Background/Objectives: This study aims to create a strong binary classifier and evaluate the performance of pre-trained convolutional neural networks (CNNs) to effectively distinguish between benign and malignant ovarian tumors from still ultrasound images. Methods: The dataset consisted of 3510 ultrasound images from 585 women with ovarian tumors, 390 benign and 195 malignant, that were classified by experts and verified by histopathology. A 20% to80% split for training and validation was applied within a k-fold cross-validation framework, ensuring comprehensive utilization of the dataset. The final classifier was an aggregate of three pre-trained CNNs (VGG16, ResNet50, and InceptionNet), with experimentation focusing on the aggregation weights and decision threshold probability for the classification of each mass. Results: The aggregate model outperformed all individual models, achieving an average sensitivity of 96.5% and specificity of 88.1% compared to the subjective assessment’s (SA) 95.9% sensitivity and 93.9% specificity. All the above results were calculated at a decision threshold probability of 0.2. Notably, misclassifications made by the model were similar to those made by SA. Conclusions: CNNs and AI-assisted image analysis can enhance the diagnosis and aid ultrasonographers with less experience by minimizing errors. Further research is needed to fine-tune CNNs and validate their performance in diverse clinical settings, potentially leading to even higher sensitivity and overall accuracy.

Background/Objectives: There are indications that the microbial composition of the maternal mucosal surfaces is associated with adverse events during pregnancy. The aim of this review is to investigate the link between vaginal microbiome alterations and gestational com-plications risk. Methods: This comprehensive literature review was performed using Medline and Scopus databases. The following search algorithm was used "Pregnancy Complications"[Mesh] AND (Vagin*) and after literature screening 44 studies were included in the final review. Results: The studies that were included investigated the association between vaginal microbial composi-tion and preterm birth, miscarriage, preeclampsia, ectopic pregnancy, gestational diabetes mellitus, chorioamnionitis and preterm premature rupture of membranes. In most of the studies, it was well established that increased microbial diversity is associated with these conditions. Also, the depletion of Lactobacillus species is linked to most of the gestational complication, while the increased relative abundance and especially L. crispatus may exerts a protective effect in favor of the pregnant woman. Several pathogenic taxa including Gardnerella, Prevotella, Sneathia, Bac-terial Vaginosis-Associated Bacteria-2, Atopobium and Megasphera seem to be correlated to higher maternal morbidity. Conclusions: Vaginal microbiome aberrations seem to have an as-sociation with pregnancy related adverse events, but more high-quality homogenous studies are necessary to reliably verify this link.

Objectives The discrimination of ovarian lesions presents a significant problem in everyday clinical practice with ultrasonography appearing to be the most effective diagnostic technique. The aim of our study was to externally evaluate the performance of different diagnostic models when applied by examiners with various levels of experience. Methods This was a diagnostic accuracy study including women who were admitted for adnexal masses, between July 2018 and April 2021, to a Greek tertiary oncology center. Preoperatively sonographic data were evaluated by an expert gynecologist, a 6^th and a 1^st year gynecology resident, who applied the International Ovarian Tumor Analysis (IOTA) Simple Rules (SR) and Assessment of Different NEoplasias in the adneXa (ADNEX) model to discriminate between benign and malignant ovarian tumors. The explant pathology report was used as the reference diagnosis. Kappa statistics were used for the investigation of the level of agreement between the examined systems and the raters. Results We included 66 women, 39 with benign and 27 with malignant ovarian tumors. ADNEX (with and without “CA-125”) had high sensitivity (96–100%) when applied by all raters but a rather low specificity (36%) when applied by the 1st year resident. SR could not be applied in 6% to 17% of the cases. It had slightly lower sensitivity, higher specificity, and higher overall accuracy, especially when applied by the 1st year resident (61% vs. 92%), compared to ADNEX. Conclusion Both ADNEX and SR can be utilized for screening in non-oncology centers since they offer high sensitivity even when used by less experienced examiners. In the hands of inexperienced examiners, SR appears to be the best model for assessing ovarian lesions. Received: 10 April 2022 Accepted after revision: 02 February 2023 Article published online: 23 August 2023 © 2023. The Author(s). This is an open access article published by Thieme under the terms of the Creative Commons Attribution-NonDerivative-NonCommercial-License, permitting copying and reproduction so long as the original work is given appropriate credit. Contents may not be used for commercial purposes, or adapted, remixed, transformed or built upon. (https://creativecommons.org/licenses/by-nc-nd/4.0/). Georg Thieme Verlag KG Rüdigerstraße 14, 70469 Stuttgart, Germany

The purpose of the study was to assess the efficacy of local ultrasound-guided methotrexate injection in patients with caesarean section scar pregnancy, to chart the course of beta-human chorionic gonadotropin levels (HCG) after treatment, and to see if HCG levels are correlated with clinical presentation.Between May 2018 and January 2021, data were collected retrospectively from the Early Pregnancy Unit of a tertiary hospital.Our clinic assessed 20 patients; one disputed terminating the pregnancy and was not included in the research. The remaining 19 patients, with a median age of 34 years, received intragestational sac methotrexate injection under ultrasound guidance. 7w3d was the median gestational age. These women had one to four previous caesarean sections, with a mean of 1.60±9. Patients with caesarean scar pregnancy most typically presented with spotting (42.1%), whereas 26.3% were asymptomatic. Except in cases of pain, the symptomatic women’s HCG levels were lower than in the non-symptomatic women. The level of HCG in patients with pain was approximately double that of non-pain patients (p=0.2557). In our series, intragestational sac methotrexate injection was effective in 17/19 women, or 89.5% (95%CI: 75.7-100%). HCG levels were undetectable in 97.6±30 days on average (minimum: 42 days, maximum: 147 days).Caesarean scar pregnancy is a rare possibly fatal condition with no consensus on the optimal treatment. An experienced Early Pregnancy Unit member performing local methotrexate injections under ultrasound guidance is a feasible and successful strategy in clinically stable patients.

Background: It is well established in the literature that pregnancy-associated plasma protein-A (PAPP-A) is linked to several adverse pregnancy outcomes, including pre-eclampsia (PE), fetal growth restriction (FGR), and preterm birth (PTB) in singleton pregnancies. However, data regarding such an association in twin pregnancies are lacking. The primary goal of this systematic review and meta-analysis was to assess the potential value of low PAPP-A levels in the prediction of the subsequent development of hypertensive disorders of pregnancy (HDPs), PTB, and small for gestational age (SGA)/FGR fetuses in twin pregnancies and investigate its association with the development of gestational diabetes, intrauterine death (IUD) of at least one twin, and birth weight discordance (BWD) among the fetuses. Methods: Medline, Scopus, CENTRAL, Clinicaltrials.gov, and Google Scholar databases were systematically searched from inception until 31 July 2024. All observational studies reporting low PAPP-A levels after the performance of the first-trimester combined test as part of the screening for chromosomal abnormalities with reported adverse pregnancy outcomes were included. Results: The current systematic review encompassed a total of 11 studies (among which 6 were included in the current meta-analysis) that enrolled a total of 3741 patients. Low PAPP-A levels were not associated with HDPs (OR 1.25, 95% CI 0.78, 2.02, I-square test: 13%). Low PAPP-A levels were positively associated with both the development of preterm birth prior to 32 (OR 2.85, 95% CI 1.70, 4.77, I-square test: 0%) and 34 weeks of gestational age (OR 2.09, 95% CI 1.34, 3.28, I-square test: 0%). Furthermore, low PAPP-A levels were positively associated with SGA/FGR (OR 1.58, 95% CI 1.04, 2.41, I-square test: 0%). Prediction intervals indicated that the sample size that was used did not suffice to support these findings in future studies. Conclusions: Our study indicated that low PAPP-A levels are correlated with an increased incidence of adverse perinatal outcomes in twin pregnancies. Identifying women at elevated risk for such adversities in twin pregnancies may facilitate appropriate management and potential interventions, but additional studies are required to identify the underlying mechanism linking PAPP-A with those obstetrical complications.

The wandering spleen (WS) is a rare condition in which the spleen is not found in its usual location in the left hypochondrium but is positioned in the lower abdomen or the pelvis. This is a case of a 21-year-old woman who presented with chronic, intermittent, and subtle pain in the left lower quadrant of her abdomen. After clinical examination and ultrasound evaluation, an adnexal lesion was detected in the left lumbar area, and no splenic tissue was found in the left hypochondrium. The wandering spleen should be included in the differential diagnosis when encountering a patient with non-typical or acute abdominal pain. Accurate diagnostic evaluation can be performed with low-cost imaging modalities such as Doppler ultrasound.