A group of emerging heterocyclic nitrogenous disinfection byproducts: Formation and cytotoxicity of halopyridinols in drinking water.

Recently, a new group of halopyridinol disinfection byproducts (DBPs) was reported in drinking water. The in vivo developmental and acute toxicity assays have shown that they were more toxic than a few commonly known aliphatic DBPs such as bromoform and iodoacetic acid. However, many pyridinol DBPs with the same main structures but different halogen substitutions were still unknown due to complicated water quality conditions and various disinfection methods applied in drinking water treatment plants. Studies on their transformation mechanisms in drinking water disinfection were quite limited. In this study, comprehensive detection and identification of halopyridinols were conducted, and five new halopyridinols were first reported, including 2-chloro-3-pyridinol, 2,6-dichloro-3-pyridinol, 2-bromo-5-chloro-3-pyridinol, 2,4,6-trichloro-3-pyridinol and 2,5,6-trichloro-3-pyridinol. Formation conditions and mechanisms of the halopyridinols were explored, and results showed that chlorination promoted their formation compared with chloramination. Halopyridinols were intermediate DBPs that could undergo further transformation/degradation with increasing contact time, disinfectant dose, bromide concentration, and pH. The in vitro cytotoxicity of the halopyridinols was evaluated using human hepatocellular carcinoma cells. Results showed that the cytotoxicity of 3,5,6-trichloro-2-pyridinol was the highest (EC50 = 474.3 µM), which was 13.0 and 1.6 times higher than that of 2-bromo-3-pyridinol (EC50 = 6214.5 µM) and tribromomethane (EC50 = 753.6 µM), respectively.

Association between electroencephalogram alpha-band oscillations and executive and processing functions in patients with cerebral small vessel diseases.

Electroencephalogram (EEG) alpha-band oscillations may reflect executive and processing function in patients with cerebral small vessel disease (CSVD). We aimed to assess such association and its relationship with CSVD severity, and to identify specific alpha-band parameters and the cut-off values for cognitive screening. We analysed the dispersion of amplitude-frequency characteristics of EEG alpha-band and different alpha-band parameters (PFα , ΔPFα , PPα , NCL) in different brain locations. We also assessed patients' executive and processing functions using verbal fluency test (VFT) and color trails test (CTT), and CSVD severity using total burden and Fazekas scores. 129 patients were recruited in the study. After adjusting for age, gender and education, PFα(F3), PFα(F4) and NCL were significantly associated with VFT-composite performance (p < 0.05). CTT-1 time and error were associated with PFα(F3), PFα(F4), ΔPFα(O1;F3) and CSVD severity (p < 0.05), whereas CTT-2 time was only associated with CSVD severity. Moreover, the correlations between alpha-band oscillations and cognitive function were higher in low than in high disease-severity group (ρ: -0.58 vs. -0.38, p < 0.05). The AUC of selected alpha-band parameters were higher than 0.8 for VFT and CTT. Specific alpha-band parameters in the frontal lobe were identified to correspond to executive and processing function. Assessing EEG alpha-band oscillations may assist in screening cognitive impairment.

Magnetic Graphene Oxide Nanocomposites Boosts Craniomaxillofacial Bone Regeneration by Modulating circAars/miR-128-3p/SMAD5 Signaling Axis.

Background: The ability of nanomaterials to induce osteogenic differentiation is limited, which seriously imped the repair of craniomaxillofacial bone defect. Magnetic graphene oxide (MGO) nanocomposites with the excellent physicochemical properties have great potential in bone tissue engineering. In this study, we aim to explore the craniomaxillofacial bone defect repairment effect of MGO nanocomposites and its underlying mechanism. Methods: The biocompatibility of MGO nanocomposites was verified by CCK8, live/dead staining and cytoskeleton staining. The function of MGO nanocomposites induced osteogenic differentiation of BMSCs was investigated by ALP activity detection, mineralized nodules staining, detection of osteogenic genes and proteins, and immune-histochemical staining. BMSCs with or without MGO osteogenic differentiation induction were collected and subjected to high-throughput circular ribonucleic acids (circRNAs) sequencing, and then crucial circRNA circAars was screened and identified. Bioinformatics analysis, Dual-luciferase reporter assay, RNA binding protein immunoprecipitation (RIP), fluorescence in situ hybridization (FISH) and osteogenic-related examinations were used to further explore the ability of circAars to participate in MGO nanocomposites regulation of osteogenic differentiation of BMSCs and its potential mechanism. Furthermore, critical-sized calvarial defects were constructed and were performed to verify the osteogenic differentiation induction effects and its potential mechanism induced by MGO nanocomposites. Results: We verify the good biocompatibility and osteogenic differentiation improvement effects of BMSCs mediated by MGO nanocomposites. Furthermore, a new circRNA-circAars, we find and identify, is obviously upregulated in BMSCs mediated by MGO nanocomposites. Silencing circAars could significantly decrease the osteogenic ability of MGO nanocomposites. The underlying mechanism involved circAars sponging miR-128-3p to regulate the expression of SMAD5, which played an important role in the repair craniomaxillofacial bone defects mediated by MGO nanocomposites. Conclusion: We found that MGO nanocomposites regulated osteogenic differentiation of BMSCs via the circAars/miR-128-3p/SMAD5 pathway, which provided a feasible and effective strategy for the treatment of craniomaxillofacial bone defects.

Alkali injury-induced pathological lymphangiogenesis in the iris facilitates the infiltration of T cells and ocular inflammation.

Inflammatory lymphangiogenesis is intimately linked to immune regulation and tissue homeostasis. However, current evidence has suggested that classic lymphatic vessels are physiologically absent in intraocular structures. Here, we show that neolymphatic vessels were induced in the iris after corneal alkali injury (CAI) in a VEGFR3-dependent manner. Cre-loxP-based lineage tracing revealed that these lymphatic endothelial cells (LECs) originate from existing Prox1+ lymphatic vessels. Notably, the ablation of iridial lymphangiogenesis via conditional deletion of VEGFR3 alleviated the ocular inflammatory response and pathological T cell infiltration. Our findings demonstrate that iridial neolymphatics actively participate in pathological immune responses following injury and suggest intraocular lymphangiogenesis as a valuable therapeutic target for the treatment of ocular inflammation.

Applications of Data Characteristic AI-Assisted Raman Spectroscopy in Pathological Classification.

Raman spectroscopy has been widely used for label-free biomolecular analysis of cells and tissues for pathological diagnosis in vitro and in vivo. AI technology facilitates disease diagnosis based on Raman spectroscopy, including machine learning (PCA and SVM), manifold learning (UMAP), and deep learning (ResNet and AlexNet). However, it is not clear how to optimize the appropriate AI classification model for different types of Raman spectral data. Here, we selected five representative Raman spectral data sets, including endometrial carcinoma, hepatoma extracellular vesicles, bacteria, melanoma cell, diabetic skin, with different characteristics regarding sample size, spectral data size, Raman shift range, tissue sites, Kullback-Leibler (KL) divergence, and significant Raman shifts (i.e., wavenumbers with significant differences between groups), to explore the performance of different AI models (e.g., PCA-SVM, SVM, UMAP-SVM, ResNet or AlexNet). For data set of large spectral data size, Resnet performed better than PCA-SVM and UMAP. By building data characteristic-assisted AI classification model, we optimized the network parameters (e.g., principal components, activation function, and loss function) of AI model based on data size and KL divergence etc. The accuracy improved from 85.1 to 94.6% for endometrial carcinoma grading, from 77.1 to 90.7% for hepatoma extracellular vesicles detection, from 89.3 to 99.7% for melanoma cell detection, from 88.1 to 97.9% for bacterial identification, from 53.7 to 85.5% for diabetic skin screening, and mean time expense of 5 s.

Searching for Two-Neutrino and Neutrinoless Double Beta Decay of

^{134}Xe is a candidate isotope for neutrinoless double beta decay (0νßß) search. In addition, the two-neutrino case (2νßß) allowed by the standard model of particle physics has not yet been observed. With the 656-kg natural xenon in the fiducial volume of the PandaX-4T detector, which contains 10.4% of ^{134}Xe, and its initial 94.9-day exposure, we have established the most stringent constraints on 2νßß and 0νßß of ^{134}Xe half-lives, with limits of 2.8×10^{22} yr and 3.0×10^{23} yr at 90% confidence level, respectively. The 2νßß (0νßß) limit surpasses the previously reported best result by a factor of 32 (2.7), highlighting the potential of large monolithic natural xenon detectors for double beta decay searches.

VirusPredictor: XGBoost-based software to predict virus-related sequences in human data.

MOTIVATION: Discovering disease causative pathogens, particularly viruses without reference genomes, poses a technical challenge as they are often unidentifiable through sequence alignment. Machine learning prediction of patient high-throughput sequences unmappable to human and pathogen genomes may reveal sequences originating from uncharacterized viruses. Currently, there is a lack of software specifically designed for accurately predicting such viral sequences in human data. RESULTS: We developed a fast XGBoost method and software VirusPredictor leveraging an in-house viral genome database. Our two-step XGBoost models first classify each query sequence into one of three groups: infectious virus, endogenous retrovirus (ERV) or non-ERV human. The prediction accuracies increased as the sequences became longer, i.e. 0.76, 0.93, and 0.98 for 150-350 (Illumina short reads), 850-950 (Sanger sequencing data), and 2000-5000 bp sequences, respectively. Then, sequences predicted to be from infectious viruses are further classified into one of six virus taxonomic subgroups, and the accuracies increased from 0.92 to >0.98 when query sequences increased from 150-350 to >850 bp. The results suggest that Illumina short reads should be de novo assembled into contigs (e.g. ∼1000 bp or longer) before prediction whenever possible. We applied VirusPredictor to multiple real genomic and metagenomic datasets and obtained high accuracies. VirusPredictor, a user-friendly open-source Python software, is useful for predicting the origins of patients' unmappable sequences. This study is the first to classify ERVs in infectious viral sequence prediction. This is also the first study combining virus sub-group predictions. AVAILABILITY AND IMPLEMENTATION: www.dllab.org/software/VirusPredictor.html.

Multi-Dimensional Medical Image Fusion With Complex Sparse Representation.

In the field of medical imaging, the fusion of data from diverse modalities plays a pivotal role in advancing our understanding of pathological conditions. Sparse representation (SR), a robust signal modeling technique, has demonstrated noteworthy success in multi-dimensional (MD) medical image fusion. However, a fundamental limitation appearing in existing SR models is their lack of directionality, restricting their efficacy in extracting anatomical details from different imaging modalities. To tackle this issue, we propose a novel directional SR model, termed complex sparse representation (ComSR), specifically designed for medical image fusion. ComSR independently represents MD signals over directional dictionaries along specific directions, allowing precise analysis of intricate details of MD signals. Besides, current studies in medical image fusion mostly concentrate on addressing either 2D or 3D fusion problems. This work bridges this gap by proposing a MD medical image fusion method based on ComSR, presenting a unified framework for both 2D and 3D fusion tasks. Experimental results across six multi-modal medical image fusion tasks, involving 93 pairs of 2D source images and 20 pairs of 3D source images, substantiate the superiority of our proposed method over 11 state-of-the-art 2D fusion methods and 4 representative 3D fusion methods, in terms of both visual quality and objective evaluation. The source code of our fusion method is available at https://github.com/Imagefusions/imagefusions/tree/main.

TEMPO-Mediated Dehydrogenative Hydroxyfluoroalkylation of Arylamines with Polyfluorinated Alcohols.

An efficient 2,2,6,6-tetramethylpiperidinooxy (TEMPO)-mediated hydroxyfluoroalkylation of arylamines with polyfluorinated alcohols via a radical-triggered C(sp2)-H/C(sp3)-H dehydrogenative cross-coupling process was developed. This transformation features simple operation, high atom economy, broad substrate compatibility, and excellent regioselectivity, leading to a series of hydroxyfluoroalkylated arylamine derivatives. Importantly, these synthetic products were further used to evaluate the antitumor activity in cancer cell lines by Cell Counting Kit-8 assay and the outcomes indicated that some compounds show a potent antiproliferative effect.

Applications of charcoal, activated charcoal, and biochar in aquaculture - A review.

Environmental pollution and poor feed quality pose potential threats to aquatic organisms and human health, representing challenges for the aquaculture industry. In light of the rising demand for aquatic organisms, there is an urgent need to improve aquacultural production and protect the products from contamination. Char, a carbonaceous material derived through pyrolysis of organic carbon-rich biomass, has proven advantages in soil, air, and water remediation. While char's performance and the associated physicochemical characteristics depend strongly on the pyrolysis temperature, residence time, and feedstock type, char generally shows advantages in pollutant removal from the environment and livestock. This enables it to enhance the health and growth performance of livestock. Given the growing attention to char application in aquaculture in recent years, this review summarises major studies on three applications: aquacultural water treatment, sediment remediation, and char-feed supplement. Most of these studies have demonstrated char's positive effects on pollutant removal from organisms and aquacultural environments. Moreover, adopting char as fish feed can improve fish growth performance and the condition of their intestinal villi. However, due to insufficient literature, further investigation is needed into the mechanistic aspects of pollutants removal in aquatic organisms by char as a feed additive, such as the transportation of char inside aquatic organisms, the positive and negative effects of char on these products, and how char alters the gut microbiota community of these products. This paper presents an overview of the current application of char in aquaculture and highlights the research areas that require further investigation to enrich future studies.

Arbuscular Mycorrhizal Fungus Alleviates Charged Nanoplastic Stress in Host Plants via Enhanced Defense-Related Gene Expressions and Hyphal Capture.

Contamination of small-sized plastics is recognized as a factor of global change. Nanoplastics (NPs) can readily enter organisms and pose significant ecological risks. Arbuscular mycorrhizal (AM) fungi are the most ubiquitous and impactful plant symbiotic fungi, regulating essential ecological functions. Here, we first found that an AM fungus, Rhizophagus irregularis, increased lettuce shoot biomass by 25-100% when exposed to positively and negatively charged NPs vs control, although it did not increase that grown without NPs. The stress alleviation was attributed to the upregulation of gene expressions involving phytohormone signaling, cell wall metabolism, and oxidant scavenging. Using a root organ-fungus axenic growth system treated with fluorescence-labeled NPs, we subsequently revealed that the hyphae captured NPs and further delivered them to roots. NPs were observed at the hyphal cell walls, membranes, and spore walls. NPs mediated by the hyphae were localized at the root epidermis, cortex, and stele. Hyphal exudates aggregated positively charged NPs, thereby reducing their uptake due to NP aggregate formation (up to 5000 nm). This work demonstrates the critical roles of AM fungus in regulating NP behaviors and provides a potential strategy for NP risk mitigation in terrestrial ecosystems. Consequent NP-induced ecological impacts due to the affected AM fungi require further attention.

Tyrosine phosphatase PTPN11/SHP2 in solid tumors - bull's eye for targeted therapy?

Encoded by PTPN11, the Src-homology 2 domain-containing phosphatase 2 (SHP2) integrates signals from various membrane-bound receptors such as receptor tyrosine kinases (RTKs), cytokine and integrin receptors and thereby promotes cell survival and proliferation. Activating mutations in the PTPN11 gene may trigger signaling pathways leading to the development of hematological malignancies, but are rarely found in solid tumors. Yet, aberrant SHP2 expression or activation has implications in the development, progression and metastasis of many solid tumor entities. SHP2 is involved in multiple signaling cascades, including the RAS-RAF-MEK-ERK-, PI3K-AKT-, JAK-STAT- and PD-L1/PD-1- pathways. Although not mutated, activation or functional requirement of SHP2 appears to play a relevant and context-dependent dichotomous role. This mostly tumor-promoting and infrequently tumor-suppressive role exists in many cancers such as gastrointestinal tumors, pancreatic, liver and lung cancer, gynecological entities, head and neck cancers, prostate cancer, glioblastoma and melanoma. Recent studies have identified SHP2 as a potential biomarker for the prognosis of some solid tumors. Based on promising preclinical work and the advent of orally available allosteric SHP2-inhibitors early clinical trials are currently investigating SHP2-directed approaches in various solid tumors, either as a single agent or in combination regimes. We here provide a brief overview of the molecular functions of SHP2 and collate current knowledge with regard to the significance of SHP2 expression and function in different solid tumor entities, including cells in their microenvironment, immune escape and therapy resistance. In the context of the present landscape of clinical trials with allosteric SHP2-inhibitors we discuss the multitude of opportunities but also limitations of a strategy targeting this non-receptor protein tyrosine phosphatase for treatment of solid tumors.

MM-Net: A MixFormer-Based Multi-Scale Network for Anatomical and Functional Image Fusion.

Anatomical and functional image fusion is an important technique in a variety of medical and biological applications. Recently, deep learning (DL)-based methods have become a mainstream direction in the field of multi-modal image fusion. However, existing DL-based fusion approaches have difficulty in effectively capturing local features and global contextual information simultaneously. In addition, the scale diversity of features, which is a crucial issue in image fusion, often lacks adequate attention in most existing works. In this paper, to address the above problems, we propose a MixFormer-based multi-scale network, termed as MM-Net, for anatomical and functional image fusion. In our method, an improved MixFormer-based backbone is introduced to sufficiently extract both local features and global contextual information at multiple scales from the source images. The features from different source images are fused at multiple scales based on a multi-source spatial attention-based cross-modality feature fusion (CMFF) module. The scale diversity of the fused features is further enriched by a series of multi-scale feature interaction (MSFI) modules and feature aggregation upsample (FAU) modules. Moreover, a loss function consisting of both spatial domain and frequency domain components is devised to train the proposed fusion model. Experimental results demonstrate that our method outperforms several state-of-the-art fusion methods on both qualitative and quantitative comparisons, and the proposed fusion model exhibits good generalization capability. The source code of our fusion method will be available at https://github.com/yuliu316316.

Dual-channel neural network for instance segmentation of synapse.

Detection and segmentation of neural synapses in electron microscopy images are the committed steps for analyzing neural ultrastructure. To date, manual annotation of the structure in synapses has been the primary method, which is time-consuming and restricts the throughput of data acquisition. Recent studies have utilized a series of deformations based on a segmentation model for the detection and segmentation of transmission electron microscope images. However, the analysis of synaptic segmentation and statistics still lacks sufficient automation and high-throughput. Therefore, we developed a dual-channel neural network instance segmentation model with weighted top-down and multi-scale bottom-up schemes, which aid in accurately detecting and segmenting synaptic vesicles and their active zones within presynaptic membranes in complex environments. In addition, we proposed a masked self-supervised pre-training model based on the latest convolutional architecture to improve performance in downstream segmentation tasks. By comparing our model to other state-of-the-art methods, we determined its viability and accuracy. The applicability of our model is thoroughly demonstrated by distinct application scenarios for neurobiological research. These findings indicate that the dual-channel neural network could facilitate the analysis of synaptic structures for the advancement of biomedical research and electron microscope reconstruction techniques.

Emulsion template fabricated heterogeneous bilayer gelatin-based scaffolds with sustained-delivery of lycium barbarum glycopeptide for periodontitis treatment.

Periodontitis is a chronic inflammatory disease raising the risks of tooth-supporting structures destruction and even tooth loss. The way to reconstruct periodontal bone tissues in inflammatory microenvironment has been long in demand for periodontitis treatment. In this study, the lycium barbarum glycopeptide (LbGP) loaded gelatin-based scaffolds were fabricated for periodontitis treatment. Gelatin microspheres with suitable size were prepared by emulsification and gathered by oxidized sodium alginate to prepare heterogeneous bilayer gelatin-based scaffolds, and then they were loaded with LbGP. The prepared scaffolds possessed interconnected porous microstructures, good degradation properties, sufficient mechanical properties, sustained release behavior and well biocompatibility. In vitro experiments suggested that the LbGP loaded gelatin-based scaffolds could inhibit the expression of inflammatory factors (IL-1ß, IL-6, and TNF-α), promote the expression of anti-inflammatory factor (IL-10), and the expression of osteogenic markers (BMP2, Runx2, ALP, and OCN) in PDLSCs under the LPS-stimulated inflammatory microenvironment. Moreover, in rat periodontitis models, the LbGP gelatin-based scaffolds would reduce the alveolar bone resorption of rats, increase the collagen fiber content of periodontal membrane, alleviate local inflammation and improve the expression of osteogenesis-related factors. Therefore, the LbGP loaded gelatin-based scaffolds in this study will provide a potential therapeutic strategy for periodontitis treatment.

SFE-Net: Spatial-Frequency Enhancement Network for robust nuclei segmentation in histopathology images.

Morphological features of individual nuclei serve as a dependable foundation for pathologists in making accurate diagnoses. Existing methods that rely on spatial information for feature extraction have achieved commendable results in nuclei segmentation tasks. However, these approaches are not sufficient to extract edge information of nuclei with small sizes and blurred outlines. Moreover, the lack of attention to the interior of the nuclei leads to significant internal inconsistencies. To address these challenges, we introduce a novel Spatial-Frequency Enhancement Network (SFE-Net) to incorporate spatial-frequency features and promote intra-nuclei consistency for robust nuclei segmentation. Specifically, SFE-Net incorporates a distinctive Spatial-Frequency Feature Extraction module and a Spatial-Guided Feature Enhancement module, which are designed to preserve spatial-frequency information and enhance feature representation respectively, to achieve comprehensive extraction of edge information. Furthermore, we introduce the Label-Guided Distillation method, which utilizes semantic features to guide the segmentation network in strengthening boundary constraints and learning the intra-nuclei consistency of individual nuclei, to improve the robustness of nuclei segmentation. Extensive experiments on three publicly available histopathology image datasets (MoNuSeg, TNBC and CryoNuSeg) demonstrate the superiority of our proposed method, which achieves 79.23%, 81.96% and 73.26% Aggregated Jaccard Index, respectively. The proposed model is available at https://github.com/jinshachen/SFE-Net.

Comparison of the Effects of Tenofovir Disoproxil Fumarate (TDF) and Tenofovir Alafenamide (TAF) on Liver Function in Patients with Hepatitis B: A Meta-analysis.

Objective: This is a meta-analysis comparing the efficacy of Tenofovir disoproxil fumarate (TDF) and Tenofovir alafenamide (TAF) in the treatment of chronic hepatitis B (CHB) so as to provide a reference for clinical medication. Methods: Relevant literature about TDF and TAF in the treatment of CHB was searched in the literature databases, and two researchers two researchers conducted independent cross-screening conducted independent cross-screening according to the inclusion and exclusion criteria. The authors, publication time, research subjects. The literature quality was evaluated by, and outcome measures of the selected literature were extracted. The literature quality was evaluated using the Jadad scale and Cochrane risk-of-bias tool. Meta-analysis was conducted using the RevMan 5.3 software. Results: After screening, 5 references were included, with a total of 5324 subjects. Patients who were treated with TDF and TAF were included in the TDF group and TAF group, respectively. The meta-analysis showed no significant difference in viral suppression between groups after 12 months of treatment (P > .05). Still, the alanine transaminase (ALT) normalization rate was higher, and the incidence of adverse reactions was lower in TAF group versus TDF group at 12 months after treatment (P < .05). Conclusions: Both TAF and TDF are effective in the treatment of CHB, but the former is preferred due to its higher safety profile.

Application of hyperbaric oxygen therapy in diabetic foot ulcers: A meta-analysis.

Hyperbaric oxygen therapy (HBOT) has been used in patients with diabetic foot ulcers (DFU) for many years, but its clinical efficacy is still controversial. Therefore, this study explored the efficacy of HBOT applied to DFU by means of meta-analysis. PubMed, Cochrane Library, Embase, CNKI and Wanfang databases were searched, from database inception to October 2023, and published randomised controlled trials (RCTs) of HBOT in DFU were collected. Two investigators independently screened the collected literature, extracted relevant data and assessed the quality of the literature. Review Manager 5.4 software was applied for data analysis. Twenty-nine RCTs with 1764 patients were included. According to the combined results, when compared with conventional treatment, HBOT significantly increased the complete healing rate of DFUs (46.76% vs. 24.46%, odds ratio [OR]: 2.83, 95% CI: 2.29-3.51, p < 0.00001) and decreased the amputation rate (26.03% vs. 45.00%, OR: 0.41, 95% CI: 0.18-0.95, p = 0.04), but the incidence of adverse events was significantly higher in patients (17.37% vs. 8.27%, OR: 2.49, 95% CI: 1.35-4.57, p = 0.003), whereas there was no significant difference in the mortality (6.96% vs. 12.71%, OR: 0.52, 95% CI: 0.21-1.28, p = 0.16). Our results suggest that HBOT is effective in increasing the complete healing rate and decreasing the amputation rate in patients with DFUs, but increases the incidence of adverse events, while it has no significant effect on mortality.

A Novel Data Augmentation Approach Using Mask Encoding for Deep Learning-Based Asynchronous SSVEP-BCI.

Deep learning (DL)-based methods have been successfully employed as asynchronous classification algorithms in the steady-state visual evoked potential (SSVEP)-based brain-computer interface (BCI) system. However, these methods often suffer from the limited amount of electroencephalography (EEG) data, leading to overfitting. This study proposes an effective data augmentation approach called EEG mask encoding (EEG-ME) to mitigate overfitting. EEG-ME forces models to learn more robust features by masking partial EEG data, leading to enhanced generalization capabilities of models. Three different network architectures, including an architecture integrating convolutional neural networks (CNN) with Transformer (CNN-Former), time domain-based CNN (tCNN), and a lightweight architecture (EEGNet) are utilized to validate the effectiveness of EEG-ME on publicly available benchmark and BETA datasets. The results demonstrate that EEG-ME significantly enhances the average classification accuracy of various DL-based methods with different data lengths of time windows on two public datasets. Specifically, CNN-Former, tCNN, and EEGNet achieve respective improvements of 3.18%, 1.42%, and 3.06% on the benchmark dataset as well as 11.09%, 3.12%, and 2.81% on the BETA dataset, with the 1-second time window as an example. The enhanced performance of SSVEP classification with EEG-ME promotes the implementation of the asynchronous SSVEP-BCI system, leading to improved robustness and flexibility in human-machine interaction.

Rethinking the Effectiveness of Objective Evaluation Metrics in Multi-focus Image Fusion: A Statistic-based Approach.

As an effective technique to extend the depth-of-field (DOF) of optical lenses, multi-focus image fusion has recently become an active topic in image processing community. However, a major problem remaining unsolved in this field is the lack of universal criteria in selecting objective evaluation metrics. Consequently, the metrics utilized in different studies often vary significantly, leading to high difficulties in achieving unbiased evaluation. To address this problem, this paper proposes a statistic-based approach for verifying the effectiveness of objective metrics in multi-focus image fusion. The core idea is to adopt statistical correlation measures to evaluate the performance consistency between a certain fusion metric and some popular full-reference image quality assessment models. In addition, a convolutional neural network (CNN)-based fusion metric is presented to measure the similarity between the source images and the fused image based on the semantic features at multiple abstraction levels. A comparative study is conducted to evaluate 20 existing fusion metrics using the proposed statistic-based approach on a large-scale, realistic and with-ground-truth multi-focus image fusion dataset recently released. Experimental results demonstrate the feasibility of the proposed approach in evaluating the effectiveness of objective metrics and the advantage of our CNN-based metric. Resources will be released at https://github.com/yuliu316316.