Maximal Margin Support Vector Machine for Feature Representation and Classification

High-dimensional small sample size data, which may lead to singularity in computation, are becoming increasingly common in the field of pattern recognition. Moreover, it is still an open problem how to extract the most suitable low-dimensional features for the support vector machine (SVM) and simultaneously avoid singularity so as to enhance the SVM's performance. To address these problems, this article designs a novel framework that integrates the discriminative feature extraction and sparse feature selection into the support vector framework to make full use of the classifiers' characteristics to find the optimal/maximal classification margin. As such, the extracted low-dimensional features from high-dimensional data are more suitable for SVM to obtain good performance. Thus, a novel algorithm, called the maximal margin SVM (MSVM), is proposed to achieve this goal. An alternatively iterative learning strategy is adopted in MSVM to learn the optimal discriminative sparse subspace and the corresponding support vectors. The mechanism and the essence of the designed MSVM are revealed. The computational complexity and convergence are also analyzed and validated. Experimental results on some well-known databases (including breastmnist, pneumoniamnist, colon-cancer, etc.) show the great potential of MSVM against classical discriminant analysis methods and SVM-related methods, and the codes can be available on https://www.scholat.com/laizhihui.

mTOR-dependent loss of PON1 secretion and antiphospholipid autoantibody production underlie autoimmunity-mediated cirrhosis in transaldolase deficiency

Transaldolase deficiency predisposes to chronic liver disease progressing from cirrhosis to hepatocellular carcinoma (HCC). Transition from cirrhosis to hepatocarcinogenesis depends on mitochondrial oxidative stress, as controlled by cytosolic aldose metabolism through the pentose phosphate pathway (PPP). Progression to HCC is critically dependent on NADPH depletion and polyol buildup by aldose reductase (AR), while this enzyme protects from carbon trapping in the PPP and growth restriction in TAL deficiency. Although AR inactivation blocked susceptibility to hepatocarcinogenesis, it enhanced growth restriction, carbon trapping in the non-oxidative branch of the PPP and failed to reverse the depletion of glucose 6-phosphate (G6P) and liver cirrhosis. Here, we show that inactivation of the TAL-AR axis results in metabolic stress characterized by reduced mitophagy, enhanced overall autophagy, activation of the mechanistic target of rapamycin (mTOR), diminished glycosylation and secretion of paraoxonase 1 (PON1), production of antiphospholipid autoantibodies (aPL), loss of CD161+ NK cells, and expansion of CD38+ Ito cells, which are responsive to treatment with rapamycin in vivo. The present study thus identifies glycosylation and secretion of PON1 and aPL production as mTOR-dependent regulatory checkpoints of autoimmunity underlying liver cirrhosis in TAL deficiency.

Robust and Precise Facial Landmark Detection by Self-Calibrated Pose Attention Network

Current fully supervised facial landmark detection methods have progressed rapidly and achieved remarkable performance. However, they still suffer when coping with faces under large poses and heavy occlusions for inaccurate facial shape constraints and insufficient labeled training samples. In this article, we propose a semisupervised framework, that is, a self-calibrated pose attention network (SCPAN) to achieve more robust and precise facial landmark detection in challenging scenarios. To be specific, a boundary-aware landmark intensity (BALI) field is proposed to model more effective facial shape constraints by fusing boundary and landmark intensity field information. Moreover, a self-calibrated pose attention (SCPA) model is designed to provide a self-learned objective function that enforces intermediate supervision without label information by introducing a self-calibrated mechanism and a pose attention mask. We show that by integrating the BALI fields and SCPA model into a novel SCPAN, more facial prior knowledge can be learned and the detection accuracy and robustness of our method for faces with large poses and heavy occlusions have been improved. The experimental results obtained for challenging benchmark datasets demonstrate that our approach outperforms state-of-the-art methods in the literature.

High-Performance Adaptive Weak Fault Diagnosis Based on the Global Parameter Optimization Model of a Cascaded Stochastic Resonance System

Stochastic resonance (SR), as a type of noise-assisted signal processing method, has been widely applied in weak signal detection and mechanical weak fault diagnosis. In order to further improve the weak signal detection performance of SR-based approaches and realize high-performance weak fault diagnosis, a global parameter optimization (GPO) model of a cascaded SR system is proposed in this work. The cascaded SR systems, which involve multiple multi-parameter-adjusting SR systems with both bistable and tri-stable potential functions, are first introduced. The fixed-parameter optimization (FPO) model and the GPO models of the cascaded systems to achieve optimal SR outputs are proposed based on the particle swarm optimization (PSO) algorithm. Simulated results show that the GPO model is capable of achieving a better SR output compared to the FPO model with rather good robustness and stability in detecting low signal-to-noise ratio (SNR) weak signals, and the tri-stable cascaded SR system has a better weak signal detection performance compared to the bistable cascaded SR system. Furthermore, the weak fault diagnosis approach based on the GPO model of the tri-stable cascaded system is proposed, and two rolling bearing weak fault diagnosis experiments are performed, thus verifying the effectiveness of the proposed approach in high-performance adaptive weak fault diagnosis.

Stochastic Resonance with Parameter Estimation for Enhancing Unknown Compound Fault Detection of Bearings

Although stochastic resonance (SR) has been widely used to enhance weak fault signatures in machinery and has obtained remarkable achievements in engineering application, the parameter optimization of the existing SR-based methods requires the quantification indicators dependent on prior knowledge of the defects to be detected; for example, the widely used signal-to-noise ratio easily results in a false SR and decreases the detection performance of SR further. These indicators dependent on prior knowledge would not be suitable for real-world fault diagnosis of machinery where their structure parameters are unknown or are not able to be obtained. Therefore, it is necessary for us to design a type of SR method with parameter estimation, and such a method can estimate these parameters of SR adaptively by virtue of the signals to be processed or detected in place of the prior knowledge of the machinery. In this method, the triggered SR condition in second-order nonlinear systems and the synergic relationship among weak periodic signals, background noise and nonlinear systems can be considered to decide parameter estimation for enhancing unknown weak fault characteristics of machinery. Bearing fault experiments were performed to demonstrate the feasibility of the proposed method. The experimental results indicate that the proposed method is able to enhance weak fault characteristics and diagnose weak compound faults of bearings at an early stage without prior knowledge and any quantification indicators, and it presents the same detection performance as the SR methods based on prior knowledge. Furthermore, the proposed method is more simple and less time-consuming than other SR methods based on prior knowledge where a large number of parameters need to be optimized. Moreover, the proposed method is superior to the fast kurtogram method for early fault detection of bearings.

Enhanced robust spatial feature selection and correlation filter learning for UAV tracking

Spatial boundary effect can significantly reduce the performance of a learned discriminative correlation filter (DCF) model. A commonly used method to relieve this effect is to extract appearance features from a wider region of a target. However, this way would introduce unexpected features from background pixels and noises, which will lead to a decrease of the filter's discrimination power. To address this shortcoming, this paper proposes an innovative method called enhanced robust spatial feature selection and correlation filter Learning (EFSCF), which performs jointly sparse feature learning to handle boundary effects effectively while suppressing the influence of background pixels and noises. Unlike the ℓ₂-norm-based tracking approaches that are prone to non-Gaussian noises, the proposed method imposes the ℓ_2,1-norm on the loss term to enhance the robustness against the training outliers. To enhance the discrimination further, a jointly sparse feature selection scheme based on the ℓ_2,1 -norm is designed to regularize the filter in rows and columns simultaneously. To the best of the authors' knowledge, this has been the first work exploring the structural sparsity in rows and columns of a learned filter simultaneously. The proposed model can be efficiently solved by an alternating direction multiplier method. The proposed EFSCF is verified by experiments on four challenging unmanned aerial vehicle datasets under severe noise and appearance changes, and the results show that the proposed method can achieve better tracking performance than the state-of-the-art trackers.

Myoelectric Pattern Recognition Using Gramian Angular Field and Convolutional Neural Networks for Muscle-Computer Interface

In the field of the muscle-computer interface, the most challenging task is extracting patterns from complex surface electromyography (sEMG) signals to improve the performance of myoelectric pattern recognition. To address this problem, a two-stage architecture, consisting of Gramian angular field (GAF)-based 2D representation and convolutional neural network (CNN)-based classification (GAF-CNN), is proposed. To explore discriminant channel features from sEMG signals, sEMG-GAF transformation is proposed for time sequence signal representation and feature modeling, in which the instantaneous values of multichannel sEMG signals are encoded in image form. A deep CNN model is introduced to extract high-level semantic features lying in image-form-based time sequence signals concerning instantaneous values for image classification. An insight analysis explains the rationale behind the advantages of the proposed method. Extensive experiments are conducted on benchmark publicly available sEMG datasets, i.e., NinaPro and CagpMyo, whose experimental results validate that the proposed GAF-CNN method is comparable to the state-of-the-art methods, as reported by previous work incorporating CNN models.

Typicality-Aware Adaptive Similarity Matrix for Unsupervised Learning

Graph-based clustering approaches, especially the family of spectral clustering, have been widely used in machine learning areas. The alternatives usually engage a similarity matrix that is constructed in advance or learned from a probabilistic perspective. However, unreasonable similarity matrix construction inevitably leads to performance degradation, and the sum-to-one probability constraints may make the approaches sensitive to noisy scenarios. To address these issues, the notion of typicality-aware adaptive similarity matrix learning is presented in this study. The typicality (possibility) rather than the probability of each sample being a neighbor of other samples is measured and adaptively learned. By introducing a robust balance term, the similarity between any pairs of samples is only related to the distance between them, yet it is not affected by other samples. Therefore, the impact caused by the noisy data or outliers can be alleviated, and meanwhile, the neighborhood structures can be well captured according to the joint distance between samples and their spectral embeddings. Moreover, the generated similarity matrix has block diagonal properties that are beneficial to correct clustering. Interestingly, the results optimized by the typicality-aware adaptive similarity matrix learning share the common essence with the Gaussian kernel function, and the latter can be directly derived from the former. Extensive experiments on synthetic and well-known benchmark datasets demonstrate the superiority of the proposed idea when comparing with some state-of-the-art methods.

Precise Facial Landmark Detection by Reference Heatmap Transformer

Most facial landmark detection methods predict landmarks by mapping the input facial appearance features to landmark heatmaps and have achieved promising results. However, when the face image is suffering from large poses, heavy occlusions and complicated illuminations, they cannot learn discriminative feature representations and effective facial shape constraints, nor can they accurately predict the value of each element in the landmark heatmap, limiting their detection accuracy. To address this problem, we propose a novel Reference Heatmap Transformer (RHT) by introducing reference heatmap information for more precise facial landmark detection. The proposed RHT consists of a Soft Transformation Module (STM) and a Hard Transformation Module (HTM), which can cooperate with each other to encourage the accurate transformation of the reference heatmap information and facial shape constraints. Then, a Multi-Scale Feature Fusion Module (MSFFM) is proposed to fuse the transformed heatmap features and the semantic features learned from the original face images to enhance feature representations for producing more accurate target heatmaps. To the best of our knowledge, this is the first study to explore how to enhance facial landmark detection by transforming the reference heatmap information. The experimental results from challenging benchmark datasets demonstrate that our proposed method outperforms the state-of-the-art methods in the literature.

Guided Discrimination and Correlation Subspace Learning for Domain Adaptation

As a branch of transfer learning, domain adaptation leverages useful knowledge from a source domain to a target domain for solving target tasks. Most of the existing domain adaptation methods focus on how to diminish the conditional distribution shift and learn invariant features between different domains. However, two important factors are overlooked by most existing methods: 1) the transferred features should be not only domain invariant but also discriminative and correlated, and 2) negative transfer should be avoided as much as possible for the target tasks. To fully consider these factors in domain adaptation, we propose a guided discrimination and correlation subspace learning (GDCSL) method for cross-domain image classification. GDCSL considers the domain-invariant, category-discriminative, and correlation learning of data. Specifically, GDCSL introduces the discriminative information associated with the source and target data by minimizing the intraclass scatter and maximizing the interclass distance. By designing a new correlation term, GDCSL extracts the most correlated features from the source and target domains for image classification. The global structure of the data can be preserved in GDCSL because the target samples are represented by the source samples. To avoid negative transfer issues, we use a sample reweighting method to detect target samples with different confidence levels. A semi-supervised extension of GDCSL (Semi-GDCSL) is also proposed, and a novel label selection scheme is introduced to ensure the correction of the target pseudo-labels. Comprehensive and extensive experiments are conducted on several cross-domain data benchmarks. The experimental results verify the effectiveness of the proposed methods over state-of-the-art domain adaptation methods.

Canonical Correlation Analysis With Low-Rank Learning for Image Representation

As a multivariate data analysis tool, canonical correlation analysis (CCA) has been widely used in computer vision and pattern recognition. However, CCA uses Euclidean distance as a metric, which is sensitive to noise or outliers in the data. Furthermore, CCA demands that the two training sets must have the same number of training samples, which limits the performance of CCA-based methods. To overcome these limitations of CCA, two novel canonical correlation learning methods based on low-rank learning are proposed in this paper for image representation, named robust canonical correlation analysis (robust-CCA) and low-rank representation canonical correlation analysis (LRR-CCA). By introducing two regular matrices, the training sample numbers of the two training datasets can be set as any values without any limitation in the two proposed methods. Specifically, robust-CCA uses low-rank learning to remove the noise in the data and extracts the maximization correlation features from the two learned clean data matrices. The nuclear norm and L₁ -norm are used as constraints for the learned clean matrices and noise matrices, respectively. LRR-CCA introduces low-rank representation into CCA to ensure that the correlative features can be obtained in low-rank representation. To verify the performance of the proposed methods, five publicly image databases are used to conduct extensive experiments. The experimental results demonstrate the proposed methods outperform state-of-the-art CCA-based and low-rank learning methods.

Research on a Bearing Fault Enhancement Diagnosis Method with Convolutional Neural Network Based on Adaptive Stochastic Resonance

As a powerful feature extraction tool, a convolutional neural network (CNN) has strong adaptability for big data applications such as bearing fault diagnosis, whereas the classification performance is limited when the quality of raw signals is poor. In this paper, stochastic resonance (SR), which provides an advanced feature enhancement approach for weak signals with strong background noise, is introduced as a data pre-processing method for the CNN to improve its classification performance. First, a multiparameter adjusting bistable Duffing system that can achieve SR under large-parameter weak signals is introduced. A hybrid optimization algorithm (HOA) combining the genetic algorithm (GA) and the simulated annealing (SA) is proposed to adaptively obtain the optimized parameters and output signal-to-noise ratio (SNR) of the Duffing system. Therefore, the data optimization based on the multiparameter-adjusting SR of Duffing system can be realized. An SR-based mapping method is further proposed to convert the outputs of the Duffing system into grey images, which can be further processed by a normal CNN with batch normalization (BN) layers and dropout layers. After verifying the feasibility of the HOA in multiparameter optimization of the Duffing system, the bearing fault data set from the CWRU bearing data center was processed by the proposed fault enhancement classification and identification method. The research showed that the weak features of the bearing signals could be enhanced significantly through the adaptive multiparameter optimization of SR, and classification accuracies for 10 categories of bearing signals could achieve 100% and those for 20 categories could achieve more than 96.9%, which is better than other methods. The influences of the population number on the classification accuracies and calculation time were further studied, and the feature map and network visualization are presented. It was demonstrated that the proposed method can realize high-performance fault enhancement classification and identification.

Weighted Correlation Embedding Learning for Domain Adaptation

Domain adaptation leverages rich knowledge from a related source domain so that it can be used to perform tasks in a target domain. For more knowledge to be obtained under relaxed conditions, domain adaptation methods have been widely used in pattern recognition and image classification. However, most of the existing domain adaptation methods only consider how to minimize different distributions of the source and target domains, which neglects what should be transferred for a specific task and suffers negative transfer by distribution outliers. To address these problems, in this paper, we propose a novel domain adaptation method called weighted correlation embedding learning (WCEL) for image classification. In the WCEL approach, we seamlessly integrated correlation learning, graph embedding, and sample reweighting into a unified learning model. Specifically, we extracted the maximum correlated features from the source and target domains for image classification tasks. In addition, two graphs were designed to preserve the discriminant information from interclass samples and neighborhood relations in intraclass samples. Furthermore, to prevent the negative transfer problem, we developed an efficient sample reweighting strategy to predict the target with different confidence levels. To verify the performance of the proposed method in image classification, extensive experiments were conducted with several benchmark databases, verifying the superiority of the WCEL method over other state-of-the-art domain adaptation algorithms.

Robust Twin Bounded Support Vector Classifier With Manifold Regularization

Support vector machine (SVM), as a supervised learning method, has different kinds of varieties with significant performance. In recent years, more research focused on nonparallel SVM, where twin SVM (TWSVM) is the typical one. In order to reduce the influence of outliers, more robust distance measurements are considered in these methods, but the discriminability of the models is neglected. In this article, we propose robust manifold twin bounded SVM (RMTBSVM), which considers both robustness and discriminability. Specifically, a novel norm, that is, capped L₁-norm, is used as the distance metric for robustness, and a robust manifold regularization is added to further improve the robustness and classification performance. In addition, we also use the kernel method to extend the proposed RMTBSVM for nonlinear classification. We introduce the optimization problems of the proposed model. Subsequently, effective algorithms for both linear and nonlinear cases are proposed and proved to be convergent. Moreover, the experiments are conducted to verify the effectiveness of our model. Compared with other methods under the SVM framework, the proposed RMTBSVM shows better classification accuracy and robustness.

Robust Facial Landmark Detection by Multiorder Multiconstraint Deep Networks

Recently, heatmap regression has been widely explored in facial landmark detection and obtained remarkable performance. However, most of the existing heatmap regression-based facial landmark detection methods neglect to explore the high-order feature correlations, which is very important to learn more representative features and enhance shape constraints. Moreover, no explicit global shape constraints have been added to the final predicted landmarks, which leads to a reduction in accuracy. To address these issues, in this article, we propose a multiorder multiconstraint deep network (MMDN) for more powerful feature correlations and shape constraints' learning. Especially, an implicit multiorder correlating geometry-aware (IMCG) model is proposed to introduce the multiorder spatial correlations and multiorder channel correlations for more discriminative representations. Furthermore, an explicit probability-based boundary-adaptive regression (EPBR) method is developed to enhance the global shape constraints and further search the semantically consistent landmarks in the predicted boundary for robust facial landmark detection. It is interesting to show that the proposed MMDN can generate more accurate boundary-adaptive landmark heatmaps and effectively enhance shape constraints to the predicted landmarks for faces with large pose variations and heavy occlusions. Experimental results on challenging benchmark data sets demonstrate the superiority of our MMDN over state-of-the-art facial landmark detection methods.

Generalized Embedding Regression: A Framework for Supervised Feature Extraction

Sparse discriminative projection learning has attracted much attention due to its good performance in recognition tasks. In this article, a framework called generalized embedding regression (GER) is proposed, which can simultaneously perform low-dimensional embedding and sparse projection learning in a joint objective function with a generalized orthogonal constraint. Moreover, the label information is integrated into the model to preserve the global structure of data, and a rank constraint is imposed on the regression matrix to explore the underlying correlation structure of classes. Theoretical analysis shows that GER can obtain the same or approximate solution as some related methods with special settings. By utilizing this framework as a general platform, we design a novel supervised feature extraction approach called jointly sparse embedding regression (JSER). In JSER, we construct an intrinsic graph to characterize the intraclass similarity and a penalty graph to indicate the interclass separability. Then, the penalty graph Laplacian is used as the constraint matrix in the generalized orthogonal constraint to deal with interclass marginal points. Moreover, the L_2,1 -norm is imposed on the regression terms for robustness to outliers and data's variations and the regularization term for jointly sparse projection learning, leading to interesting semantic interpretability. An effective iterative algorithm is elaborately designed to solve the optimization problem of JSER. Theoretically, we prove that the subproblem of JSER is essentially an unbalanced Procrustes problem and can be solved iteratively. The convergence of the designed algorithm is also proved. Experimental results on six well-known data sets indicate the competitive performance and latent properties of JSER.

Salience-Guided Iterative Asymmetric Mutual Hashing for Fast Person Re-Identification

Person Re-identification (ReID) aims to retrieve the pedestrian with the same identity across different views. Existing studies mainly focus on improving accuracy, while ignoring their efficiency. Recently, several hash based methods have been proposed. Despite their improvement in efficiency, there still exists an unacceptable gap in accuracy between these methods and real-valued ones. Besides, few attempts have been made to simultaneously explicitly reduce redundancy and improve discrimination of hash codes, especially for short ones. Integrating Mutual learning may be a possible solution to reach this goal. However, it fails to utilize the complementary effect of teacher and student models. Additionally, it will degrade the performance of teacher models by treating two models equally. To address these issues, we propose a salience-guided iterative asymmetric mutual hashing (SIAMH) to achieve high-quality hash code generation and fast feature extraction. Specifically, a salience-guided self-distillation branch (SSB) is proposed to enable SIAMH to generate hash codes based on salience regions, thus explicitly reducing the redundancy between codes. Moreover, a novel iterative asymmetric mutual training strategy (IAMT) is proposed to alleviate drawbacks of common mutual learning, which can continuously refine the discriminative regions for SSB and extract regularized dark knowledge for two models as well. Extensive experiment results on five widely used datasets demonstrate the superiority of the proposed method in efficiency and accuracy when compared with existing state-of-the-art hashing and real-valued approaches. The code is released at https://github.com/Vill-Lab/SIAMH.

Analysis of mutation status and homologous recombination deficiency in tumors of patients with germline BRCA1 or BRCA2 mutations and metastatic breast cancer: OlympiAD

BACKGROUND

Presence of a germline BRCA1 and/or BRCA2 mutation (gBRCAm) may sensitize tumors to poly(ADP-ribose) polymerase (PARP) inhibition via inactivation of the second allele, resulting in gene-specific loss of heterozygosity (gsLOH) and homologous recombination deficiency (HRD). Here we explore whether tissue sample testing provides an additional route to germline testing to inform treatment selection for PARP inhibition.

PATIENTS AND METHODS

In this prespecified exploratory analysis, BRCA1 and/or BRCA2 mutations in blood samples (gBRCAm) and tumor tissue (tBRCAm) were analyzed from patients with human epidermal growth factor receptor 2 (HER2)-negative metastatic breast cancer and known gBRCAm, enrolled in the phase III OlympiAD trial. The frequency and nature of tBRCAm, HRD score status [HRD-positive (score ≥42) versus HRD-negative (score <42) using the Myriad myChoice® CDx test] and rates of gsLOH were determined, and their impact on clinical efficacy (objective response rate and progression-free survival) was explored.

RESULTS

Tissue samples from 161/302 patients yielded tBRCAm, HRD and gsLOH data for 143 (47%), 129 (43%) and 125 (41%) patients, respectively. Concordance between gBRCAm and tBRCAm was 99%. gsLOH was observed in 118/125 (94%) patients [BRCA1m, 73/76 (96%); BRCA2m, 45/49 (92%)]. A second mutation event was recorded for two of the three BRCA1m patients without gsLOH. The incidence of HRD-negative was 16% (21/129) and was more common for BRCA2m (versus BRCA1m) and/or for hormone receptor-positive (versus triple-negative) disease. Olaparib antitumor activity was observed irrespective of HRD score.

CONCLUSIONS

gBRCAm identified in patients with HER2-negative metastatic breast cancer by germline testing in blood was also identified by tumor tissue testing. gsLOH was common, indicating a high rate of biallelic inactivation in metastatic breast cancer. Olaparib activity was seen regardless of gsLOH status or HRD score. Thus, additional tumor testing to inform PARP inhibitor treatment selection may not be supported for these patients.

Learning Dynamic Relationships for Facial Expression Recognition Based on Graph Convolutional Network

Facial action units (AUs) analysis plays an important role in facial expression recognition (FER). Existing deep spectral convolutional networks (DSCNs) have made encouraging performance for FER based on a set of facial local regions and a predefined graph structure. However, these regions do not have close relationships to AUs, and DSCNs cannot model the dynamic spatial dependencies of these regions for estimating different facial expressions. To tackle these issues, we propose a novel double dynamic relationships graph convolutional network (DDRGCN) to learn the strength of the edges in the facial graph by a trainable weighted adjacency matrix. We construct facial graph data by 20 regions of interest (ROIs) guided by different facial AUs. Furthermore, we devise an efficient graph convolutional network in which the inherent dependencies of vertices in the facial graph can be learned automatically during network training. Notably, the proposed model only has 110K parameters and 0.48MB model size, which is significantly less than most existing methods. Experiments on four widely-used FER datasets demonstrate that the proposed dynamic relationships graph network achieves superior results compared to existing light-weight networks, not just in terms of accuracy but also model size and speed.

WaveCNet: Wavelet Integrated CNNs to Suppress Aliasing Effect for Noise-Robust Image Classification

Though widely used in image classification, convolutional neural networks (CNNs) are prone to noise interruptions, i.e. the CNN output can be drastically changed by small image noise. To improve the noise robustness, we try to integrate CNNs with wavelet by replacing the common down-sampling (max-pooling, strided-convolution, and average pooling) with discrete wavelet transform (DWT). We firstly propose general DWT and inverse DWT (IDWT) layers applicable to various orthogonal and biorthogonal discrete wavelets like Haar, Daubechies, and Cohen, etc., and then design wavelet integrated CNNs (WaveCNets) by integrating DWT into the commonly used CNNs (VGG, ResNets, and DenseNet). During the down-sampling, WaveCNets apply DWT to decompose the feature maps into the low-frequency and high-frequency components. Containing the main information including the basic object structures, the low-frequency component is transmitted into the following layers to generate robust high-level features. The high-frequency components are dropped to remove most of the data noises. The experimental results show that WaveCNets achieve higher accuracy on ImageNet than various vanilla CNNs. We have also tested the performance of WaveCNets on the noisy version of ImageNet, ImageNet-C and six adversarial attacks, the results suggest that the proposed DWT/IDWT layers could provide better noise-robustness and adversarial robustness. When applying WaveCNets as backbones, the performance of object detectors (i.e., faster R-CNN and RetinaNet) on COCO detection dataset are consistently improved. We believe that suppression of aliasing effect, i.e. separation of low frequency and high frequency information, is the main advantages of our approach. The code of our DWT/IDWT layer and different WaveCNets are available at https://github.com/CVI-SZU/WaveCNet.

Tongxin formula protects H9c2 cardiomyocytes from cobalt chloride-induced hypoxic injury via inhibition of apoptosis

In this study, the effect of the Tongxin formula (TXF) on the apoptosis of H9c2 cardiomyocytes induced by cobalt chloride (CoCl₂) was investigated, and the potential mechanism was explored. A hypoxic injury model of H9c2 cardiomyocytes was established using CoCl₂. The cell viability was measured using a Cell Counting Kit-8 assay. The lactate dehydrogenase (LDH) release and caspase-3 activity were measured using spectrophotometry. The apoptosis was measured via Annexin V-FITC/PI staining and flow cytometry. The changes in the mitochondrial membrane potential were examined using immunofluorescence microscopy following the loading of JC-1 probes. The expressions of apoptosis-related proteins and key proteins in the phosphatidylinositol 3-kinase/protein kinase B (PI3K/Akt) pathway were examined via immunoblotting. The different TXF concentrations studied significantly improved the percentage of viability of cardiomyocytes with hypoxic injury, and the LDH release, apoptotic rate, caspase-3 activity, and levels of cleaved caspase-3 protein were reduced in the injured cells. Additionally, the TXF group had increased mitochondrial membrane potential, upregulated expression of Bcl-2 and p-Akt proteins, and significantly reduced expression of cleaved caspase-3 protein in the cells with hypoxic injury. Moreover, in the TXF group, the treatment significantly reduced the BAX protein expression, but the difference was not statistically significant compared with the CoCl2 group. In this study, TXF regulated the expression of apoptosis-related proteins, inhibited apoptosis, increased the mitochondrial membrane potential, and alleviated damage to the mitochondrial membrane, thereby protecting the cardiomyocytes from hypoxic injury. The underlying mechanism could be related to activation of the PI3K/Akt signaling pathway and upregulation of the Bcl-2 protein.

A self-supervised feature-standardization-block for cross-domain lung disease classification

With the advance of deep learning technology, convolutional neural network (CNN) has been wildly used and achieved the state-of-the-art performances in the area of medical image classification. However, most existing medical image classification methods conduct their experiments on only one public dataset. When applying a well-trained model to a different dataset selected from different sources, the model usually shows large performance degradation and needs to be fine-tuned before it can be applied to the new dataset. The goal of this work is trying to solve the cross-domain image classification problem without using data from target domain. In this work, we designed a self-supervised plug-and-play feature-standardization-block (FSB) which consisting of image normalization (INB), contrast enhancement (CEB) and boundary detection blocks (BDB), to extract cross-domain robust feature maps for deep learning framework, and applied the network for chest x-ray-based lung diseases classification. Three classic deep networks, i.e. VGG, Xception and DenseNet and four chest x-ray lung diseases datasets were employed for evaluating the performance. The experimental result showed that when employing feature-standardization-block, all three networks showed better domain adaption performance. The image normalization, contrast enhancement and boundary detection blocks achieved in average 2%, 2% and 5% accuracy improvement, respectively. By combining all three blocks, feature-standardization-block achieved in average 6% accuracy improvement.

An integrated network pharmacology and transcriptomic method to explore the mechanism of the total Rhizoma Coptidis alkaloids in improving diabetic nephropathy

ETHNOPHARMACOLOGICAL RELEVANCE

Rhizoma Coptidis (RC) is a traditional Chinese medicine (TCM) used for treating diabetes (Xiao Ke Zheng), which is firstly recorded in Shennong Bencao Jing. Modern pharmacological studies have confirmed that RC has beneficial effects on diabetes and its complications. Alkaloids are the main active pharmacological component of RC. However, the effect and molecular mechanism of total Rhizoma Coptidis alkaloids (TRCA) in improving diabetic nephropathy (DN) are still unclear.

AIM OF THE STUDY

To verify the effect of TRCA in the treatment of DN and clarify the molecular mechanism by combining network pharmacology and transcriptomic.

MATERIALS AND METHODS

Eight-week-old db/db mice were orally administered with normal saline, 100 mg/kg TRCA, and 100 mg/kg berberine (BBR) for 8 weeks. Serum, urine, and kidney samples were collected to measure biological indicators and observe renal pathological changes. Then, the molecular mechanism of TRCA improving DN was predicted by the network pharmacology. Briefly, the main active alkaloids components of TRCA and their targets were collected from the database, as well as the potential targets of DN. Using the Cytoscape software to visualize the interactive network diagram of "ingredient-target". The GO and KEGG pathways enrichment analysis of the core targets were executed by Metascape. Furthermore, RNA-seq was used to get whole transcriptomes from the kidneys of db/m mice, db/db mice, and db/db mice treated with TRCA. The key differentially expressed genes (DEGs) were gathered to conduct the GO and KEGG pathways enrichment analysis. Finally, the potential pathways were validated by western blotting.

RESULTS

The administration of BBR or TRCA for 8 weeks significantly reduced the fasting blood glucose (FBG) and body weight of db/db mice, and improved their renal function and lipid disorders. According to H&E, PAS, and Masson staining, both the BBR and TRCA could alleviate renal damage and fibrosis. The Venn diagram had shown that seven alkaloids ingredients collected from TRCA regulated 85 common targets merged in the TRCA and DN. The results of RNA-seq indicated that there are 121 potential targets for TRCA treatment on DN. Intriguingly, both the AGE-RAGE signaling pathway and the PI3k-Akt signaling pathway were included in the KEGG pathways enrichment results of network pharmacology and RNA-seq. Moreover, we verified that TRCA down-regulated the expression of related proteins in the AGEs-RAGE-TGFβ/Smad2 and PI3K-Akt pathways in the kidney tissues.

CONCLUSIONS

In summary, the renal protection of TRCA on DN may be related to activation of the AGEs-RAGE-TGFβ/Smad2 and PI3K-Akt signaling pathways.

Androgen deprivation-induced elevated nuclear SIRT1 promotes prostate tumor cell survival by reactivation of AR signaling

The NAD⁺-dependent deacetylase, Sirtuin 1 (SIRT1) is involved in prostate cancer pathogenesis. However, the actual contribution is unclear as some reports propose a protective role while others suggest it is harmful. We provide evidence for a contextual role for SIRT1 in prostate cancer. Our data show that (i) mice orthotopically implanted with SIRT1-silenced LNCaP cells produced smaller tumors; (ii) SIRT1 suppression mimicked AR inhibitory effects in hormone responsive LNCaP cells; and (iii) caused significant reduction in gene signatures associated with E2F and MYC targets in AR-null PC-3 and E2F and mTORC1 signaling in castrate-resistant ARv7 positive 22Rv1 cells. Our findings further show increased nuclear SIRT1 (nSIRT1) protein under androgen-depleted relative to androgen-replete conditions in prostate cancer cell lines. Silencing SIRT1 resulted in decreased recruitment of AR to PSA enhancer selectively under androgen-deprivation conditions. Prostate cancer outcome data show that patients with higher levels of nSIRT1 progress to advanced disease relative to patients with low nSIRT1 levels. Collectively, we demonstrate that lowering SIRT1 levels potentially provides new avenues to effectively prevent prostate cancer recurrence.

Robust Face Alignment by Multi-Order High-Precision Hourglass Network

Heatmap regression (HR) has become one of the mainstream approaches for face alignment and has obtained promising results under constrained environments. However, when a face image suffers from large pose variations, heavy occlusions and complicated illuminations, the performances of HR methods degrade greatly due to the low resolutions of the generated landmark heatmaps and the exclusion of important high-order information that can be used to learn more discriminative features. To address the alignment problem for faces with extremely large poses and heavy occlusions, this paper proposes a heatmap subpixel regression (HSR) method and a multi-order cross geometry-aware (MCG) model, which are seamlessly integrated into a novel multi-order high-precision hourglass network (MHHN). The HSR method is proposed to achieve high-precision landmark detection by a well-designed subpixel detection loss (SDL) and subpixel detection technology (SDT). At the same time, the MCG model is able to use the proposed multi-order cross information to learn more discriminative representations for enhancing facial geometric constraints and context information. To the best of our knowledge, this is the first study to explore heatmap subpixel regression for robust and high-precision face alignment. The experimental results from challenging benchmark datasets demonstrate that our approach outperforms state-of-the-art methods in the literature.

Robust facial landmark detection by cross-order cross-semantic deep network

Recently, convolutional neural networks (CNNs)-based facial landmark detection methods have achieved great success. However, most of existing CNN-based facial landmark detection methods have not attempted to activate multiple correlated facial parts and learn different semantic features from them that they can not accurately model the relationships among the local details and can not fully explore more discriminative and fine semantic features, thus they suffer from partial occlusions and large pose variations. To address these problems, we propose a cross-order cross-semantic deep network (CCDN) to boost the semantic features learning for robust facial landmark detection. Specifically, a cross-order two-squeeze multi-excitation (CTM) module is proposed to introduce the cross-order channel correlations for more discriminative representations learning and multiple attention-specific part activation. Moreover, a novel cross-order cross-semantic (COCS) regularizer is designed to drive the network to learn cross-order cross-semantic features from different activation for facial landmark detection. It is interesting to show that by integrating the CTM module and COCS regularizer, the proposed CCDN can effectively activate and learn more fine and complementary cross-order cross-semantic features to improve the accuracy of facial landmark detection under extremely challenging scenarios. Experimental results on challenging benchmark datasets demonstrate the superiority of our CCDN over state-of-the-art facial landmark detection methods.

Technical validation of a new microfluidic device for enrichment of CTCs from large volumes of blood by using buffy coats to mimic diagnostic leukapheresis products

Diagnostic leukapheresis (DLA) enables to sample larger blood volumes and increases the detection of circulating tumor cells (CTC) significantly. Nevertheless, the high excess of white blood cells (WBC) of DLA products remains a major challenge for further downstream CTC enrichment and detection. To address this problem, we tested the performance of two label-free CTC technologies for processing DLA products. For the testing purposes, we established ficollized buffy coats (BC) with a WBC composition similar to patient-derived DLA products. The mimicking-DLA samples (with up to 400 × 106 WBCs) were spiked with three different tumor cell lines and processed with two versions of a spiral microfluidic chip for label-free CTC enrichment: the commercially available ClearCell FR1 biochip and a customized DLA biochip based on a similar enrichment principle, but designed for higher throughput of cells. While the samples processed with FR1 chip displayed with increasing cell load significantly higher WBC backgrounds and decreasing cell recovery, the recovery rates of the customized DLA chip were stable, even if challenged with up to 400 × 106 WBCs (corresponding to around 120 mL peripheral blood or 10% of a DLA product). These results indicate that the further up-scalable DLA biochip has potential to process complete DLA products from 2.5 L of peripheral blood in an affordable way to enable high-volume CTC-based liquid biopsies.

Robust Flexible Preserving Embedding

Neighborhood preserving embedding (NPE) has been proposed to encode overall geometry manifold embedding information. However, the class-special structure of the data is destroyed by noise or outliers existing in the data. To address this problem, in this article, we propose a novel embedding approach called robust flexible preserving embedding (RFPE). First, RFPE recovers the noisy data by low-rank learning and obtains clean data. Then, the clean data are used to learn the projection matrix. In this way, the projective learning is totally unaffected by noise or outliers. By encoding a flexible regularization term, RFPE can keep the property of the data points with a nonlinear manifold and be more flexible. RFPE searches the optimal projective subspace for feature extraction. In addition, we also extend the proposed RFPE to a kernel case and propose kernel RFPE (KRFPE). Extensive experiments on six public image databases show the superiority of the proposed methods over other state-of-the-art methods.

Single-site laparoscopic percutaneous extraperitoneal closure (SLPEC) of hernia sac high ligation using an ordinary taper needle: a novel technique for pediatric inguinal hernia

PURPOSE

Laparoscopic high ligation of the internal inguinal ring is an alternative procedure for treatment of pediatric inguinal hernia (PIH), with a major trend toward increasing use of extracorporeal knotting and decreasing use of working ports. We have utilized this laparoscopic technique to treat the entire spectrum of PIH (including incarcerated cases) for more than 17 years, and the technique continues to evolve and improve. We herein report our latest modification of this minimally invasive technique, namely single-site laparoscopic percutaneous extraperitoneal closure (SLPEC) of hernia sac high ligation using an ordinary taper needle, and evaluate its safety and efficacy.

METHODS

From July 2016 to July 2019, 790 children with indirect PIH were treated by laparoscopic surgery. All patients underwent high ligation surgery with a modified single-site laparoscopic technique mainly performed by extracorporeal suturing with an ordinary closed-eye taper needle (1/2 arc 11 × 34). The clinical data were retrospectively analyzed.

RESULTS

All surgeries were successful without serious complications. A contralateral patent processus vaginalis (CPPV) was found intraoperatively and subsequently repaired in 190 patients (25.4%). The mean operative time was 15 min (8-25 min) for 557 unilateral hernias and 21 min (14-36 min) for 233 bilateral hernias. The mean postoperative stay was 20 h. Minor complications occurred in five patients (0.63%) and were managed properly, with no major impact on the final outcomes. No recurrence was noted in the patients who were followed up for 6-42 months. No obvious scar was present postoperatively.

CONCLUSION

Modified SLPEC of hernia sac high ligation using an ordinary taper needle for repair of indirect PIH is a safe, reliable, and minimally invasive procedure with satisfactory outcome, with no special device being needed. It is easy to learn and perform and is worthy of popularization in the clinical setting.