医生的工作负荷。CAA技术结合病理医师的临床经验,可作为宫颈癌筛查中重要的辅助工具。
Objective To evaluate the potential of computer-aided analysis(CAA)technology for liquid-based thin-layer cytology in improving the accuracy and efficiency of cervical cancer screening.Methods Using artificial intelligence deep learning models,this study analyzed 220,000 images of liquid-based thin-layer cytology samples.The diagnostic outcomes and efficiency of the analysis methods were statistically evaluated.Cervical cytology diagnoses followed the 2014 Bethesda System(TBS),with positive results classified as ASC-US and above.Results The accuracy and efficiency of three different cervical cancer screening methods were compared.The sensitivity,specificity and accuracy of pathologists were 96.80%,93.61%and accuracy 95.21%,respectively;those of AI-assisted analysis were 98.60%,79.61%and 89.11%,respectively;and those of AI analysis system-assisted pathologist review were 100.00%,95.74%and 97.87%,respectively.The results indicate that compared to traditional manual microscopic review,computer-aided analysis significantly improves the accuracy of pathologists′reviews.Regarding review times,three pathologists required approximately 11000 hours to review all 220000 samples manually,while AI-only analysis took 3663 hours.AI-assisted review required approximately 5500 hours,doubling the efficiency compared to manual review.Conclusion Computer-aided analysis of liquid-based thin-layer cytology holds significant value in cervical cancer screening.It effectively enhances screening accuracy and efficiency,alleviating pathologists′workloads.By combining CAA technology with clinical experience,it can serve as an important auxiliary tool for cervical cancer screening.
作者
杨伟康
张燕
易利模
吴庆军
刘艳群
郭君
王嫚
凌晟荣
彭汝娇
索婷姣
向婷
YANG Wei-kang;ZHANG Yan;YI Li-mo;WU Qing-jun;LIU Yan-qun;GUO Jun;WANG Man;LING Sheng-rong;PENG Ru-jiao;SUO Ting-jiao;XIANG Ting(Department of Preventive Health Care,Shenzhen Longhua District Maternal and Child Health Hospital,Shenzhen 518109,Guangdong,China;不详)
出处
《广东医学》
2025年第4期495-501,共7页
Guangdong Medical Journal
基金
深圳市龙华区科技创新专项资金项目(社会公益科研项目资助类-医疗卫生项目)(2021031)。
关键词
宫颈癌筛查
计算机辅助分析
深度学习
宫颈液基薄层细胞学
诊断准确性
cervical cancer screening
computer-aided analysis
deep learning
liquid-based thin-layer cytology
diagnostic accuracy
