目的探索并验证基于华为云ModelArts平台构建的深度学习模型在宫颈液基细胞学(liquid-based cytology,LBC)非典型细胞诊断中的应用价值,并评估其对不同诊断经验医师的辅助效果。方法回顾性分析2020年东莞市人民医院1044例宫颈脱落细胞...目的探索并验证基于华为云ModelArts平台构建的深度学习模型在宫颈液基细胞学(liquid-based cytology,LBC)非典型细胞诊断中的应用价值,并评估其对不同诊断经验医师的辅助效果。方法回顾性分析2020年东莞市人民医院1044例宫颈脱落细胞学标本,采用华为云ModelArts平台开发的人工智能(artifical intelligence,AI)辅助诊断系统与初级、中级、高级医师进行诊断比对,计算灵敏度、特异度、精确率、符合率、曲线下面积(area under the curve,AUC)等指标,评估AI系统的诊断效能及其对不同年资医师的辅助诊断效果。采用McNemar检验比较AI系统与人工诊断的差异。结果在1044例宫颈脱落细胞学标本中,AI系统在非典型细胞检出的灵敏度和特异度分别为98.96%和89.15%,均高于初级医师(81.95%和91.81%)。AI系统的总体诊断精确率为93.68%,显著高于初级医师(87.26%,P<0.001)。AI辅助可显著提高初级医师的诊断性能,灵敏度从80.1%提升至96.5%,特异度从85.6%提升至92.3%。结论本研究构建的AI辅助宫颈细胞学诊断系统性能优越,尤其能显著提高初级医师的诊断水平,具有良好的临床应用前景。展开更多
目的:本文主要探讨HPV E6/E7 mRNA与薄层液基细胞学检测(Thinprep Cytologic Test, TCT)结合在子宫颈癌及癌前病变筛查中的价值。方法:选取2018年1月~2022年12月期间在延安市人民医院就诊的均进行过HPV E6/E7 mRNA、TCT的宫颈异常患者67...目的:本文主要探讨HPV E6/E7 mRNA与薄层液基细胞学检测(Thinprep Cytologic Test, TCT)结合在子宫颈癌及癌前病变筛查中的价值。方法:选取2018年1月~2022年12月期间在延安市人民医院就诊的均进行过HPV E6/E7 mRNA、TCT的宫颈异常患者674例,以活检组织病理结果为金标准,分析不同检查方法对宫颈癌及癌前病变的筛查价值。结果:674例活检阳性的病例中:HPV E6/E7 mPNA检出阳性448例,TCT检出阳性371例;HPV E6/E7、TCT检查的诊断一致性为63.35%;与联合检测比较,HPV E6/E7 mRNA、TCT在宫颈癌前病变的检测中符合率均较低,差异均有统计学意义(P Objective: To analyze clinical application value of HPV E6/E7 mRNA and Thinprep cytologic test (TCT) detection in screening for cervical lesions. Methods: A total of 674 patients with cervical abnormalities who underwent HPV E6/E7 mRNA and TCT in Yan’an people’s Hospital from January 2018 to December 2022 were selected. With the histopathological results as the gold standard, the screening value of different examination methods for cervical cancer was analyzed. Results: Histopathological biopsies showed that the diagnostic concordance of HPV E6/E7 and TCT was 62.42%, and the sensitivity, specificity and accuracy of HPV E6/E7, TCT and colposcopy in detecting HSIL + SCC were all lower compared with the combined test, and the differences were statistically significant (P < 0.05). Conclusion The combination of HPV E6/E7 mPNA and TCT improve the value of screening for cervical cancer and may help in better clinical diagnosis and treatment.展开更多
文摘目的探索并验证基于华为云ModelArts平台构建的深度学习模型在宫颈液基细胞学(liquid-based cytology,LBC)非典型细胞诊断中的应用价值,并评估其对不同诊断经验医师的辅助效果。方法回顾性分析2020年东莞市人民医院1044例宫颈脱落细胞学标本,采用华为云ModelArts平台开发的人工智能(artifical intelligence,AI)辅助诊断系统与初级、中级、高级医师进行诊断比对,计算灵敏度、特异度、精确率、符合率、曲线下面积(area under the curve,AUC)等指标,评估AI系统的诊断效能及其对不同年资医师的辅助诊断效果。采用McNemar检验比较AI系统与人工诊断的差异。结果在1044例宫颈脱落细胞学标本中,AI系统在非典型细胞检出的灵敏度和特异度分别为98.96%和89.15%,均高于初级医师(81.95%和91.81%)。AI系统的总体诊断精确率为93.68%,显著高于初级医师(87.26%,P<0.001)。AI辅助可显著提高初级医师的诊断性能,灵敏度从80.1%提升至96.5%,特异度从85.6%提升至92.3%。结论本研究构建的AI辅助宫颈细胞学诊断系统性能优越,尤其能显著提高初级医师的诊断水平,具有良好的临床应用前景。
文摘目的:本文主要探讨HPV E6/E7 mRNA与薄层液基细胞学检测(Thinprep Cytologic Test, TCT)结合在子宫颈癌及癌前病变筛查中的价值。方法:选取2018年1月~2022年12月期间在延安市人民医院就诊的均进行过HPV E6/E7 mRNA、TCT的宫颈异常患者674例,以活检组织病理结果为金标准,分析不同检查方法对宫颈癌及癌前病变的筛查价值。结果:674例活检阳性的病例中:HPV E6/E7 mPNA检出阳性448例,TCT检出阳性371例;HPV E6/E7、TCT检查的诊断一致性为63.35%;与联合检测比较,HPV E6/E7 mRNA、TCT在宫颈癌前病变的检测中符合率均较低,差异均有统计学意义(P Objective: To analyze clinical application value of HPV E6/E7 mRNA and Thinprep cytologic test (TCT) detection in screening for cervical lesions. Methods: A total of 674 patients with cervical abnormalities who underwent HPV E6/E7 mRNA and TCT in Yan’an people’s Hospital from January 2018 to December 2022 were selected. With the histopathological results as the gold standard, the screening value of different examination methods for cervical cancer was analyzed. Results: Histopathological biopsies showed that the diagnostic concordance of HPV E6/E7 and TCT was 62.42%, and the sensitivity, specificity and accuracy of HPV E6/E7, TCT and colposcopy in detecting HSIL + SCC were all lower compared with the combined test, and the differences were statistically significant (P < 0.05). Conclusion The combination of HPV E6/E7 mPNA and TCT improve the value of screening for cervical cancer and may help in better clinical diagnosis and treatment.
文摘目的探讨在HPV阳性女性中,液基细胞学、DNA倍体分析及P16/Ki-67双染检测对宫颈癌前病变的分流作用。方法回顾性分析2021年5月至2022年12月在我院妇科行阴道镜及宫颈活检的妇女590例。患者高危人乳头瘤病毒(human papilloma virus,HPV)检测阳性,且行液基细胞学(liquid-based cytology,LBC)、DNA倍体分析、P16/Ki-67双染3种检查,对上述3种方法的灵敏度、特异性、受试者工作特征(receiver operating characteristic,ROC)曲线进行统计分析。结果液基细胞学、DNA倍体分析和P16/Ki-67双染3种筛查方法对宫颈癌前病变的灵敏度分别为84.2%、77.5%、76.4%,特异性分别为40.7%、49.2%、70.1%,曲线下面积(area under the curve,AUC)分别是0.625、0.634、0.733,其中,P16/Ki-67双染检测显著优于液基细胞学检查及DNA倍体分析(P<0.0001)。结论本研究认为,在HPV阳性女性中,P16/Ki-67双染检测的分流效果最佳。
