摘要
目的:比较基于人工智能(AI)的子宫内膜细胞医学图像分析系统(AI病理识别系统)在不同医疗机构诊断的准确性,从而评价其临床应用的同质化。方法:采用回顾性研究方法,选取西安交通大学第一附属医院(交大组)和西安大兴医院(大兴组)2021年9月至2023年5月因异常阴道流血或超声提示宫腔异常就诊患者的子宫内膜液基细胞学病理切片,各100例,分别由两家医院相同型号的AI病理识别系统阅片后报告结果,以患者的子宫内膜组织学病理结果为金标准,分析两组AI病理识别系统诊断的准确度、灵敏度和特异度。结果:交大组和大兴组AI病理识别系统的诊断准确度分别为93.0%、89.0%,灵敏度分别为87.8%、82.1%,特异度分别为96.6%、91.7%。两组AI病理识别系统的诊断准确度、灵敏度、特异度比较,差异均无统计学意义(P>0.05)。结论:基于AI病理识别系统在不同医疗机构应用的诊断准确度、灵敏度和特异度无明显差异,证实该系统临床应用同质化性能良好。
Objective:To compare the accuracy of AI-assisted medical imaging analysis system for endometrial cells in different medical institutions and evaluate their clinical homogenization.Methods:This retrospective study selected 100 endometrial liquid-based cytology pathology specimens from patients who visited the First Affiliated Hospital of Xi'an Jiaotong University(Jiaotong group)and Xi'an Daxing Hospital(Daxing group)from September 2021 to May 2023 due to abnormal vaginal bleeding or ultrasound-suggested cavity abnormalities.The accuracy,sensitivity and specificity of the two AI pathological recognition systems were analyzed based on the pathological results of the patient's endometrial tissue as the gold standard.Results:The diagnostic accuracy of the AI-assisted endometrial cell medical imaging analysis system in the Jiaotong group and the Daxing group was 93.0%and 89.0%,respectively.The sensitivity was 87.8%and 82.1%,respectively,and the specificity was 96.6%and 91.7%,respectively.There was no significant difference in diagnostic accuracy,sensitivity,and specificity between the two AI-assisted systems(P>0.05).Conclusion:The AI-assisted endometrial cell medical imaging analysis system shows homogenization in the diagnostic accuracy,sensitivity,and specificity when used in different medical institutions.
作者
尹盼月
安静
马志华
王怡然
王田田
王斌
王建六
李奇灵
YIN Panyue;AN Jing;MA Zhihua;WANG Yiran;WANG Tiantian;WANG Bin;WANG Jianliu;LI Qiling(Department of Obstetrics and Gynecology,the First Affiliated Hospital of Xi'an Jiaotong University,Shaanxi Xi'an 710061,China;Department of Obstetrics and Gynecology,Xi'an Daxing Hospital,Shaanxi Xi'an 710016,China;Department of Obstetrics and Gynecology,Peking University People's Hospital,Beijing 100000,China)
出处
《现代肿瘤医学》
CAS
2024年第2期296-299,共4页
Journal of Modern Oncology
基金
陕西省重点研发计划-重点项目(编号:2017ZDXM-SF-068)
西安交通大学第一附属医院临床研究重点项目(编号:XJTU1AF-CRF-2019-002)
陕西省技术创新引导专项(基金)项目(编号:2019QYPY-138)。
关键词
子宫内膜细胞学
人工智能
病理诊断
同质化
endometrial cytology
artificial intelligence
pathologic diagnosis
homogenization
