Complete Region of Interest for Unconstrained Palmprint Recognition.

Unconstrained palmprint images have shown great potential for recognition applications due to their lower restrictions regarding hand poses and backgrounds during contactless image acquisition. However, they face two challenges: 1) unclear palm contours and finger-valley points of unconstrained palmprint images make it difficult to locate landmarks to crop the palmprint region of interest (ROI); and 2) large intra-class diversities of unconstrained palmprint images hinder the learning of intra-class-invariant palmprint features. In this paper, we propose to directly extract the complete palmprint region as the ROI (CROI) using the detection-style CenterNet without requiring the detection of any landmarks, and large intra-class diversities may occur. To address this, we further propose a palmprint feature alignment and learning hybrid network (PalmALNet) for unconstrained palmprint recognition. Specifically, we first exploit and align the multi-scale shallow representation of unconstrained palmprint images via deformable convolution and alignment-aware supervision, such that the pixel gaps of the intra-class palmprint CROIs can be minimized in shallow feature space. Then, we develop multiple triple-attention learning modules by integrating spatial, channel, and self-attention operations into convolution to adaptively learn and highlight the latent identity-invariant palmprint information, enhancing the overall discriminative power of the palmprint features. Extensive experimental results on four challenging palmprint databases demonstrate the promising effectiveness of both the proposed PalmALNet and CROI for unconstrained palmprint recognition.

Learning Attention in the Frequency Domain for Flexible Real Photograph Denoising.

Recent advancements in deep learning techniques have pushed forward the frontiers of real photograph denoising. However, due to the inherent pooling operations in the spatial domain, current CNN-based denoisers are biased towards focusing on low-frequency representations, while discarding the high-frequency components. This will induce a problem for suboptimal visual quality as the image denoising tasks target completely eliminating the complex noises and recovering all fine-scale and salient information. In this work, we tackle this challenge from the frequency perspective and present a new solution pipeline, coined as frequency attention denoising network (FADNet). Our key idea is to build a learning-based frequency attention framework, where the feature correlations on a broader frequency spectrum can be fully characterized, thus enhancing the representational power of the network across multiple frequency channels. Based on this, we design a cascade of adaptive instance residual modules (AIRMs). In each AIRM, we first transform the spatial-domain features into the frequency space. Then, a learning-based frequency attention framework is devised to explore the feature inter-dependencies converted in the frequency domain. Besides this, we introduce an adaptive layer by leveraging the guidance of the estimated noise map and intermediate features to meet the challenges of model generalization in the noise discrepancy. The effectiveness of our method is demonstrated on several real camera benchmark datasets, with superior denoising performance, generalization capability, and efficiency versus the state-of-the-art.

Succinylation of Park7 activates a protective metabolic response to acute kidney injury.

Acute kidney injury (AKI) is extremely prevalent among hospitalizations and presents a significant risk for the development of chronic kidney disease and increased mortality. Ischemia caused by shock, trauma, and transplant are common causes of AKI. To attenuate ischemic AKI therapeutically, we need a better understanding of the physiological and cellular mechanisms underlying damage. Instances of ischemia are most damaging in proximal tubule epithelial cells (PTECs) where hypoxic signaling cascades, and perhaps more rapidly, posttranslational modifications (PTMs), act in concert to change cellular metabolism. Here, we focus on the effects of the understudied PTM, lysine succinylation. We have previously shown a protective effect of protein hypersuccinylation on PTECs after depletion of the desuccinylase sirtuin5. General trends in the results suggested that hypersuccinylation led to upregulation of peroxisomal activity and was protective against kidney injury. Included in the list of changes was the Parkinson's-related deglycase Park7. There is little known about any links between peroxisome activity and Park7. In this study, we show in vitro and in vivo that Park7 has a crucial role in protection from AKI and upregulated peroxisome activity. These data in combination with published results of Park7's protective role in cardiovascular damage and chronic kidney disease lead us to hypothesize that succinylation of Park7 may ameliorate oxidative damage resulting from AKI and prevent disease progression. This novel mechanism provides a potential therapeutic mechanism that can be targeted.NEW & NOTEWORTHY Succinylation is an understudied posttranslational modification that has been shown to increase peroxisomal activity. Furthermore, increased peroxisomal activity has been shown to reduce oxidative stress and protect proximal tubules after acute kidney injury. Analysis of mass spectrometry succinylomic and proteomic data reveals a novel role for Parkinson's related Park7 in mediating Nrf2 antioxidant response after kidney injury. This novel protection pathway provides new insights for kidney injury prevention and development of novel therapeutics.

Tensorized Multi-View Low-Rank Approximation Based Robust Hand-Print Recognition.

Since hand-print recognition, i.e., palmprint, finger-knuckle-print (FKP), and hand-vein, have significant superiority in user convenience and hygiene, it has attracted greater enthusiasm from researchers. Seeking to handle the long-standing interference factors, i.e., noise, rotation, shadow, in hand-print images, multi-view hand-print representation has been proposed to enhance the feature expression by exploiting multiple characteristics from diverse views. However, the existing methods usually ignore the high-order correlations between different views or fuse very limited types of features. To tackle these issues, in this paper, we present a novel tensorized multi-view low-rank approximation based robust hand-print recognition method (TMLA_RHR), which can dexterously manipulate the multi-view hand-print features to produce a high-compact feature representation. To achieve this goal, we formulate TMLA_RHR by two key components, i.e., aligned structure regression loss and tensorized low-rank approximation, in a joint learning model. Specifically, we treat the low-rank representation matrices of different views as a tensor, which is regularized with a low-rank constraint. It models the across information between different views and reduces the redundancy of the learned sub-space representations. Experimental results on eight real-world hand-print databases prove the superiority of the proposed method in comparison with other state-of-the-art related works.

Myoglobin Inhibits Breast Cancer Cell Fatty Acid Oxidation and Migration via Heme-dependent Oxidant Production and Not Fatty Acid Binding.

The monomeric heme protein myoglobin (Mb), traditionally thought to be expressed exclusively in cardiac and skeletal muscle, is now known to be expressed in approximately 40% of breast tumors. While Mb expression is associated with better patient prognosis, the molecular mechanisms by which Mb limits cancer progression are unclear. In muscle, Mb's predominant function is oxygen storage and delivery, which is dependent on the protein's heme moiety. However, prior studies demonstrate that the low levels of Mb expressed in cancer cells preclude this function. Recent studies propose a novel fatty acid binding function for Mb via a lysine residue (K46) in the heme pocket. Given that cancer cells can upregulate fatty acid oxidation (FAO) to maintain energy production for cytoskeletal remodeling during cell migration, we tested whether Mb-mediated fatty acid binding modulates FAO to decrease breast cancer cell migration. We demonstrate that the stable expression of human Mb in MDA-MB-231 breast cancer cells decreases cell migration and FAO. Site-directed mutagenesis of Mb to disrupt Mb fatty acid binding did not reverse Mb-mediated attenuation of FAO or cell migration in these cells. In contrast, cells expressing Apo-Mb, in which heme incorporation was disrupted, showed a reversal of Mb-mediated attenuation of FAO and cell migration, suggesting that Mb attenuates FAO and migration via a heme-dependent mechanism rather than through fatty acid binding. To this end, we show that Mb's heme-dependent oxidant generation propagates dysregulated gene expression of migratory genes, and this is reversed by catalase treatment. Collectively, these data demonstrate that Mb decreases breast cancer cell migration, and this effect is due to heme-mediated oxidant production rather than fatty acid binding. The implication of these results will be discussed in the context of therapeutic strategies to modulate oxidant production and Mb in tumors. Highlights: Myoglobin (Mb) expression in MDA-MB-231 breast cancer cells slows migration.Mb expression decreases mitochondrial respiration and fatty acid oxidation.Mb-dependent fatty acid binding does not regulate cell migration or respiration.Mb-dependent oxidant generation decreases mitochondrial metabolism and migration.Mb-derived oxidants dysregulate migratory gene expression.

Dietary dicarboxylic acids provide a non-storable alternative fat source that protects mice against obesity.

Dicarboxylic fatty acids are generated in the liver and kidney in a minor pathway called fatty acid ω-oxidation. The effects of consuming dicarboxylic fatty acids as an alternative source of dietary fat have not been explored. Here, we fed dodecanedioic acid, a 12-carbon dicarboxylic (DC12), to mice at 20% of daily caloric intake for nine weeks. DC12 increased metabolic rate, reduced body fat, reduced liver fat, and improved glucose tolerance. We observed DC12-specific breakdown products in liver, kidney, muscle, heart, and brain, indicating that oral DC12 escaped first-pass liver metabolism and was utilized by many tissues. In tissues expressing the "a" isoform of acyl-CoA oxidase-1 (ACOX1), a key peroxisomal fatty acid oxidation enzyme, DC12 was chain shortened to the TCA cycle intermediate succinyl-CoA. In tissues with low peroxisomal fatty acid oxidation capacity, DC12 was oxidized by mitochondria. In vitro, DC12 was catabolized even by adipose tissue and was not stored intracellularly. We conclude that DC12 and other dicarboxylic acids may be useful for combatting obesity and for treating metabolic disorders.

Uncertainty-aware prototypical learning for anomaly detection in medical images.

Anomalous object detection (AOD) in medical images aims to recognize the anomalous lesions, and is crucial for early clinical diagnosis of various cancers. However, it is a difficult task because of two reasons: (1) the diversity of the anomalous lesions and (2) the ambiguity of the boundary between anomalous lesions and their normal surroundings. Unlike existing single-modality AOD models based on deterministic mapping, we constructed a probabilistic and deterministic AOD model. Specifically, we designed an uncertainty-aware prototype learning framework, which considers the diversity and ambiguity of anomalous lesions. A prototypical learning transformer (Pformer) is established to extract and store the prototype features of different anomalous lesions. Moreover, Bayesian neural uncertainty quantizer, a probabilistic model, is designed to model the distributions over the outputs of the model to measure the uncertainty of the model's detection results for each pixel. Essentially, the uncertainty of the model's anomaly detection result for a pixel can reflect the anomalous ambiguity of this pixel. Furthermore, an uncertainty-guided reasoning transformer (Uformer) is devised to employ the anomalous ambiguity, encouraging the proposed model to focus on pixels with high uncertainty. Notably, prototypical representations stored in Pformer are also utilized in anomaly reasoning that enables the model to perceive diversities of the anomalous objects. Extensive experiments on five benchmark datasets demonstrate the superiority of our proposed method. The source code will be available in github.com/umchaohuang/UPformer.

A self-supervised network for image denoising and watermark removal.

In image watermark removal, popular methods depend on given reference non-watermark images in a supervised way to remove watermarks. However, reference non-watermark images are difficult to be obtained in the real world. At the same time, they often suffer from the influence of noise when captured by digital devices. To resolve these issues, in this paper, we present a self-supervised network for image denoising and watermark removal (SSNet). SSNet uses a parallel network in a self-supervised learning way to remove noise and watermarks. Specifically, each sub-network contains two sub-blocks. The upper sub-network uses the first sub-block to remove noise, according to noise-to-noise. Then, the second sub-block in the upper sub-network is used to remove watermarks, according to the distributions of watermarks. To prevent the loss of important information, the lower sub-network is used to simultaneously learn noise and watermarks in a self-supervised learning way. Moreover, two sub-networks interact via attention to extract more complementary salient information. The proposed method does not depend on paired images to learn a blind denoising and watermark removal model, which is very meaningful for real applications. Also, it is more effective than the popular image watermark removal methods in public datasets. Codes can be found at https://github.com/hellloxiaotian/SSNet.

Unified Framework for Faster Clustering via Joint Schatten p-Norm Factorization With Optimal Mean.

To enhance the effectiveness and efficiency of subspace clustering in visual tasks, this work introduces a novel approach that automatically eliminates the optimal mean, which is embedded in the subspace clustering framework of low-rank representation (LRR) methods, along with the computationally factored formulation of Schatten p -norm. By addressing the issues related to meaningful computations involved in some LRR methods and overcoming biased estimation of the low-rank solver, we propose faster nonconvex subspace clustering methods through joint Schatten p -norm factorization with optimal mean (JS p NFOM), forming a unified framework for enhancing performance while reducing time consumption. The proposed approach employs tractable and scalable factor techniques, which effectively address the disadvantages of higher computational complexity, particularly when dealing with large-scale coefficient matrices. The resulting nonconvex minimization problems are reformulated and further iteratively optimized by multivariate weighting algorithms, eliminating the need for singular value decomposition (SVD) computations in the developed iteration procedures. Moreover, each subproblem can be guaranteed to obtain the closed-form solver, respectively. The theoretical analyses of convergence properties and computational complexity further support the applicability of the proposed methods in real-world scenarios. Finally, comprehensive experimental results demonstrate the effectiveness and efficiency of the proposed nonconvex clustering approaches compared to existing state-of-the-art methods on several publicly available databases. The demonstrated improvements highlight the practical significance of our work in subspace clustering tasks for visual data analysis. The source code for the proposed algorithms is publicly accessible at https://github.com/ZhangHengMin/TRANSUFFC.

Dicarboxylic Acid Dietary Supplementation Protects against AKI.

SIGNIFICANCE STATEMENT: In this study, we demonstrate that a common, low-cost compound known as octanedioic acid (DC 8 ) can protect mice from kidney damage typically caused by ischemia-reperfusion injury or the chemotherapy drug cisplatin. This compound seems to enhance peroxisomal activity, which is responsible for breaking down fats, without adversely affecting mitochondrial function. DC 8 is not only affordable and easy to administer but also effective. These encouraging findings suggest that DC 8 could potentially be used to assist patients who are at risk of experiencing this type of kidney damage. BACKGROUND: Proximal tubules are rich in peroxisomes, which are damaged during AKI. Previous studies demonstrated that increasing peroxisomal fatty acid oxidation (FAO) is renoprotective, but no therapy has emerged to leverage this mechanism. METHODS: Mice were fed with either a control diet or a diet enriched with dicarboxylic acids, which are peroxisome-specific FAO substrates, then subjected to either ischemia-reperfusion injury-AKI or cisplatin-AKI models. Biochemical, histologic, genetic, and proteomic analyses were performed. RESULTS: Both octanedioic acid (DC 8 ) and dodecanedioic acid (DC 12 ) prevented the rise of AKI markers in mice that were exposed to renal injury. Proteomics analysis demonstrated that DC 8 preserved the peroxisomal and mitochondrial proteomes while inducing extensive remodeling of the lysine succinylome. This latter finding indicates that DC 8 is chain shortened to the anaplerotic substrate succinate and that peroxisomal FAO was increased by DC 8 . CONCLUSIONS: DC 8 supplementation protects kidney mitochondria and peroxisomes and increases peroxisomal FAO, thereby protecting against AKI.

Adversarially Learning Occlusions by Backpropagation for Face Recognition.

With the accomplishment of deep neural networks, face recognition methods have achieved great success in research and are now being applied at a human level. However, existing face recognition models fail to achieve state-of-the-art performance in recognizing occluded face images, which are common scenarios captured in the real world. One of the potential reasons for this is the lack of large-scale training datasets, requiring labour-intensive and costly labelling of the occlusions. To resolve these issues, we propose an Adversarially Learning Occlusions by Backpropagation (ALOB) model, a simple yet powerful double-network framework used to mitigate manual labelling by contrastively learning the corrupted features against personal identity labels, thereby maximizing the loss. To investigate the performance of the proposed method, we compared our model to the existing state-of-the-art methods, which function under the supervision of occlusion learning, in various experiments. Extensive experimentation on LFW, AR, MFR2, and other synthetic masked or occluded datasets confirmed the effectiveness of the proposed model in occluded face recognition by sustaining better results in terms of masked face recognition and general face recognition. For the AR datasets, the ALOB model outperformed other advanced methods by obtaining a 100% recognition rate for images with sunglasses (protocols 1 and 2). We also achieved the highest accuracies of 94.87%, 92.05%, 78.93%, and 71.57% TAR@FAR = 1 × 10-3 in LFW-OCC-2.0 and LFW-OCC-3.0, respectively. Furthermore, the proposed method generalizes well in terms of FR and MFR, yielding superior results in three datasets, LFW, LFW-Masked, and MFR2, and producing accuracies of 98.77%, 97.62%, and 93.76%, respectively.

Complex II Biology in Aging, Health, and Disease.

Aging is associated with a decline in mitochondrial function which may contribute to age-related diseases such as neurodegeneration, cancer, and cardiovascular diseases. Recently, mitochondrial Complex II has emerged as an important player in the aging process. Mitochondrial Complex II converts succinate to fumarate and plays an essential role in both the tricarboxylic acid (TCA) cycle and the electron transport chain (ETC). The dysfunction of Complex II not only limits mitochondrial energy production; it may also promote oxidative stress, contributing, over time, to cellular damage, aging, and disease. Intriguingly, succinate, the substrate for Complex II which accumulates during mitochondrial dysfunction, has been shown to have widespread effects as a signaling molecule. Here, we review recent advances related to understanding the function of Complex II, succinate signaling, and their combined roles in aging and aging-related diseases.

A deep learning method for predicting the minimum inhibitory concentration of antimicrobial peptides against Escherichia coli using Multi-Branch-CNN and Attention.

Antimicrobial peptides (AMPs) are a promising alternative to antibiotics to combat drug resistance in pathogenic bacteria. However, the development of AMPs with high potency and specificity remains a challenge, and new tools to evaluate antimicrobial activity are needed to accelerate the discovery process. Therefore, we proposed MBC-Attention, a combination of a multi-branch convolution neural network architecture and attention mechanisms to predict the experimental minimum inhibitory concentration of peptides against Escherichia coli. The optimal MBC-Attention model achieved an average Pearson correlation coefficient (PCC) of 0.775 and a root mean squared error (RMSE) of 0.533 (log µM) in three independent tests of randomly drawn sequences from the data set. This results in a 5-12% improvement in PCC and a 6-13% improvement in RMSE compared to 17 traditional machine learning models and 2 optimally tuned models using random forest and support vector machine. Ablation studies confirmed that the two proposed attention mechanisms, global attention and local attention, contributed largely to performance improvement. IMPORTANCE Antimicrobial peptides (AMPs) are potential candidates for replacing conventional antibiotics to combat drug resistance in pathogenic bacteria. Therefore, it is necessary to evaluate the antimicrobial activity of AMPs quantitatively. However, wet-lab experiments are labor-intensive and time-consuming. To accelerate the evaluation process, we develop a deep learning method called MBC-Attention to regress the experimental minimum inhibitory concentration of AMPs against Escherichia coli. The proposed model outperforms traditional machine learning methods. Data, scripts to reproduce experiments, and the final production models are available on GitHub.

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.

A Novel Public Sentiment Analysis Method Based on an Isomerism Learning Model via Multiphase Processing.

The dissemination of public opinion in the social media network is driven by public sentiment, which can be used to promote the effective resolution of social incidents. However, public sentiments for incidents are often affected by environmental factors such as geography, politics, and ideology, which increases the complexity of the sentiment acquisition task. Therefore, a hierarchical mechanism is designed to reduce complexity and utilize processing at multiple phases to improve practicality. Through serial processing between different phases, the task of public sentiment acquisition can be decomposed into two subtasks, which are the classification of report text to locate incidents and sentiment analysis of individuals' reviews. Performance has been improved through improvements to the model structure, such as embedding tables and gating mechanisms. That being said, the traditional centralized structure model is not only easy to form model silos in the process of performing tasks but also faces security risks. In this article, a novel distributed deep learning model called isomerism learning based on blockchain is proposed to address these challenges, the trusted collaboration between models can be realized through parallel training. In addition, for the problem of text heterogeneity, we also designed a method to measure the objectivity of events to dynamically assign the weights of models to improve aggregation efficiency. Extensive experiments demonstrate that the proposed method can effectively improve performance and outperform the state-of-the-art methods significantly.

Mitochondrial ROS Triggers KIN Pathogenesis in FAN1-Deficient Kidneys.

Karyomegalic interstitial nephritis (KIN) is a genetic adult-onset chronic kidney disease (CKD) characterized by genomic instability and mitotic abnormalities in the tubular epithelial cells. KIN is caused by recessive mutations in the FAN1 DNA repair enzyme. However, the endogenous source of DNA damage in FAN1/KIN kidneys has not been identified. Here we show, using FAN1-deficient human renal tubular epithelial cells (hRTECs) and FAN1-null mice as a model of KIN, that FAN1 kidney pathophysiology is triggered by hypersensitivity to endogenous reactive oxygen species (ROS), which cause chronic oxidative and double-strand DNA damage in the kidney tubular epithelial cells, accompanied by an intrinsic failure to repair DNA damage. Furthermore, persistent oxidative stress in FAN1-deficient RTECs and FAN1 kidneys caused mitochondrial deficiencies in oxidative phosphorylation and fatty acid oxidation. The administration of subclinical, low-dose cisplatin increased oxidative stress and aggravated mitochondrial dysfunction in FAN1-deficient kidneys, thereby exacerbating KIN pathophysiology. In contrast, treatment of FAN1 mice with a mitochondria-targeted ROS scavenger, JP4-039, attenuated oxidative stress and accumulation of DNA damage, mitigated tubular injury, and preserved kidney function in cisplatin-treated FAN1-null mice, demonstrating that endogenous oxygen stress is an important source of DNA damage in FAN1-deficient kidneys and a driver of KIN pathogenesis. Our findings indicate that therapeutic modulation of kidney oxidative stress may be a promising avenue to mitigate FAN1/KIN kidney pathophysiology and disease progression in patients.

Toward Efficient Palmprint Feature Extraction by Learning a Single-Layer Convolution Network.

In this article, we propose a collaborative palmprint-specific binary feature learning method and a compact network consisting of a single convolution layer for efficient palmprint feature extraction. Unlike most existing palmprint feature learning methods, such as deep-learning, which usually ignore the inherent characteristics of palmprints and learn features from raw pixels of a massive number of labeled samples, palmprint-specific information, such as the direction and edge of patterns, is characterized by forming two kinds of ordinal measure vectors (OMVs). Then, collaborative binary feature codes are jointly learned by projecting double OMVs into complementary feature spaces in an unsupervised manner. Furthermore, the elements of feature projection functions are integrated into OMV extraction filters to obtain a collection of cascaded convolution templates that form a single-layer convolution network (SLCN) to efficiently obtain the binary feature codes of a new palmprint image within a single-stage convolution operation. Particularly, our proposed method can easily be extended to a general version that can efficiently perform feature extraction with more than two types of OMVs. Experimental results on five benchmark databases show that our proposed method achieves very promising feature extraction efficiency for palmprint recognition.

Flexible and Generalized Real Photograph Denoising Exploiting Dual Meta Attention.

Supervised deep learning techniques have been widely explored in real photograph denoising and achieved noticeable performances. However, being subject to specific training data, most current image denoising algorithms can easily be restricted to certain noisy types and exhibit poor generalizability across testing sets. To address this issue, we propose a novel flexible and well-generalized approach, coined as dual meta attention network (DMANet). The DMANet is mainly composed of a cascade of the self-meta attention blocks (SMABs) and collaborative-meta attention blocks (CMABs). These two blocks have two forms of advantages. First, they simultaneously take both spatial and channel attention into account, allowing our model to better exploit more informative feature interdependencies. Second, the attention blocks are embedded with the meta-subnetwork, which is based on metalearning and supports dynamic weight generation. Such a scheme can provide a beneficial means for self and collaborative updating of the attention maps on-the-fly. Instead of directly stacking the SMABs and CMABs to form a deep network architecture, we further devise a three-stage learning framework, where different blocks are utilized for each feature extraction stage according to the individual characteristics of SMAB and CMAB. On five real datasets, we demonstrate the superiority of our approach against the state of the art. Unlike most existing image denoising algorithms, our DMANet not only possesses a good generalization capability but can also be flexibly used to cope with the unknown and complex real noises, making it highly competitive for practical applications.

GM3 synthase deficiency increases brain glucose metabolism in mice.

GM3 synthase (GM3S) deficiency is a rare neurodevelopmental disorder caused by an inability to synthesize gangliosides, for which there is currently no treatment. Gangliosides are brain-enriched, plasma membrane glycosphingolipids with poorly understood biological functions related to cell adhesion, growth, and receptor-mediated signal transduction. Here, we investigated the effects of GM3S deficiency on metabolism and mitochondrial function in a mouse model. By indirect calorimetry, GM3S knockout mice exhibited increased whole-body respiration and an increased reliance upon carbohydrate as an energy source. 18F-FDG PET confirmed higher brain glucose uptake in knockout mice, and GM3S deficient N41 neuronal cells showed higher glucose utilization in vitro. Brain mitochondria from knockout mice respired at a higher rate on Complex I substrates including pyruvate. This appeared to be due to higher expression of pyruvate dehydrogenase (PDH) and lower phosphorylation of PDH, which would favor pyruvate entry into the mitochondrial TCA cycle. Finally, it was observed that blocking glucose metabolism with the glycolysis inhibitor 2-deoxyglucose reduced seizure intensity in GM3S knockout mice following administration of kainate. In conclusion, GM3S deficiency may be associated with a hypermetabolic phenotype that could promote seizure activity.

Deep Bilateral Filtering Network for Point-Supervised Semantic Segmentation in Remote Sensing Images.

Semantic segmentation methods based on deep neural networks have achieved great success in recent years. However, training such deep neural networks relies heavily on a large number of images with accurate pixel-level labels, which requires a huge amount of human effort, especially for large-scale remote sensing images. In this paper, we propose a point-based weakly supervised learning framework called the deep bilateral filtering network (DBFNet) for the semantic segmentation of remote sensing images. Compared with pixel-level labels, point annotations are usually sparse and cannot reveal the complete structure of the objects; they also lack boundary information, thus resulting in incomplete prediction within the object and the loss of object boundaries. To address these problems, we incorporate the bilateral filtering technique into deeply learned representations in two respects. First, since a target object contains smooth regions that always belong to the same category, we perform deep bilateral filtering (DBF) to filter the deep features by a nonlinear combination of nearby feature values, which encourages the nearby and similar features to become closer, thus achieving a consistent prediction in the smooth region. In addition, the DBF can distinguish the boundary by enlarging the distance between the features on different sides of the edge, thus preserving the boundary information well. Experimental results on two widely used datasets, the ISPRS 2-D semantic labeling Potsdam and Vaihingen datasets, demonstrate that our proposed DBFNet can achieve a highly competitive performance compared with state-of-the-art fully-supervised methods. Code is available at https://github.com/Luffy03/DBFNet.