Colposcopy is a test performed to detect precancerous lesions of cervical cancer. Since cervical cancer progresses slowly, finding and treating precancerous lesions helps prevent cervical cancer. In particular, it is clinically important to detect high-grade squamous intraepithelial lesions (HSIL) that require surgical treatment among precancerous lesions of cervix. There have been several studies using convolutional neural network (CNN) for classifying colposcopic images. However, no studies have been reported on using the segmentation technique to detect HSIL. In present study, we aimed to examine whether the accuracy of a CNN model in detecting HSIL from colposcopic images can be improved when segmentation information for acetowhite epithelium is added. Without segmentation information, ResNet-18, 50, and 101 achieved classification accuracies of 70.2%, 66.2%, and 69.3%, respectively. The experts classified the same test set with accuracies of 74.6% and 73.0%. After adding segmentation information of acetowhite epithelium to the original images, the classification accuracies of ResNet-18, 50, and 101 improved to 74.8%, 76.3%, and 74.8%, respectively. We demonstrated that the HSIL detection accuracy improved by adding segmentation information to the CNN model, and the improvement in accuracy was consistent across different ResNets.

Background: Antenatal Bartter syndrome is an autosomal recessive disorder causing severe polyuria that leads to severe polyhydramnios and preterm labor. Prenatal diagnosis of antenatal Bartter syndrome is difficult because the genetic diagnosis can only be confirmed following a clinical diagnosis in infants. Reports of prenatal diagnosis and treatment of antenatal Bartter syndrome are limited. Case Presentation: We present the case of a 33-year-old pregnant woman with refractory polyhydramnios at 31 weeks of gestation. There were no structural anomalies or placental problems on ultrasonography; therefore, antenatal Bartter syndrome was suspected. With repeated amniocentesis and indomethacin therapy, the pregnancy continued to 36 weeks of gestation. The clinical features of the infant and subsequent genetic testing confirmed the diagnosis of antenatal Bartter syndrome. The baby was in good clinical condition at the 3-month follow-up visit. Conclusions: For pregnant women with early onset and refractory severe polyhydramnios without morphological anomalies, antenatal Bartter syndrome should be highly suspected.

The present study aimed to evaluate the long-term oncological and obstetric outcomes following the loop electrosurgical excision procedure (LEEP) in patients with cervical intraepithelial neoplasia (CIN) and investigate the risk factors for recurrence and preterm birth. This retrospective cohort study included patients who underwent LEEP for CIN 2–3 between 2011 and 2019. Demographic information, histopathological findings, postoperative cytology, and human papillomavirus (HPV) status were collected and analyzed. The Cox proportional hazards model and Kaplan-Meier curves with the log-rank test were used for risk factor analysis. A total of 385 patients treated with the LEEP were analyzed. Treatment failure, including recurrence or residual disease following surgery, was observed in 13.5% of the patients. Positive surgical margins and postoperative HPV detection were independent risk factors for CIN1 + recurrence or residual disease (HR 1.948 [95%CI 1.020–3.720], p = 0.043, and HR 6.848 [95%CI 3.652–12.840], p-value < 0.001, respectively). Thirty-one patients subsequently delivered after LEEP, and the duration between LEEP and delivery was significantly associated with preterm-related complications, such as a short cervix, preterm labor, and preterm premature rupture of the membrane (p = 0.009). However, only a history of preterm birth was associated with preterm delivery. Positive HPV status after LEEP and margin status were identified as independent risk factors for treatment failure in patients with CIN who underwent LEEP. However, combining these two factors did not improve the prediction accuracy for recurrence.