Search

Colposcopy is the gold standard diagnostic tool for identifying cervical lesions. However, the accuracy of colposcopies depends on the proficiency of the colposcopist. Machine learning algorithms using an artificial intelligence (AI) system can quickly process large amounts of data and have been successfully applied in several clinical situations. This study evaluated the feasibility of an AI system as an assistive tool for diagnosing high-grade cervical intraepithelial neoplasia lesions compared to the human interpretation of cervical images. This two-centered, crossover, double-blind, randomized controlled trial included 886 randomly selected images. Four colposcopists (two proficient and two inexperienced) independently evaluated cervical images, once with and the other time without the aid of the Cerviray AI® system (AIDOT, Seoul, Republic of Korea). The AI aid demonstrated improved areas under the curve on the localization receiver-operating characteristic curve compared with the colposcopy impressions of colposcopists (difference 0.12, 95% confidence interval, 0.10–0.14, p < 0.001). Sensitivity and specificity also improved when using the AI system (89.18% vs. 71.33%; p < 0.001, 96.68% vs. 92.16%; p < 0.001, respectively). Additionally, the classification accuracy rate improved with the aid of AI (86.40% vs. 75.45%; p < 0.001). Overall, the AI system could be used as an assistive diagnostic tool for both proficient and inexperienced colposcopists in cervical cancer screenings to estimate the impression and location of pathologic lesions. Further utilization of this system could help inexperienced colposcopists confirm where to perform a biopsy to diagnose high-grade lesions. [ABSTRACT FROM AUTHOR]

Objective: To identify high‐risk HPV (hrHPV) genotypes associated with high‐grade vaginal intraepithelial neoplasia (VaIN), and evaluate the efficacy of various treatments for high‐grade VaIN. Methods: A retrospective review of outcomes among women diagnosed with VaIN after vaginal punch biopsy conducted due to an abnormal Papanicolaou smear or positive test for hrHPV at a hospital in Seoul, Korea, from 2013 to 2018. Logistic regression was used to identify variables associated with abnormal pathologic outcomes. Results: Among 389 women included in the study, 58 were diagnosed with high‐grade VaIN, including VaIN stage 2 (n = 37), VaIN stage 3 (n = 16), carcinoma in situ of the vagina (n = 3), and squamous carcinoma of the vagina (n = 2). In multivariate logistic regression analysis, risk of high‐grade VaIN and cancer was higher among women with abnormal cytology (odds ratio [OR], 1.88; 95% confidence interval [CI], 1.47–2.47), any hrHPV infection (OR, 8.75; 95% CI, 1.14–67.31), HPV16 infection (OR, 5.71; 95% CI, 2.57–12.68), or HPV31 infection (OR, 4.37; 95% CI, 1.45–13.11). Conclusion: The findings suggest that infection with hrHPV, especially HPV16 and HPV31, is significantly associated with high‐grade VaIN. Regarding treatment modalities, ablative or excisional treatments showed good efficacy against pathologic regression of high‐grade VaIN. Synopsis: Infection with high‐risk HPV genotypes, especially HPV16 and HPV31, was strongly associated with high‐grade vaginal intraepithelial neoplasia. [ABSTRACT FROM AUTHOR]

Objective: The aim of this study was to investigate the short-term efficacy and safety of Poly-gamma-glutamic acid (γ-PGA) and the immunologic changes in patients with CIN 1. Methods: Participants were randomly assigned to one of two groups and orally treated with placebo or 1,500 mg of γ-PGA for 4 weeks. The primary endpoint of the study was histologic regression rate of CIN 1 at 12 weeks between γ-PGA and control groups. The secondary endpoints were HPV clearance and change in immune responses. Result: From April 2013 to December 2015, 195 patients participated in the study. In the intention-to-treat analysis, 42 (42.4%) of the women who received γ-PGA experienced histologic remission versus 26 (27.1%) in the control group, with a statistically significant difference (p = 0.018). In the γ-PGA group, HPV clearance was found in 37 (43.5%) of 85 patients infected with high-risk HPV, showing a significant difference compared to the control group, in which 20 (26.7%) of 75 patients exhibited HPV clearance (p = 0.026). However, there was no significant difference between the two groups in the change of NK cell activity, major histocompatibility complex (MHC) class II CD8 count, and CD56 count. Conclusion: γ-PGA showed a short-term therapeutic effect on CIN 1 and high-risk HPV infection. It is a non-invasive, promising oral medication for women with these conditions. Trial registration: Clinical Trials . [ABSTRACT FROM AUTHOR]