Improved prediction of clinical pregnancy using artificial intelligence with enhanced inner cell mass and trophectoderm images.

This study aimed to assess the performance of an artificial intelligence (AI) model for predicting clinical pregnancy using enhanced inner cell mass (ICM) and trophectoderm (TE) images. In this retrospective study, we included static images of 2555 day-5-blastocysts from seven in vitro fertilization centers in South Korea. The main outcome of the study was the predictive capability of the model to detect clinical pregnancies (gestational sac). Compared with the original embryo images, the use of enhanced ICM and TE images improved the average area under the receiver operating characteristic curve for the AI model from 0.716 to 0.741. Additionally, a gradient-weighted class activation mapping analysis demonstrated that the enhanced image-trained AI model was able to extract features from crucial areas of the embryo in 99% (506/512) of the cases. Particularly, it could extract the ICM and TE. In contrast, the AI model trained on the original images focused on the main areas in only 86% (438/512) of the cases. Our results highlight the potential efficacy of using ICM- and TE-enhanced embryo images when training AI models to predict clinical pregnancy.

Classification and Explanation for Intrusion Detection System Based on Ensemble Trees and SHAP Method.

In recent years, many methods for intrusion detection systems (IDS) have been designed and developed in the research community, which have achieved a perfect detection rate using IDS datasets. Deep neural networks (DNNs) are representative examples applied widely in IDS. However, DNN models are becoming increasingly complex in model architectures with high resource computing in hardware requirements. In addition, it is difficult for humans to obtain explanations behind the decisions made by these DNN models using large IoT-based IDS datasets. Many proposed IDS methods have not been applied in practical deployments, because of the lack of explanation given to cybersecurity experts, to support them in terms of optimizing their decisions according to the judgments of the IDS models. This paper aims to enhance the attack detection performance of IDS with big IoT-based IDS datasets as well as provide explanations of machine learning (ML) model predictions. The proposed ML-based IDS method is based on the ensemble trees approach, including decision tree (DT) and random forest (RF) classifiers which do not require high computing resources for training models. In addition, two big datasets are used for the experimental evaluation of the proposed method, NF-BoT-IoT-v2, and NF-ToN-IoT-v2 (new versions of the original BoT-IoT and ToN-IoT datasets), through the feature set of the net flow meter. In addition, the IoTDS20 dataset is used for experiments. Furthermore, the SHapley additive exPlanations (SHAP) is applied to the eXplainable AI (XAI) methodology to explain and interpret the classification decisions of DT and RF models; this is not only effective in interpreting the final decision of the ensemble tree approach but also supports cybersecurity experts in quickly optimizing and evaluating the correctness of their judgments based on the explanations of the results.

Extended Spatially Localized Perturbation GAN (eSLP-GAN) for Robust Adversarial Camouflage Patches.

Deep neural networks (DNNs), especially those used in computer vision, are highly vulnerable to adversarial attacks, such as adversarial perturbations and adversarial patches. Adversarial patches, often considered more appropriate for a real-world attack, are attached to the target object or its surroundings to deceive the target system. However, most previous research employed adversarial patches that are conspicuous to human vision, making them easy to identify and counter. Previously, the spatially localized perturbation GAN (SLP-GAN) was proposed, in which the perturbation was only added to the most representative area of the input images, creating a spatially localized adversarial camouflage patch that excels in terms of visual fidelity and is, therefore, difficult to detect by human vision. In this study, the use of the method called eSLP-GAN was extended to deceive classifiers and object detection systems. Specifically, the loss function was modified for greater compatibility with an object-detection model attack and to increase robustness in the real world. Furthermore, the applicability of the proposed method was tested on the CARLA simulator for a more authentic real-world attack scenario.

Auraptene Enhances Junction Assembly in Cerebrovascular Endothelial Cells by Promoting Resilience to Mitochondrial Stress through Activation of Antioxidant Enzymes and mtUPR.

Junctional proteins in cerebrovascular endothelial cells are essential for maintaining the barrier function of the blood-brain barrier (BBB), thus protecting the brain from the infiltration of pathogens. The present study showed that the potential therapeutic natural compound auraptene (AUR) enhances junction assembly in cerebrovascular endothelial cells by inducing antioxidant enzymes and the mitochondrial unfolded protein response (mtUPR). Treatment of mouse cerebrovascular endothelial cells with AUR enhanced the expression of junctional proteins, such as occludin, zonula occludens-1 (ZO-1) and vascular endothelial cadherin (VE-cadherin), by increasing the levels of mRNA encoding antioxidant enzymes. AUR treatment also resulted in the depolarization of mitochondrial membrane potential and activation of mtUPR. The ability of AUR to protect against ischemic conditions was further assessed using cells deprived of oxygen and glucose. Pretreatment of these cells with AUR protected against damage to junctional proteins, including occludin, claudin-5, ZO-1 and VE-cadherin, accompanied by a stress resilience response regulated by levels of ATF5, LONP1 and HSP60 mRNAs. Collectively, these results indicate that AUR promotes resilience against oxidative stress and improves junction assembly, suggesting that AUR may help maintain intact barriers in cerebrovascular endothelial cells.

A Distributed Black-Box Adversarial Attack Based on Multi-Group Particle Swarm Optimization.

Adversarial attack techniques in deep learning have been studied extensively due to its stealthiness to human eyes and potentially dangerous consequences when applied to real-life applications. However, current attack methods in black-box settings mainly employ a large number of queries for crafting their adversarial examples, hence making them very likely to be detected and responded by the target system (e.g., artificial intelligence (AI) service provider) due to its high traffic volume. A recent proposal able to address the large query problem utilizes a gradient-free approach based on Particle Swarm Optimization (PSO) algorithm. Unfortunately, this original approach tends to have a low attack success rate, possibly due to the model's difficulty of escaping local optima. This obstacle can be overcome by employing a multi-group approach for PSO algorithm, by which the PSO particles can be redistributed, preventing them from being trapped in local optima. In this paper, we present a black-box adversarial attack which can significantly increase the success rate of PSO-based attack while maintaining a low number of query by launching the attack in a distributed manner. Attacks are executed from multiple nodes, disseminating queries among the nodes, hence reducing the possibility of being recognized by the target system while also increasing scalability. Furthermore, we utilize Multi-Group PSO with Random Redistribution (MGRR-PSO) for perturbation generation, performing better than the original approach against local optima, thus achieving a higher success rate. Additionally, we propose to efficiently remove excessive perturbation (i.e, perturbation pruning) by utilizing again the MGRR-PSO rather than a standard iterative method as used in the original approach. We perform five different experiments: comparing our attack's performance with existing algorithms, testing in high-dimensional space in ImageNet dataset, examining our hyperparameters (i.e., particle size, number of clients, search boundary), and testing on real digital attack to Google Cloud Vision. Our attack proves to obtain a 100% success rate on MNIST and CIFAR-10 datasets and able to successfully fool Google Cloud Vision as a proof of the real digital attack by maintaining a lower query and wide applicability.

External validation of the post-varicocele repair semen analysis nomogram to predict total motile sperm count: A multicenter study.

Total motile sperm count is an important parameter for predicting the probability of natural pregnancy. We have externally validated the Samplaski's post-varicocele repair semen analysis nomogram to confirm the predictive accuracy of total motile sperm count. A total of 300 patients who had undergone varicocelectomy between July 2016 and July 2019 from 4 treatment centres were included in this validation cohort study. The predictive performance of the externally validated nomogram was revealed by applying the Pearson correlation coefficient (R = 0.328; 95% confidence interval (CI) 0.220-0.435; p < .001). Compared to Samplaski's nomogram result (R = 0.581; 95% CI 0.186-0.729), our study also revealed a statistically significant rate. However, it had a relatively lower correlation coefficient rate. Notably, the predicted total motile sperm count was lower than the observed post-varicocelectomy total motile sperm count. The calibration plot revealed that the discrepancy between the predicted and observed total motile sperm count was plausible. However, it had low explanatory power in this nomogram model. This validation study demonstrates that the post-varicocele repair Samplaski's nomogram predicts a relatively lower total motile sperm count than the observed count.

Dynamics of histone H3 phosphorylation at threonine 3 during meiotic maturation in mouse oocytes.

Various histone residues are post-translationally modified during the cell cycle. Among these, histone H3 phosphorylation at threonine 3 (H3T3ph) is newly characterized and has been considered to be crucial for chromosome dynamics during mitosis. However, little is known about the role of H3T3ph during mouse oocyte maturation. In the present study, we examined H3T3ph expression and localization during oocyte meiosis. Our results showed that H3T3ph was tightly associated with condensed chromosomes during meiotic maturation. H3T3ph along the chromosome arms was dissociated at anaphase/telophase I, but centromeric H3T3ph remained intact. Moreover, the inhibition of H3T3ph with the small molecule inhibitors CHR-6494 and 5-Itu impaired segregation of homologous chromosomes during meiosis. Partial inhibition of H3T3ph revealed that centromeric Aurora B/C kinase is sufficient to complete meiosis I, but Aurora B/C kinase along the chromosome arms is required to ensure accurate homologous chromosome segregation. Therefore, our results demonstrate that H3T3ph is a universal regulator of chromosome dynamics during oocyte meiosis and mitosis.

Greatwall kinase is required for meiotic maturation in porcine oocytes.

Meiotic maturation in many species is initiated by the activation of maturation-promoting factor (MPF) with concomitant inactivation of counteracting phosphatases, most notably protein phosphatase 2A (PP2A). Recently, Greatwall (GWL) has been identified as a cell cycle regulator that inhibits PP2A activity. In this study, we demonstrate that GWL is required for meiotic maturation in porcine oocytes. GWL expression increases from germinal vesicle (GV) to metaphase II (MII) stages of porcine oocytes and dramatically decreases with progression of the meiotic cell cycle. GWL is initially localized in the nucleus of GV oocytes and is associated with spindle fibers following GV breakdown. Depletion of GWL inhibited or delayed meiotic maturation secondary to defects in chromosome congression and spindle formation. Conversely, overexpression of GWL overcame meiotic arrest and initiated progression to MII stage. However, these oocytes had severe spindle defects. Furthermore, MII oocytes depleted of GWL progressed to pronuclear formation. Taken together, our data demonstrate that GWL is required not only for meiotic maturation but also for maintenance of MII arrest in porcine oocytes.

Cdc25B phosphatase participates in maintaining metaphase II arrest in mouse oocytes.

Cdc25B is an essential regulator for meiotic resumption in mouse oocytes. However, the role of this phosphatase during the later stage of the meiotic cell cycle is not known. In this study, we investigated the role of Cdc25B during metaphase II (MII) arrest in mouse oocytes. Cdc25B was extensively phosphorylated during MII arrest with an increase in the phosphatase activity toward Cdk1. Downregulation of Cdc25B by antibody injection induced the formation of a pronucleus-like structure. Conversely, overexpression of Cdc25B inhibited Ca(2+)-mediated release from MII arrest. Moreover, Cdc25B was immediately dephosphorylated and hence inactivated during MII exit, suggesting that Cdk1 phosphorylation is required to exit from MII arrest. Interestingly, this inactivation occurred prior to cyclin B degradation. Taken together, our data demonstrate that MII arrest in mouse oocytes is tightly regulated not only by the proteolytic degradation of cyclin B but also by dynamic phosphorylation of Cdk1.