Background Deep learning has presented considerable potential and is gaining more importance in computer assisted diagnosis. As the gold standard for pathologically diagnosing cervical intraepithelial lesions and invasive cervical cancer, colposcopy-guided biopsy faces challenges in improving accuracy and efficiency worldwide, especially in developing countries. To ease the heavy burden of cervical cancer screening, it is urgent to establish a scientific, accurate and efficient method for assisting diagnosis and biopsy. Methods The data were collected to establish three deeplearning-based models. For every case, one saline image, one acetic image, one iodine image and the corresponding clinical information, including age, the results of human papillomavirus testing and cytology, type of transformation zone, and pathologic diagnosis, were collected. The dataset was proportionally divided into three subsets including the training set, the test set and the validation set, at a ratio of 8:1:1. The validation set was used to evaluate model performance. After model establishment, an independent dataset of high-definition images was collected to further evaluate the model performance. In addition, the comparison of diagnostic accuracy between colposcopists and models weas performed. Results The sensitivity, specificity and accuracy of the classification model to differentiate negative cases from positive cases were 85.38%, 82.62% and 84.10% respectively, with an AUC of 0.93. The recall and DICE of the segmentation model to segment suspicious lesions in acetic images were 84.73% and 61.64%, with an average accuracy of 95.59%. Furthermore, 84.67% of highgrade lesions were detected by the acetic detection model. Compared to colposcopists, the diagnostic system performed better in ordinary colposcopy images but slightly unsatisfactory in high-definition images. Implications The deep learning-based diagnostic system could help assist colposcopy diagnosis and biopsy for HSILs.
Cytology triage has been generally recommended for human papillomavirus (HPV)-positive women, but is highly dependent on well-trained cytologists. The present study was designed to explore whether HPV E6/E7 mRNA detection in cervical exfoliated cells can be a potential triage for HPV-positive women from a clinic-based population. Both the primary HPV testing and Papanicolaou (Pap) test were performed on all eligible HPV-positive women. HPV E6/E7 mRNA was detected by QuantiVirus HPV E6/E7 mRNA assay in cervical exfoliated cells. All HPV-positive women underwent colposcopy and further biopsy if indicated. The data were assessed by Pearson's Chi-squared test and the receiver operating characteristic curve. A total of 404 eligible HPV-positive women were enrolled. Positive rate of E6/E7 mRNA in high-grade squamous intraepithelial lesion (HSIL) cases was higher than that in low-grade squamous intraepithelial lesion (LSIL) or normal cases. There was no statistical difference found between mRNA and cytological testing with sensitivity (89.52% vs. 86.67%, P=0.671), specificity (48.96% vs. 48.96%, P=1.000), positive predictive value (39.00% vs. 38.24%, P=1.000), and negative predictive value (92.76% vs. 90.97%, P=0.678) for detecting ≥HSIL. HPV E6/E7 mRNA detection in cervical exfoliated cells shows the same performance as Pap triage for HSIL identification for HPV-positive women. Detection of HPV E6/E7 mRNA may be used as a new triage option for HPV-positive women.
Histological low-grade squamous intraepithelial lesion/cervical intraepithelial neoplasia grade 1 (LSIL/CIN1) preceded by normal or mildly abnormal cytology is recommended for conservative follow-up, with no separated management. In this study, we assessed the triage value of human papillomavirus (HPV) 16/18 genotyping in 273 patients with LSIL/CIN1. HPV16/18 genotyping was performed at baseline and follow-up was at 6-monthly intervals for up to 2 years. At each follow-up, women positive for cytology or high-risk HPV (hrHPV) were referred for colposcopy. Enrollment cytology, HPV16/18 genotyping, and questionnaire-obtained factors were linked to the 2-year cumulative progression rate. Univariate and multivariate analyses were performed taking into account time-to-event with Cox proportional hazard regression. The results showed that 190 cases (69.6%) regressed, 37 (13.6%) persisted, and 46 (16.8%) progressed. HPV16/18 positivity (hazard ratio (HR), 2.708; 95% confidence interval (CI), 1.432-5.121; P=0.002) is significantly associated with higher 2-year cumulative progression rate. Sub-analysis by enrollment cytology and age restricted the positive association among patients preceded by mildly abnormal cytology and aged 30 years or older. Immediate treatment is a rational recommendation for the high-risk subgroup, when good compliance is not assured.
Background Human papillomavirus (HPV) infection is the main cause of cervical cancer. Characteristics of HPV infections, including the HPV genotype and duration of infection, determine a patient’s risk of high-grade lesions. Risk quantification of cervical lesions caused by different HPV genotypes is an important component of evaluation of cervical lesion. Data and evidence are necessary to gain a deeper understanding of the pathogenicity of different HPV genotypes. The present study investigated the clinical characteristics of patients infected with single human papillomavirus (HPV) 53. Methods This retrospective study analyzed the clinical data of patients who underwent cervical colposcopy guided biopsy between October 2015 and January 2021. The clinical outcomes and the follow-up results of the patients with single HPV53 infection were described. Results 82.3% of the initial histological results of all 419 patients with single HPV53 infection showed negative (Neg). The number of patients with cervical intraepithelial neoplasia (CIN)1, CIN2, CIN3, vaginal intraepithelial neoplasia (VaIN)1, CIN1 + VaIN1, CIN1 + VaIN2, and CIN2 + VaIN2 was 45, 10, 2, 9, 6, 1, and 1, respectively. Cancer was not detected in any patient. When the cytology was negative for intraepithelial lesion or malignancy (NILM), atypical squamous cells of undetermined significance (ASC-US) or low-grade squamous intraepithelial lesion (LSIL), we observed a significant difference in the distribution of histological results (P < 0.05). 95 patients underwent follow-up with cytology according to the exclusion criteria. No progression of high-grade lesions was observed during the follow-up period of 3–34 months. Conclusions The lesion caused by HPV53 infection progressed slowly. The pathogenicity of a single HPV53 infection was low.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.