The Role of the Intestinal Flora and Its Derivatives in Neurocognitive Disorders: A Narrative Review from Surgical Perspective.

Perioperative neurocognitive dysfunction is a significant concern for population health, impacting postoperative recovery and increasing the financial burden on patients. With an increasing number of surgical procedures being performed, the prevention and management of perioperative neurocognitive dysfunction have garnered significant attention. While factors such as age, lifestyle, genetics, and education are known to influence the development of cognitive dysfunction, recent research has highlighted the role of the gut microbiota in neurological health. An increased abundance of pro-inflammatory gut microbiota can trigger and worsen neuroinflammation, neuronal cell damage, and impaired cellular autophagy. Moreover, the inflammation-promoting gut microbiota can disrupt immune function, impair neuroautophagy, and affect the production and circulation of extracellular vesicles and neurotransmitters. These factors collectively play a role in the onset and advancement of cognitive impairment. This narrative review delves into the molecular mechanisms through which gut microbiota and their derivatives contribute to cognitive impairment, focusing on the impact of anesthesia surgery, changes in gut microbial populations, and perioperative cognitive impairment associations. The study suggests that alterations in the abundance of various bacterial species and their metabolites pre- and post-surgery may be linked to postoperative cognitive impairment. Furthermore, the potential of probiotics or prebiotics in addressing cognitive impairment is discussed, offering a promising avenue for investigating the treatment of perioperative neurocognitive disorders.

Deep Location Soft-Embedding-Based Network with Regional Scoring for Mammogram Classification.

Early detection and treatment of breast cancer can significantly reduce patient mortality, and mammogram is an effective method for early screening. Computer-aided diagnosis (CAD) of mammography based on deep learning can assist radiologists in making more objective and accurate judgments. However, existing methods often depend on datasets with manual segmentation annotations. In addition, due to the large image sizes and small lesion proportions, many methods that do not use region of interest (ROI) mostly rely on multi-scale and multi-feature fusion models. These shortcomings increase the labor, money, and computational overhead of applying the model. Therefore, a deep location soft-embedding-based network with regional scoring (DLSEN-RS) is proposed. DLSEN-RS is an end-to-end mammography image classification method containing only one feature extractor and relies on positional embedding (PE) and aggregation pooling (AP) modules to locate lesion areas without bounding boxes, transfer learning, or multi-stage training. In particular, the introduced PE and AP modules exhibit versatility across various CNN models and improve the model's tumor localization and diagnostic accuracy for mammography images. Experiments are conducted on published INbreast and CBIS-DDSM datasets, and compared to previous state-of-the-art mammographic image classification methods, DLSEN-RS performed satisfactorily.

Exploring sparsity in graph transformers.

Graph Transformers (GTs) have achieved impressive results on various graph-related tasks. However, the huge computational cost of GTs hinders their deployment and application, especially in resource-constrained environments. Therefore, in this paper, we explore the feasibility of sparsifying GTs, a significant yet under-explored topic. We first discuss the redundancy of GTs based on the characteristics of existing GT models, and then propose a comprehensive Graph Transformer SParsification (GTSP) framework that helps to reduce the computational complexity of GTs from four dimensions: the input graph data, attention heads, model layers, and model weights. Specifically, GTSP designs differentiable masks for each individual compressible component, enabling effective end-to-end pruning. We examine our GTSP through extensive experiments on prominent GTs, including GraphTrans, Graphormer, and GraphGPS. The experimental results demonstrate that GTSP effectively reduces computational costs, with only marginal decreases in accuracy or, in some instances, even improvements. For example, GTSP results in a 30% reduction in Floating Point Operations while contributing to a 1.8% increase in Area Under the Curve accuracy on the OGBG-HIV dataset. Furthermore, we provide several insights on the characteristics of attention heads and the behavior of attention mechanisms, all of which have immense potential to inspire future research endeavors in this domain. Our code is available at https://github.com/LiuChuang0059/GTSP.

Logical Relation Inference and Multiview Information Interaction for Domain Adaptation Person Re-Identification.

Domain adaptation person re-identification (Re-ID) is a challenging task, which aims to transfer the knowledge learned from the labeled source domain to the unlabeled target domain. Recently, some clustering-based domain adaptation Re-ID methods have achieved great success. However, these methods ignore the inferior influence on pseudo-label prediction due to the different camera styles. The reliability of the pseudo-label plays a key role in domain adaptation Re-ID, while the different camera styles bring great challenges for pseudo-label prediction. To this end, a novel method is proposed, which bridges the gap of different cameras and extracts more discriminative features from an image. Specifically, an intra-to-intermechanism is introduced, in which samples from their own cameras are first grouped and then aligned at the class level across different cameras followed by our logical relation inference (LRI). Thanks to these strategies, the logical relationship between simple classes and hard classes is justified, preventing sample loss caused by discarding the hard samples. Furthermore, we also present a multiview information interaction (MvII) module that takes features of different images from the same pedestrian as patch tokens, obtaining the global consistency of a pedestrian that contributes to the discriminative feature extraction. Unlike the existing clustering-based methods, our method employs a two-stage framework that generates reliable pseudo-labels from the views of the intracamera and intercamera, respectively, to differentiate the camera styles, subsequently increasing its robustness. Extensive experiments on several benchmark datasets show that the proposed method outperforms a wide range of state-of-the-art methods. The source code has been released at https://github.com/lhf12278/LRIMV.

Comprehensive Graph Gradual Pruning for Sparse Training in Graph Neural Networks.

Graph neural networks (GNNs) tend to suffer from high computation costs due to the exponentially increasing scale of graph data and a large number of model parameters, which restricts their utility in practical applications. To this end, some recent works focus on sparsifying GNNs (including graph structures and model parameters) with the lottery ticket hypothesis (LTH) to reduce inference costs while maintaining performance levels. However, the LTH-based methods suffer from two major drawbacks: 1) they require exhaustive and iterative training of dense models, resulting in an extremely large training computation cost, and 2) they only trim graph structures and model parameters but ignore the node feature dimension, where vast redundancy exists. To overcome the above limitations, we propose a comprehensive graph gradual pruning framework termed CGP. This is achieved by designing a during-training graph pruning paradigm to dynamically prune GNNs within one training process. Unlike LTH-based methods, the proposed CGP approach requires no retraining, which significantly reduces the computation costs. Furthermore, we design a cosparsifying strategy to comprehensively trim all the three core elements of GNNs: graph structures, node features, and model parameters. Next, to refine the pruning operation, we introduce a regrowth process into our CGP framework, to reestablish the pruned but important connections. The proposed CGP is evaluated over a node classification task across six GNN architectures, including shallow models graph convolutional network (GCN) and graph attention network (GAT), shallow-but-deep-propagation models simple graph convolution (SGC) and approximate personalized propagation of neural predictions (APPNP), and deep models GCN via initial residual and identity mapping (GCNII) and residual GCN (ResGCN), on a total of 14 real-world graph datasets, including large-scale graph datasets from the challenging Open Graph Benchmark (OGB). Experiments reveal that the proposed strategy greatly improves both training and inference efficiency while matching or even exceeding the accuracy of the existing methods.

The predictive accuracy of CT radiomics combined with machine learning in predicting the invasiveness of small nodular lung adenocarcinoma.

Background: Conventionally, the judgment of whether small pulmonary nodules are invasive is mainly made by thoracic surgeons according to the chest computed tomography (CT) features of patients. However, there are limits to how much useful information can be obtained from this approach. A large number of feature information was extracted from CT images by CT radiomics. The machine learning algorithm was used to construct models based on radiomic characteristics to predict the invasiveness of lung adenocarcinoma (LUAD) with a good prediction accuracy. Methods: A total of 416 patients with pathologically confirmed preinvasive lesions and LUAD after video-assisted thoracoscopic surgery (VATS) in the Department of Thoracic Surgery of the First People's Hospital of Yunnan Province from February 2020 to February 2022 were retrospectively analyzed. According to random classification, patients were divided into 2 groups. The RadCloud platform was used to extract radiomics features, and the most relevant radiomics features were selected by continuous dimension reduction method. Then, 6 machine learning algorithms were used to establish and verify the prediction model of small lung nodular adenocarcinoma invasiveness. Receiver operating characteristic (ROC) curve and area under curve (AUC) were used to evaluate the predictive performance. Results: There were 78 cases of pre-invasive lesions and 226 cases of invasive lesions in the training group, and 34 cases of pre-invasive lesions and 78 cases of invasive lesions in the validation group. In the training group, the AUC values of the 6 models were all more than 0.914, the 95% confidence interval (CI) was 0.857-1.00, the sensitivity was equal or more than 0.87, and the specificity was equal or more than 0.85. In the validation group, the AUC values of the 6 models were all equal or more than 0.732, the 95% CI was 0.651-1.00, the sensitivity was equal or more than 0.7, and the specificity was more than 0.77. Conclusions: Machine learning algorithms were used to construct models to predict the invasiveness of small nodular LUAD based on radiomics features, which it could provide more evidence for doctors to make diagnoses and more personalized treatment plans for patients.

BiN-Flow: Bidirectional Normalizing Flow for Robust Image Dehazing.

Image dehazing aims to remove haze in images to improve their image quality. However, most image dehazing methods heavily depend on strict prior knowledge and paired training strategy, which would hinder generalization and performance when dealing with unseen scenes. In this paper, to address the above problem, we propose Bidirectional Normalizing Flow (BiN-Flow), which exploits no prior knowledge and constructs a neural network through weakly-paired training with better generalization for image dehazing. Specifically, BiN-Flow designs 1) Feature Frequency Decoupling (FFD) for mining the various texture details through multi-scale residual blocks and 2) Bidirectional Propagation Flow (BPF) for exploiting the one-to-many relationships between hazy and haze-free images using a sequence of invertible Flow. In addition, BiN-Flow constructs a reference mechanism (RM) that uses a small number of paired hazy and haze-free images and a large number of haze-free reference images for weakly-paired training. Essentially, the mutual relationships between hazy and haze-free images could be effectively learned to further improve the generalization and performance for image dehazing. We conduct extensive experiments on five commonly-used datasets to validate the BiN-Flow. The experimental results that BiN-Flow outperforms all state-of-the-art competitors demonstrate the capability and generalization of our BiN-Flow. Besides, our BiN-Flow could produce diverse dehazing images for the same image by considering restoration diversity.

Effects of dietary fibre on intestinal microbiota in geese evaluated by 16SrRNA gene sequencing.

AIMS: The purpose of the research is to study the effects of different fibre types and sources on the intestinal flora of geese. METHODS AND RESULTS: A total of 48 geese (males: 35 days old) were divided into four groups, each of which included three replicates of four geese. Groups 1-4 were fed a diet containing 5% corn stover Crude fibre (CF, the LJ group), 8% corn stover CF (the HJ group), 5% alfalfa CF (the LM group) or 8% alfalfa CF (the HM group), respectively. After 42 days of feeding, the intestinal flora of each group was determined by 16SrRNA gene sequencing. In the duodenum, the diet supplemented with corn stover meal increased the relative abundance of Proteobacteria, Actinobacteria and Euryarchaeota, and with alfalfa as fibre source increased the relative abundance of Firmicutes, Bacteroidetes, Tenericutes and Chloroflexi. In the jejunum, Bacteroidetes, Actinobacteria, Planctomycetes, Acidobacteria, Tenericutes and Spirochetes were significantly more abundant in the corn stover group. There were no significant differences among the results for the other two fibre sources, which were fibre level in their influence where in ileum. Firmicutes, Deferribacteres and Euryarchaeota with corn stover as fibre source in the cecum were higher than the alfalfa group. CONCLUSIONS: Different fibre sources have significant effects on goose gut microbiota. The same flora has the same trend of change in different intestinal segments. The relative fibre source in the ileum makes the gut microbiota more sensitive to differences in fibre levels. SIGNIFICANCE AND IMPACT OF THE STUDY: This study proved that the dietary fibre affects the intestinal flora. At the same time, different groups of dietary fibre may be used to provide the possibility to study functional roles of specific bacteria in host physiology.

Image Hallucination From Attribute Pairs.

Recent image-generation methods have demonstrated that realistic images can be produced from captions. Despite the promising results achieved, existing caption-based generation methods confront a dilemma. On the one hand, the image generator should be provided with sufficient details for realistic hallucination, meaning that longer sentences with rich content are preferred, but on the other hand, the generator is meanwhile fragile to long sentences due to their complex semantics and syntax like long-range dependencies and the combinatorial explosion of object visual features. Toward alleviating this dilemma, a novel approach is proposed in this article to hallucinate images from attribute pairs, which can be extracted from natural language processing (NLP) toolsets in the presence of complex semantics and syntax. Attribute pairs, therefore, enable our image generator to tackle long sentences handily and alleviate the combinatorial explosion, and at the same time, allow us to enlarge the training dataset and to produce hallucinations from randomly combined attribute pairs at ease. Experiments on widely used datasets demonstrate that the proposed approach yields results superior to the state of the art.

A Contour Co-Tracking Method for Image Pairs.

We proposed a contour co-tracking method for co-segmentation of image pairs based on active contour model. Our method comprehensively re-models objects and backgrounds signified by level set functions, and leverages Hellinger distance to measure the similarity between image regions encoded by probability distributions. The main contribution are as follows. 1) The new energy functional, combining a rewarding and a penalty term, relaxes the assumptions of co-segmentation methods. 2) Hellinger distance, fulfilling the triangle inequality, ensures a coherence measurement between probability distributions in metric space, and contributes to finding a unique solution to the energy functional. The proposed contour co-tracking method was carefully verified against five representative methods on four popular datasets, i.e., the images pair dataset (105 pairs), MSRC dataset (30 pairs), iCoseg dataset (66 pairs) and Coseg-rep dataset (25 pairs). The comparison experiments suggest that our method achieves the competitive and even better performance compared to the state-of-the-art co-segmentation methods.

One year of African swine fever outbreak in China.

African swine fever (ASF) is a major threat to domestic pigs and wild boars. Since 2018, ASF outbreaks have been ongoing in China. As of August 3, 2019, a total of 151 ASF clusters of outbreaks reported in China have caused severe economic losses for the industry, the pig farmers and pork producers, due to the lack of an efficacious vaccine. The present study aims to analyze the epidemiologic characteristics of ASF outbreak that occurred in several regions across China during the period August 2018- August 2019. Particular focus was on the epidemic distribution, main transmission routes, incidence/fatality, impact on pig production capacity, and the main preventive measures adopted to mitigate the risk of ASF spread in pig farming systems by Chinese government. Results show that anthropogenic factors, spatial distribution, efficient measures taken by China,and good response timely in implementation of preventive measures are important on the transmission of ASF and these suggest that effective ASF risk management in China will require a comprehensive and integrated approach linking science and implemented by all relevant stakeholders. This provides an empirical basis to optimize current interventions as well as develop new tools and strategies to reduce the risk transmission of African swine fever virus (ASFV) to domestic pigs and wild boars.

Constrained Discriminative Projection Learning for Image Classification.

Projection learning is widely used in extracting discriminative features for classification. Although numerous methods have already been proposed for this goal, they barely explore the label information during projection learning and fail to obtain satisfactory performance. Besides, many existing methods can learn only a limited number of projections for feature extraction which may degrade the performance in recognition. To address these problems, we propose a novel constrained discriminative projection learning (CDPL) method for image classification. Specifically, CDPL can be formulated as a joint optimization problem over subspace learning and classification. The proposed method incorporates the low-rank constraint to learn a robust subspace which can be used as a bridge to seamlessly connect the original visual features and objective outputs. A regression function is adopted to explicitly exploit the class label information so as to enhance the discriminability of subspace. Unlike existing methods, we use two matrices to perform feature learning and regression, respectively, such that the proposed approach can obtain more projections and achieve superior performance in classification tasks. The experiments on several datasets show clearly the advantages of our method against other state-of-the-art methods.

p -Laplacian Regularization for Scene Recognition.

The explosive growth of multimedia data on the Internet makes it essential to develop innovative machine learning algorithms for practical applications especially where only a small number of labeled samples are available. Manifold regularized semi-supervised learning (MRSSL) thus received intensive attention recently because it successfully exploits the local structure of data distribution including both labeled and unlabeled samples to leverage the generalization ability of a learning model. Although there are many representative works in MRSSL, including Laplacian regularization (LapR) and Hessian regularization, how to explore and exploit the local geometry of data manifold is still a challenging problem. In this paper, we introduce a fully efficient approximation algorithm of graph p -Laplacian, which significantly saving the computing cost. And then we propose p -LapR (pLapR) to preserve the local geometry. Specifically, p -Laplacian is a natural generalization of the standard graph Laplacian and provides convincing theoretical evidence to better preserve the local structure. We apply pLapR to support vector machines and kernel least squares and conduct the implementations for scene recognition. Extensive experiments on the Scene 67 dataset, Scene 15 dataset, and UC-Merced dataset validate the effectiveness of pLapR in comparison to the conventional manifold regularization methods.

Domain-Weighted Majority Voting for Crowdsourcing.

Crowdsourcing labeling systems provide an efficient way to generate multiple inaccurate labels for given observations. If the competence level or the "reputation," which can be explained as the probabilities of annotating the right label, for each crowdsourcing annotators is equal and biased to annotate the right label, majority voting (MV) is the optimal decision rule for merging the multiple labels into a single reliable one. However, in practice, the competence levels of annotators employed by the crowdsourcing labeling systems are often diverse very much. In these cases, weighted MV is more preferred. The weights should be determined by the competence levels. However, since the annotators are anonymous and the ground-truth labels are usually unknown, it is hard to compute the competence levels of the annotators directly. In this paper, we propose to learn the weights for weighted MV by exploiting the expertise of annotators. Specifically, we model the domain knowledge of different annotators with different distributions and treat the crowdsourcing problem as a domain adaptation problem. The annotators provide labels to the source domains and the target domain is assumed to be associated with the ground-truth labels. The weights are obtained by matching the source domains with the target domain. Although the target-domain labels are unknown, we prove that they could be estimated under mild conditions. Both theoretical and empirical analyses verify the effectiveness of the proposed method. Large performance gains are shown for specific data sets.

Response of goose intestinal microflora to the source and level of dietary fiber.

Geese are capable of digesting and making use of a high-fiber diet, but the mechanism is not well understood and would be of great significance for the development and utilization of roughage resources. In this study, we investigated the effect of dietary fiber (source: corn stover and alfalfa, included at 5% or 8%) on microflora in goose intestines. We used 35-day-old Carlos geese in which we first studied the influence of fiber ingestion on diet digestibility and immune organ indices of geese and found that high dietary fiber (8% content) significantly increased feed intake, the digestibility of neutral and acid detergent fiber, and thymus, bursa, and spleen size. Subsequently, we investigated the effect of dietary fiber on the microbial flora in the various intestinal segments by high throughput sequencing. The bacterial diversity and relative abundance were significantly affected by the type and amount of dietary fiber fed, including that of cellulolytic bacteria such as Bacteroides, Ruminococcus, Clostridium, and Pseudomonas spp. Finally, we isolated and identified 8 strains with cellulolytic ability from goose intestine and then analyzed their activities in combination. The optimal combination for cellulase activity was Cerea bacillus and Pseudomonas aeruginosa. This study has laid a theoretical and practical foundation for knowledge of the efficient conversion and utilization of cellulose by geese.

Screening and identification of lignin-degrading bacteria in termite gut and the construction of LiP-expressing recombinant Lactococcus lactis.

Lignin, a common natural polymers, is abundant and complex, and termites can break down and utilize the lignin in their food. In this study an attempt was made to isolate and characterize the lignolytic bacteria from termite (Reticulitermes chinensis Snyder) gut. Two strains (PY12 and MX5) with high lignin peroxidase (LiP) activity were screened using the azure B method. By analyzing their 16S rRNA, the strain PY12 was classified as Enterobacter hormaechei; MX5, as Bacillus licheniformis. We then optimized the different conditions of liquid fermentation medium, and obtained LiP activities of 278 U/L and 256 U/L for PY12 and MX5, respectively. Subsequently, we confirmed the LiP activities of the strains by evaluating their decolorizing effects on various dyes. Finally, we cloned the LiP gene of strain PY12 and successfully transferred it to Lactococcus lactis. We believe that our results provide the theoretical and practical basis for the production of genetically engineered bacteria that produce LiP, thus allowing for the utilization of naturally available lignin as an energy resource.

Coherent Semantic-Visual Indexing for Large-Scale Image Retrieval in the Cloud.

The rapidly increasing number of images on the internet has further increased the need for efficient indexing for digital image searching of large databases. The design of a cloud service that provides high efficiency but compact image indexing remains challenging, partly due to the well-known semantic gap between user queries and the rich semantics of large-scale data sets. In this paper, we construct a novel joint semantic-visual space by leveraging visual descriptors and semantic attributes, which narrows the semantic gap by combining both attributes and indexing into a single framework. Such a joint space embraces the flexibility of coherent semantic-visual indexing, which employs binary codes to boost retrieval speed while maintaining accuracy. To solve the proposed model, we make the following contributions. First, we propose an interactive optimization method to find the joint semantic and visual descriptor space. Second, we prove convergence of our optimization algorithm, which guarantees a good solution after a certain number of iterations. Third, we integrate the semantic-visual joint space system with spectral hashing, which finds an efficient solution to search up to billion-scale data sets. Finally, we design an online cloud service to provide a more efficient online multimedia service. Experiments on two standard retrieval datasets (i.e., Holidays1M, Oxford5K) show that the proposed method is promising compared with the current state-of-the-art and that the cloud system significantly improves performance.

Latent Max-Margin Multitask Learning With Skelets for 3-D Action Recognition.

Recent emergence of low-cost and easy-operating depth cameras has reinvigorated the research in skeleton-based human action recognition. However, most existing approaches overlook the intrinsic interdependencies between skeleton joints and action classes, thus suffering from unsatisfactory recognition performance. In this paper, a novel latent max-margin multitask learning model is proposed for 3-D action recognition. Specifically, we exploit skelets as the mid-level granularity of joints to describe actions. We then apply the learning model to capture the correlations between the latent skelets and action classes each of which accounts for a task. By leveraging structured sparsity inducing regularization, the common information belonging to the same class can be discovered from the latent skelets, while the private information across different classes can also be preserved. The proposed model is evaluated on three challenging action data sets captured by depth cameras. Experimental results show that our model consistently achieves superior performance over recent state-of-the-art approaches.

Manifold Ranking-Based Matrix Factorization for Saliency Detection.

Saliency detection is used to identify the most important and informative area in a scene, and it is widely used in various vision tasks, including image quality assessment, image matching, and object recognition. Manifold ranking (MR) has been used to great effect for the saliency detection, since it not only incorporates the local spatial information but also utilizes the labeling information from background queries. However, MR completely ignores the feature information extracted from each superpixel. In this paper, we propose an MR-based matrix factorization (MRMF) method to overcome this limitation. MRMF models the ranking problem in the matrix factorization framework and embeds query sample labels in the coefficients. By incorporating spatial information and embedding labels, MRMF enforces similar saliency values on neighboring superpixels and ranks superpixels according to the learned coefficients. We prove that the MRMF has good generalizability, and develops an efficient optimization algorithm based on the Nesterov method. Experiments using popular benchmark data sets illustrate the promise of MRMF compared with the other state-of-the-art saliency detection methods.

Ensemble Manifold Rank Preserving for Acceleration-Based Human Activity Recognition.

With the rapid development of mobile devices and pervasive computing technologies, acceleration-based human activity recognition, a difficult yet essential problem in mobile apps, has received intensive attention recently. Different acceleration signals for representing different activities or even a same activity have different attributes, which causes troubles in normalizing the signals. We thus cannot directly compare these signals with each other, because they are embedded in a nonmetric space. Therefore, we present a nonmetric scheme that retains discriminative and robust frequency domain information by developing a novel ensemble manifold rank preserving (EMRP) algorithm. EMRP simultaneously considers three aspects: 1) it encodes the local geometry using the ranking order information of intraclass samples distributed on local patches; 2) it keeps the discriminative information by maximizing the margin between samples of different classes; and 3) it finds the optimal linear combination of the alignment matrices to approximate the intrinsic manifold lied in the data. Experiments are conducted on the South China University of Technology naturalistic 3-D acceleration-based activity dataset and the naturalistic mobile-devices based human activity dataset to demonstrate the robustness and effectiveness of the new nonmetric scheme for acceleration-based human activity recognition.