Enhancing Ovarian Tumor Diagnosis: Performance of Convolutional Neural Networks in Classifying Ovarian Masses Using Ultrasound Images.

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.

Cracking the Code: Investigating the Correlation between Aerobic Vaginitis and Preterm Labor.

Aerobic vaginitis (AV) is a distinct clinical entity characterized by inflammation and abnormal vaginal microflora. Often mistaken for bacterial vaginosis, AV remains relatively unknown and underdiagnosed. AV's understanding is evolving, with some experts suggesting it may primarily be an immunological disorder, the prevalence of which has a range of 7-13% in non-pregnant women and 4.1-8.3% during pregnancy. Pregnancy can affect susceptibility to vaginal infections, leading to adverse outcomes for the woman and the newborn. This review summarizes the correlation between AV and adverse pregnancy outcomes, particularly preterm birth, the leading cause of morbidity and mortality among neonates. An improved understanding of AV's impact on pregnancy outcomes can lead to early recognition, proper management, and effective interventions. While some studies support an association between AV and preterm labor, the existing knowledge of this relationship remains limited. The evidence suggests that AV may contribute to adverse pregnancy outcomes, mainly preterm birth, but further research is needed to establish a definitive link. Further studies are needed to investigate the underlying mechanisms and clarify AV's role in premature labor. A comprehensive understanding of AV's impact on pregnancy outcomes is crucial for early recognition, appropriate management, and effective interventions.

Prospective Study on the Correlation between CART and Leptin Gene Expression, Obesity, and Reproductive Hormones in Individuals Undergoing Bariatric Surgery.

Obesity, a global health concern affecting 650 million individuals of all ages worldwide, prompts health complications, including fertility issues. This research investigates the impact of bariatric surgery on morbidly obese females under 40, examining the relationship between CART and leptin gene expressions and reproductive hormones. Post-surgery, a significant reduction in BMI (16.03 kg/m2, n = 29) was observed, accompanied by notable hormonal changes. FSH levels showed a mean difference of 3.18 ± 1.19 pre- and post-surgery (p < 0.001), LH levels exhibited a mean difference of 2.62 ± 1.1 (p < 0.001), E2 levels demonstrated a mean difference of 18.62 ± 5.02 (p < 0.001), and AMH levels showed a mean difference of 3.18 ± 1.19 (p < 0.001). High CART and leptin expressions before treatment correlated with lower expressions after treatment. These findings, rooted in statistically significant correlations (CART: rs = 0.51, p = 0.005; leptin: rs = 0.75, p < 0.001), shed light on potential molecular pathways connecting gene expressions with reproductive hormones post-bariatric surgery. Our study uniquely investigates the interplay between genetic markers, infertility, and bariatric surgery in women. It stands out by providing distinctive insights into the development of personalized treatment strategies for obesity-related infertility, contributing to a deeper understanding of this complex medical issue.