Oktar O, et al. J Gynecol Oncol. 2023 Dec;35:e39. https://doi.org/10.3802/jgo.2024.35.e39

Objectives: To evaluate the interobserver agreement and diagnostic accuracy of ovarian-adnexal reporting and data system magnetic resonance imaging (O-RADS MRI) and applicability to machine learning. Methods: Dynamic contrast-enhanced pelvic MRI examinations of 471 lesions were retrospectively analysed and assessed by 3 radiologists according to O-RADS MRI criteria. Radiomic data were extracted from T2 and post-contrast fat-suppressed T1-weighted images. Using these data, an artificial neural network (ANN), support vector machine, random forest, and naive Bayes models were constructed. Results: Among all readers, the lowest agreement was found for the O-RADS 4 group (kappa: 0.669; 95% confidence interval [CI] 0.634-0.733), followed by the O-RADS 5 group (kappa: 0.709; 95% CI 0.678-0.754). O-RADS 4 predicted a malignancy with an area under the curve (AUC) value of 74.3% (95% CI 0.701-0.782), and O-RADS 5 with an AUC of 95.5% (95% CI 0.932-0.972) (P < .001). Among the machine learning models, ANN achieved the highest success, distinguishing O-RADS groups with an AUC of 0.948, a precision of 0.861, and a recall of 0.824. Conclusion: The interobserver agreement and diagnostic sensitivity of the O-RADS MRI in assigning O-RADS 4-5 were not perfect, indicating a need for structural improvement. Integrating artificial intelligence into MRI protocols may enhance their performance. Advances in knowledge: Machine learning can achieve high accuracy in the correct classification of O-RADS MRI. Malignancy prediction rates were 74% for O-RADS 4 and 95% for O-RADS 5.

Objectives: Persistent Human Papillomavirus (HPV) infection in the cervix and the preinvasive lesions it causes are significant risk factors for cervical cancer. Therefore, a treatment strategy is necessary to facilitate the clearance of HPV and prevent the progression of preinvasive lesions without causing cervical tissue destruction. This study aimed to evaluate the effectiveness of a vaginal adsorbent gel composed of a hydroxyethyl cellulose matrix formulation containing dispersed silicon dioxide, antioxidant sodium selenite, deflamin, and citric acid in patients with HPV infection. Methods: The study was designed as a retrospective cohort study and involved 449 women infected with HPV. For the purposes of the study, the patients were divided into two groups: the treatment group (TG) comprised 207 patients who used the vaginal gel daily for a period of three months, while the control group (CG), consisting of 242 patients, received no treatment under an “active surveillance” protocol. The study’s endpoints encompassed the domains of cytology, histology, and HPV clearance. Results: The regression rate of smear pathologies was 24.8% in the control group and 29.0% in the group using the vaginal adsorbent gel. In the first year, the histological regression rate in cervical biopsies was 49.3% in the treatment group and 19.4% in the control group, with a significant difference between groups (p < 0.001). Moreover, the clearance rate of HPV types was found to be significantly higher in the group using the vaginal adsorbent gel. Conclusions: The findings of this study suggest that the outpatient treatment approach can effectively prevent the oncogenic progression of cervical dysplasia. This alternative method has been shown to be efficacious in preventing the progression of cervical dysplasia and promoting regression. Furthermore, the efficacy of this gel in eradicating HPV has been demonstrated within a 12-month period.

Background: The aim of this study was to evaluate the cervical regeneration process following monopolar electrosurgical conization (MESC), using a multimodal approach including ultrasonographic, cytologic, colposcopic, and histologic assessments, and to determine the relationship between the extent of excision and the capacity for cervical tissue regeneration. Methods: This prospective observational study included 28 patients who underwent MESC due to abnormal cervical cytology or biopsy-confirmed cervical intraepithelial neoplasia. Preoperative, postoperative one month and six month cervical measurements were obtained using two-dimensional transvaginal ultrasonography. Monthly colposcopic evaluations were conducted, cervical biopsies were taken at the third month, and a cytological assessment was performed at the sixth month. Cervical volume and length regeneration were calculated and analyzed in relation to the dimensions of the excised cone. Regeneration percentages and their correlations with excised tissue dimensions were evaluated using paired t-tests and Pearson correlation analysis. Results: Mean cervical volume and length regeneration rates at six months were 84.61% ± 5.64 and 86.36% ± 3.33, respectively. The transformation zone was histologically visible in 32.1% of patients at three months and cytologically in 75.9% at six months. An inverse correlation was observed between both cone volume and length and cervical regeneration (p < 0.005). Patients with larger preoperative cervical dimensions exhibited a higher regenerative capacity. Positive surgical margins were found in only one patient (3.4%), and no high-grade cytologic abnormalities were noted at follow-up. Conclusions: MESC may enable substantial cervical regeneration within six months. Larger excisions impair healing and delay transformation zone reformation, which may inform the optimal timing for initiating gynecological and colposcopic examinations, as well as for performing cervical interventions when indicated.

Aims: To evaluate the diagnostic performance of the real time shear-wave elastography in patients with endometrial cancer in terms of tumor grade and myometrial invasion depth preoperatively. Methods: In this prospective observational study, forty-eight women who were diagnosed with endometrioid type endometrium cancer in our gynecologic oncology clinic of a tertiary hospital between September 2020-January 2021 in Turkey. All patients underwent an ultrasonographic shear-wave measurements. Mean shear-wave values were measured from the tumor itself. Mean elasticity values were assessed in terms of tumor grade and myometrial invasion depth. Results: The median [%25-%75] shearwave value of the participants was 29.45kPa (5.02-167.21). Shear-wave value for grade 3 endometrial cancer showed a statistically significant difference compared to grade 1 and 2 shear-wave values (p0.05). ROC curve analysis showed significant results to determine the myometrial invasion depth and grade 3 endometrial cancer with the mean shear-wave cut-off values of 28.29 kPa and 57 kPa respectively (p<0.001). Conclusion: Real-time shear-wave elastography is a promising tool to predict the grade 3 tumors and deep myometrial invasion in endometrial cancer patients.