Objective: This study aimed to evaluate and validate the performance of deep convolutional neural networks when discriminating different histologic types of ovarian tumor in ultrasound (US) images.Material and methods: Our retrospective study took 1142 US images from 328 patients from January 2019 to June 2021. Two tasks were proposed based on US images. Task 1 was to classify benign and high-grade serous carcinoma in original ovarian tumor US images, in which benign ovarian tumor was divided into six classes: mature cystic teratoma, endometriotic cyst, serous cystadenoma, granulosa-theca cell tumor, mucinous cystadenoma and simple cyst. The US images in task 2 were segmented. Deep convolutional neural networks (DCNN) were applied to classify different types of ovarian tumors in detail. We used transfer learning on six pre-trained DCNNs: VGG16, GoogleNet, ResNet34, ResNext50, DensNet121 and DensNet201. Several metrics were adopted to assess the model performance: accuracy, sensitivity, specificity, FI-score and the area under the receiver operating characteristic curve (AUC).Results: The DCNN performed better in labeled US images than in original US images. The best predictive performance came from the ResNext50 model. The model had an overall accuracy of 0.952 for in directly classifying the seven histologic types of ovarian tumors. It achieved a sensitivity of 90% and a specificity of 99.2% for high-grade serous carcinoma, and a sensitivity of over 90% and a specificity of over 95% in most benign pathological categories.Conclusion: DCNN is a promising technique for classifying different histologic types of ovarian tumors in US images, and provide valuable computer-aided information.

Diagnostic results can be radically influenced by the quality of 2D ovarian-tumor ultrasound images. However, clinically processed 2D ovarian-tumor ultrasound images contain many artificially recognized symbols, such as fingers, crosses, dashed lines, and letters which assist artificial intelligence (AI) in image recognition. These symbols are widely distributed within the lesion’s boundary, which can also affect the useful feature-extraction-utilizing networks and thus decrease the accuracy of lesion classification and segmentation. Image inpainting techniques are used for noise and object elimination from images. To solve this problem, we observed the MMOTU dataset and built a 2D ovarian-tumor ultrasound image inpainting dataset by finely annotating the various symbols in the images. A novel framework called mask-guided generative adversarial network (MGGAN) is presented in this paper for 2D ovarian-tumor ultrasound images to remove various symbols from the images. The MGGAN performs to a high standard in corrupted regions by using an attention mechanism in the generator to pay more attention to valid information and ignore symbol information, making lesion boundaries more realistic. Moreover, fast Fourier convolutions (FFCs) and residual networks are used to increase the global field of perception; thus, our model can be applied to high-resolution ultrasound images. The greatest benefit of this algorithm is that it achieves pixel-level inpainting of distorted regions without clean images. Compared with other models, our model achieveed better results with only one stage in terms of objective and subjective evaluations. Our model obtained the best results for 256 × 256 and 512 × 512 resolutions. At a resolution of 256 × 256, our model achieved $0.9246$ for SSIM, $22.66$ for FID, and $0.07806$ for LPIPS. At a resolution of 512 × 512, our model achieved $0.9208$ for SSIM, $25.52$ for FID, and $0.08300$ for LPIPS. Our method can considerably improve the accuracy of computerized ovarian tumor diagnosis. The segmentation accuracy was improved from $71.51\%$ to $76.06\%$ for the Unet model and from $61.13\%$ to $66.65\%$ for the PSPnet model in clean images.

Background: The pre-pregnancy weight and gestational weight gain (GWG) are closely related to perinatal maternal and infant complications, but the relationship between pre-pregnancy weight and GWG and the pattern of interaction have not been reported. This study investigated the influence of weight control during pregnancy on the perinatal maternal and infant outcomes. Methods: A total of 835 singleton pregnant women who were hospitalized between January 2018 and December 2018 were retrospectively included in this study and divided into two groups: the diet guidance (DG) group (n = 167) and the control group (n = 668). The pre-pregnancy body mass index (BMI), GWG, and perinatal outcomes of the women and infants were determined in two groups. Results: The dietary modification and reasonable exercise during pregnancy effectively reduced the GWG, and even some women with pre-pregnancy obesity achieved weight loss during pregnancy. The GWG in the DG group was significantly lower than in the control group, especially in the second and third trimesters. GWG was positively related to birth weight. The birth weight in the DG group was significantly lower than in the control group when their mothers had similar GWG. In women with pre-pregnancy obesity, GWG seemed to be negatively related to birth weight. However, after adjusting the mean BMI, the pre-pregnancy BMI and GWG were positively related to the birth weight. Compared with the control group, the incidences of dystocia, postpartum hemorrhage, macrosomia, small for gestational age infants and neonatal complications significantly reduced in the DG group, and the preterm birth rate was comparable between two groups. Some women with pre-pregnancy obesity lose weight during pregnancy, but there was no premature birth or small for gestational age infant. The incidences of macrosomia, postpartum hemorrhage, dystocia, cesarean section and gestational diabetes increased significantly with the increase of pre-pregnancy BMI. Conclusion: For women with increased pre-pregnancy BMI, strict weight control is required to reduce obesity-related complications of the mother and infant. The weight control in the second and third trimesters is especially important and most likely to prevent GWG. Compared with GWG, pre-pregnancy BMI has greater influence on the birth weight and maternal and infant complications, and may even compromise the benefits of weight control during pregnancy. Thus, weight control is recommended before pregnancy.

Background: The application of artificial intelligence (AI) powered algorithm in clinical decision-making is globally popular among clinicians and medical scientists. In this research endeavor, we harnessed the capabilities of AI to enhance the precision of hysteroscopic myomectomy procedures.Methods: Our multidisciplinary team developed a comprehensive suite of algorithms, rooted in deep learning technology, addressing myomas segmentation tasks. We assembled a cohort comprising 56 patients diagnosed with submucosal myomas, each of whom underwent magnetic resonance imaging (MRI) examinations. Subsequently, half of the participants were randomly designated to undergo AI-augmented procedures. Our AI system exhibited remarkable proficiency in elucidating the precise spatial localization of submucosal myomas.Results: The results of our study showcased a statistically significant reduction in both operative duration (41.32 ± 17.83 minutes vs. 32.11 ± 11.86 minutes, p=0.03) and intraoperative blood loss (10.00 (6.25-15.00) ml vs. 10.00 (5.00-15.00) ml, p=0.04) in procedures assisted by AI.Conclusion: This work stands as a pioneering achievement, marking the inaugural deployment of an AI-powered diagnostic model in the domain of hysteroscopic surgery. Consequently, our findings substantiate the potential of AI-driven interventions within the field of gynecological surgery.

Polycystic ovary syndrome (PCOS) is the most common cause of anovulatory infertility. The ketogenic diet (KD), a diet high in fat and low in carbohydrates, has been applied clinically for the treatment of obese women with PCOS. We have previously demonstrated that KD improved the reproductive phenotype in an androgen-induced PCOS mouse model, yet the underlying molecular mechanisms remain largely unclear. The aim of the present study was to investigate the effect of KD on the reproductive phenotype of a letrozole-induced PCOS mouse model. Female C57BL/6N mice were divided into three groups, designated control, letrozole, and letrozole + KD groups. Mice of control and letrozole groups were fed the control diet, whereas letrozole + KD mice were fed a KD with 89.9% (kcal) fat for 3 weeks after the PCOS mouse model was generated. β-hydroxybutyrate (BHB), the most abundant ketone body in the body, was used to treat KGN cells with testosterone (T) to simulate the KD effect on PCOS mouse ovaries in vitro. Our data showed that KD treatment significantly increased blood ketone levels and reduced body weight. Ovarian functions were improved in some letrozole + KD mice. Results from in vitro experiments indicated mitochondrial damage owing to high T levels, which resulted in the leakage of cytochrome C and mitochondrial DNA into the cytosol and thus induced the activation of the intracellular caspase cascade and the cGAS-STING-NF-κB pathway, leading to granulosa cell inflammation and apoptosis. BHB exhibited certain protective effects on mitochondria of T-treated KGN cells via inhibiting the cGAS-STING pathway. Moreover, the cGAS-STING pathway was activated in ovaries of letrozole mice and was down-regulated in letrozole + KD mice. These findings, for the first time, revealed that hyperandrogenism induced ovarian dysfunction possibly through activation of the cGAS-STING pathway, which could be partially inhibited by ketone bodies produced from KD administration.