Cervical cancer screening system TruScreen with graph neural network-based classification versus HPV DNA quantification in high-risk HPV-positive patients
Application of Artificial Intelligence Technology in Medical Data Analysis|更新时间:2025-10-22
|
Cervical cancer screening system TruScreen with graph neural network-based classification versus HPV DNA quantification in high-risk HPV-positive patients
Journal of Chongqing Medical UniversityVol. 48, Issue 12, Pages: 1501-1506(2023)
Hu Yanli,Zhou Leming,Huang Zhongxiu,et al.Cervical cancer screening system TruScreen with graph neural network-based classification versus HPV DNA quantification in high-risk HPV-positive patients[J].Journal of Chongqing Medical University,2023,48(12):1501-1506.
Hu Yanli,Zhou Leming,Huang Zhongxiu,et al.Cervical cancer screening system TruScreen with graph neural network-based classification versus HPV DNA quantification in high-risk HPV-positive patients[J].Journal of Chongqing Medical University,2023,48(12):1501-1506. DOI: 10.13406/j.cnki.cyxb.003390.
Cervical cancer screening system TruScreen with graph neural network-based classification versus HPV DNA quantification in high-risk HPV-positive patients
选取2022年1月至2023年5月于重庆大学附属黔江医院妇科门诊行宫颈癌高危型HPV检测阳性的400例患者为研究对象。对所有研究对象依次进行TS、宫颈细胞DNA定量、阴道镜下组织病理学检查。以组织病理检查为“金标准”,除采用TS系统已有模块外,基于图神经网络进行标识学习,提取特征,随后使用支持向量机(support vector machines,SVM)和随机森林(random forest,RF)等分类器进行分类,计算并比较 TS、宫颈细胞DNA定量筛查宫颈癌及癌前病变的灵敏度、特异度、受试者工作特征(receiver operating characteristic,ROC)曲线下面积(area under the curve,AUC)、阴性预测值、阳性预测值、与活检病理结果一致性检验统计量Kappa值。
To compare the effectiveness of TruScreen(TS) integrated with a graph neural network and human papillomavirus(HPV) DNA quantification in cervical precancer and cancer screening in high-risk HPV-positive patients.
Methods
2
We included 400 patients whotested positive for high-risk HPV subtypes at the Department of Gynecology,Qianjiang Hospital,Chongqing University from January 2022 to May 2023. All the patients underwent TS,HPV DNA quantification in cervical cells,and a colposcopy-directed biopsy. The biopsy pathology results were used as the gold standard. The TS system was combined with graph neural network-based representation learning and feature extraction and classification with support vector machine and random forest classifiers. We calculated and compared the sensitivity,specificity,area under the receiver operating characteristic curve(AUC),negative predictive value,positive predictive value,agreement with biopsy pathology (kappa value) of the modified TS system and HPV DNA quantification in cervical precancer and cancer screening.
Results
2
The sensitivity,specificity,AUC,negative predictive value,and positive predictive value of TS with graph neural network-based classification for cervical precancer and cancer screening were 93.75%,95.45%,0.97,98.18%,and 87.50%,respectively,which were higher than those of HPV DNA quantitative testing (81.25%,90.91%,0.92,96.15%,and 64.29%,respectively). The kappa coefficient of agreement of TS with graph neural network-based classification with biopsy pathology was 0.89,higher than 0.72 of HPV DNA quantitative testing with biopsy pathology. There was a significant difference in the AUC of TS with graph neural network-based classification and HPV DNA quantitative testing (
P
<
0.05).
Conclusion
2
TS with graph neural network-based classification has better performance in screening for cervical precancer and cancer in high-risk HPV-positive patients than HPV DNA quantitative testing,with high accuracy and reliability. It can be used as a simple and effective cervical cancer screening method.
Zhang YY , Li J , Niu YX , et al . The expression of CXC chemokine ligand 13 in cervical cancer and its effect on the proliferation and migration of cervical cancer cells [J ] . Chinese Journal of Gerontology , 2023 , 43 ( 10 ): 2534 - 2537
Miao HZ , Wu YT , Zhu YX . Analysis on the results and cost-effectiveness of cervical and breast cancer screening for rural women in Guangdong Province from 2017 to 2019 [J ] . J Pract Med , 2023 , 39 ( 13 ): 1709 - 1713 .
Ozdemir H , Serbetcioglu GC , Ayhan A . New screening method for cervical cancer - polar prob,TruScreen [J ] . Int J Reprod Contracept Obstet Gynecol , 2020 , 9 ( 5 ): 1900 .
Ma Y , Di JL , Bi H , et al . Analysis of the triage effect of TruScreen for human papillomavirus-positive women [J ] . Chin J Clin Obstet Gynecol , 2020 , 21 ( 4 ): 385 - 387 .
Wang BJ , Ma Q , Zhao XX , et al . Application value of TCT,HPV and TruScreen in screening cervical disease [J ] . J Pract Obstet Gynecol , 2019 , 35 ( 11 ): 856 - 859 .
Boronina A , Maksimenko V , Hramov AE . Convolutional neural network outperforms graph neural network on the spatially variant graph data [J ] . Mathematics , 2023 , 11 ( 11 ): 2515 .
Zhang YH , Xu YQ , Zhang Y . A graph neural network node classification application model with enhanced node association [J ] . Appl Sci , 2023 , 13 ( 12 ): 7150 .
Hu YT , Wang SY , Wu YM , et al . Slice-level vulnerability detection and interpretation method based on graph neural network [J ] . J Softw , 2023 , 34 ( 6 ): 2543 - 2561 .
Pham P , Nguyen LTT , Nguyen NT , et al . ComGCN:community-driven graph convolutional network for link prediction in dynamic networks [J ] . IEEE Trans Syst Man Cybern , 2022 , 52 ( 9 ): 5481 - 5493 .
Sun JY , Zheng W , Zhang QF , et al . Graph neural network encoding for community detection in attribute networks [J ] . IEEE Trans Cybern , 2022 , 52 ( 8 ): 7791 - 7804 .
Tang X , Zhang HY , Mou LC , et al . An unsupervised remote sensing change detection method based on multiscale graph convolutional network and metric learning [J ] . IEEE Trans Geosci Remote Sens , 2022 , 60 : 1 - 15 .
Chen F , Zhao YQ , Li TY , et al . Clinical value of TruScreen in early diagnosis of cervical cancer and precancerous lesions:a hospital-based multicenter study [J ] . Chin J Pract Gynecol Obstet , 2021 , 37 ( 3 ): 348 - 352 .
Wang Y , Wang D , Yeerjiang KAYM , et al . Screening effect analysis of self-sampling HPV test as an alternative method for cervical cancer primary screening in areas with poor health resources in Xinjiang [J ] . Prog Obstet Gynecol , 2023 , 32 ( 2 ): 90 - 94 .
Cheng J , Liu BB , Xu L , et al . Clinical value of cervical multipoint biopsy under colposcopy combined with endocervical curettage in diagnosing cervical lesions [J ] . J Mod Oncol , 2022 , 30 ( 21 ): 3964 - 3967 .
Yu T , Li ZW , Liu S , et al . Research progress on the prediction of lymph node metastasis risk by pathological factors of conization specimens of early-stage cervical cancer [J ] . J Mod Oncol , 2023 , 31 ( 11 ): 2161 - 2163 .
Du YS , Zhang DY , Zhang DD , et al . Analysis of screening effect of common cervical cancer screening methods in cervical adenocarcinoma in situ [J ] . J Mod Oncol , 2023 , 31 ( 8 ): 1518 - 1523 .