Search

To identify candidate predictors for the prognosis of cervical intraepithelial neoplasia 2 (CIN2) lesions and evaluate the prognostic value of the local immune response.One hundred fifteen CIN2 patients were enrolled. The percentage of p16-, minichromosome maintenance complex component 2- or apolipoprotein B mRNA editing enzyme catalytic subunit 3G (APOBEC3G)-positive cells was determined immunohistochemically. Tumor-infiltrating lymphocytes (TILs) in intertumoral lesions were scored using an automated system. CIN3 disease progression and regression rates were estimated by the Kaplan-Meier method. A case-control study was conducted to screen CIN2 prognostic factors in 10 regression and 10 progression patients. Selected factors were examined in a cohort study to determine their prognostic value for CIN2.Among all participants, the cumulative progression and regression rates at 60 months were 0.477 and 0.510, respectively. In the case-control study, p16- and APOBEC3G-positive cells were higher in the progression group (p=0.043, p=0.023). Additionally, CD4CD4

Human papillomavirus subtypes are predictive indicators of cervical intraepithelial neoplasia (CIN) progression. While colposcopy is also an essential part of cervical cancer prevention, its accuracy and reproducibility are limited because of subjective evaluation. This study aimed to develop an artificial intelligence (AI) algorithm that can accurately detect the optimal lesion associated with prognosis using colposcopic images of CIN2 patients by utilizing objective AI diagnosis.We identified colposcopic findings associated with the prognosis of patients with CIN2. We developed a convolutional neural network that can automatically detect the rate of high-grade lesions in the uterovaginal area in 12 segments. We finally evaluated the detection accuracy of our AI algorithm compared with the scores by multiple gynecologic oncologists.High-grade lesion occupancy in the uterovaginal area detected by senior colposcopists was significantly correlated with the prognosis of patients with CIN2. The detection rate for high-grade lesions in 12 segments of the uterovaginal area by the AI system was 62.1% for recall, and the overall correct response rate was 89.7%. Moreover, the percentage of high-grade lesions detected by the AI system was significantly correlated with the rate detected by multiple gynecologic senior oncologists (r=0.61).Our novel AI algorithm can accurately determine high-grade lesions associated with prognosis on colposcopic images, and these results provide an insight into the additional utility of colposcopy for the management of patients with CIN2.

OBJECTIVE In cervical intraepithelial neoplasia (CIN), p16(INK4a) immunohistochemistry has been reported to be a useful diagnostic biomarker. However, limited information is available about the association between the p16(INK4a) immunohistochemistry and the outcomes of CIN. Here, we report p16(INK4a) immunohistochemistry as an effective biomarker to predict the outcomes of CIN. METHODS p16(INK4a) immunohistochemistry was performed in patients with CIN from January 2000 to August 2009. Among these patients, we have performed a retrospective analysis of the medical records to evaluate the outcome of CIN 1-2 and performed statistical analysis to determine the correlation between p16(INK4a) expression and the outcomes. We also performed HPV genotyping and analyzed the relation between the infecting human papillomavirus (HPV) genotype and the outcomes. RESULTS A total of 244 patients, including 82 with CIN 1, 60 with CIN 2, and 102 with CIN 3, were examined. The rate of p16(INK4a) overexpression increased with increasing CIN grade, 20.7% for CIN 1, 80.0% for CIN 2, and 89.2% for CIN 3, with significant differences between CIN 1 and CIN 2-3 group. In the 131 CIN 1-2 patients, the progression rate was significantly higher for the patients showing p16(INK4a) overexpression than for those not showing p16(INK4a) overexpression (p=0.005); the regression rate was also found to be significantly lower for the patients showing p16(INK4a) overexpression (p=0.003). High-risk HPV genotypes were detected in 73 patients (73.7%). Both progression and regression rates were not significantly different between the high-risk HPV-positive and HPV-negative groups (p=0.401 and p=0.381, respectively). CONCLUSION p16(INK4a) overexpression was correlated with the outcome of CIN 1-2, and p16(INK4a) is considered to be a superior biomarker for predicting the outcome of CIN 1-2 compared with HPV genotyping.

Objective The aim of this study was to investigate the risk and recurrence of early invasive adenocarcinoma of the cervix, and to determine whether non-radical methods of management could be performed. Methods The medical and histopathological records of 50 patients with early invasive adenocarcinoma of the cervix treated at Keio University Hospital between 1993 and 2005 were reviewed, and compared with the literature. Results The median follow-up period was 64.3 months. The depth of stromal invasion was ≤3 mm in 33 cases and >3 mm, but ≤5 mm in 17 cases. The horizontal spread was ≤7 mm in 25 cases and >7 mm in 25 cases. One of the 33 cases that had tumor volumes of ≤500 mm3, and three of the 17 cases with tumor volumes of >500 mm3 were positive for lymph node metastasis. When our data were combined with previously reported results, statistically significant differences were observed between the tumor volume and the frequency of pelvic lymph node metastasis/the rate of recurrence (p