Kinship verification via correlation calculation-based multi-task learning.

Previous studies have demonstrated that metric learning approaches yield remarkable performance in the field of kinship verification. Nevertheless, a prevalent limitation of most existing methods lies in their over-reliance on learning exclusively from specified types of given kin data, which frequently results in information isolation. Although generative-based metric learning methods present potential solutions to this problem, they are hindered by substantial computational costs.

A spatial-frequency hybrid restoration network for JPEG compressed image deblurring.

Image deblurring and compression-artifact removal are both ill-posed inverse problems in low-level vision tasks. So far, although numerous image deblurring and compression-artifact removal methods have been proposed respectively, the research for explicit handling blur and compression-artifact coexisting degradation image (BCDI) is rare. In the BCDI, image contents will be damaged more seriously, especially for edges and texture details.

Inter-modality feature prediction through multimodal fusion for 3D shape defect detection.

3D shape defect detection plays an important role in autonomous industrial inspection. However, accurate detection of anomalies remains challenging due to the complexity of multimodal sensor data, especially when both color and structural information are required. In this work, we propose a lightweight inter-modality feature prediction framework that effectively utilizes multimodal fused features from the inputs of RGB, depth and point clouds for efficient 3D shape defect detection.

Nitrogen-Annealed Zinc-Nickel Porous Nanosheets for Electronic State-Enhanced High-Conductivity Anode Energy Storage Mechanism Study.

This study systematically investigates the role of nitrogen annealing in enhancing the structural and electrochemical properties of ZnNiO/NF composite anode materials synthesized via hydrothermal methods. By comparing air-annealed and nitrogen-annealed (400 and 600 °C) samples, it is demonstrated that nitrogen annealing at 400 °C induces the densely stacked nanosheet morphology with optimized lattice regularity, which can significantly improve the charge transport kinetics and the interfacial stability. Electrochemical evaluations reveal an outstanding initial discharge capacity of 1873.

TMBquant: an explainable AI-powered caller advancing tumor mutation burden quantification across heterogeneous samples.

Accurate tumor mutation burden (TMB) quantification is critical for immunotherapy stratification, yet remains challenging due to variability across sequencing platforms, tumor heterogeneity, and variant calling pipelines. Here, we introduce TMBquant, an explainable AI-powered caller designed to optimize TMB estimation through dynamic feature selection, ensemble learning, and automated strategy adaptation. Built upon the H2O AutoML framework, TMBquant integrates variant features, minimizes classification errors, and enhances both accuracy and stability across diverse datasets.

CF-DTI: coarse-to-fine feature extraction for enhanced drug-target interaction prediction.

Accurate prediction of drug-target interactions (DTIs) is crucial for improving the efficiency and success rate of drug development. Despite recent advancements, existing methods often fail to leverage interaction features at multiple granular levels, resulting in suboptimal data utilization and limited predictive performance. To address these challenges, we propose CF-DTI, a coarse-to-fine drug-target interaction model that integrates both coarse-grained and fine-grained features to enhance predictive accuracy.

AGRL-DSE: Adaptive Graph Representation Learning on a Heterogeneous Graph for Drug Side Effect Prediction.

Identifying side effects is crucial for drug development and postmarket surveillance. Several computational methods based on graph neural networks (GNNs) have been developed, leveraging the topological structure and node attributes in graphs with promising results. However, existing heterogeneous-network-based approaches often fail to fully capture the complex structure and rich semantic information within these networks.

Medical gases in respiratory diseases: ozone, argon, and nitric oxide as game-changers in therapeutics.

Respiratory diseases pose a significant global health burden, prompting the exploration of novel therapeutic strategies. This narrative review consolidates existing knowledge and critically examines the evolving role of medical gases, ozone, argon, and nitric oxide (NO), in respiratory medicine. Based on recent literature, it highlights how these gases, originally used for their physicochemical properties, have now undergone a "functional crossover," revealing their broad therapeutic potential.

Impact of carotid web orientation on long-term thrombus growth risk: A numerical study using fluid-solid interaction.

Background: Carotid web (CaW) is a rare fibromuscular dysplasia lesion at the carotid bifurcation linked to thromboembolic events in young patients. CaW-induced hemodynamic disturbances contribute to thrombosis, but the impact of CaW morphology on long-term thrombotic risk remains unclear.

Method: This study developed three-dimensional numerical models based on patient-specific carotid artery anatomy with CaW angles of 30°, 60°, and 90° (models A, B, and C).

CDLR-net: a ECG classification network based on deep residual shrinkage networks and LSTM.

Many traditional classification networks directly use the limb two-lead signal (MLII) ECG signals as input for training. However, this method suffers from reduced accuracy when ECG features are not obvious, especially for premature heartbeats. To solve the issue, this paper proposed a novel network, namely CDLR-Net, that combines a Deep Residual Shrinkage Network (DRSN) with a Long Short-Term Memory (LSTM).

Cognitive prediction using regional connectivities and network biomarkers in Alzheimer's disease.

Achieving a deep understanding of brain mechanisms requires multi-scale perspectives to capture the architecture of complex networks. In this study, we focused on patients with cognitive impairment and constructed individual brain networks from neuroimaging data. We introduced a Significant Edges Selection (SES) method, which effectively extracts the most informative connections while suppressing noise.

HWANet: A Haar Wavelet-based Attention Network for remote sensing object detection.

Remote sensing object detection (RSOD) is highly challenging due to large variations in object scales. Existing deep learning-based methods still face limitations in addressing this challenge. Specifically, reliance on stride convolutions during downsampling leads to the loss of object information, and insufficient context-aware modeling capability hampers full utilization of object information at different scales.

EBAMP: An efficient de novo broad-spectrum antimicrobial peptide discovery framework.

De novo design of antimicrobial peptides (AMPs) is challenging due to the vast combinatorial space and unknown mechanisms. We propose EBAMP, a generative-discriminative framework for de novo broad-spectrum AMP design targeting bacteria and fungi. EBAMP combines a Transformer-based generative model with advanced feature-based screening to explore peptide space and select multiobjective candidates.

Accurate prediction of toxicity peptide and its function using multi-view tensor learning and latent semantic learning framework.

Motivation: Therapeutic peptide is an important ingredient in the treatment of various diseases and drug discovery. The toxicity of peptides is one of the major challenges in peptide drug therapy. With the abundance of therapeutic peptides generated in the post-genomics era, it is a challenge to promptly identify toxicity peptides using computational methods.

MGRL-DDI: Multiview Graph Representation Learning for Accurate Drug-Drug Interaction Prediction.

Drug-drug interactions (DDIs) present a significant challenge in clinical practice, as they may lead to adverse reactions, diminished therapeutic efficacy, and serious risks to patient safety. However, most existing methods depend on single-view representations of drug molecules or substructures, which limits their capacity to capture the diverse and complex nature of drug properties. To overcome this limitation, we propose MGRL-DDI, a multiview graph representation learning framework that comprehensively models drug structures from three complementary perspectives: Three-dimensional (3D) molecular graphs, motif graphs, and molecular graphs.

Towards Generic Abdominal Multi-Organ Segmentation with multiple partially labeled datasets.

An increasing number of publicly available datasets have facilitated the exploration of building universal medical segmentation models. Existing approaches address partially labeled problem of each dataset by harmonizing labels across datasets and independently focusing on the labeled foreground regions. However, significant challenges persist, particularly in the form of cross-site domain shifts and the limited utilization of partially labeled datasets.

MSFI: Multi-timescale spatio-temporal features integration in spiking neural networks.

Dynamic vision sensors (DVS) asynchronously encode the polarity of brightness changes with high temporal resolution and a wide dynamic range, making them ideal for capturing temporal information. Spiking neural networks (SNNs) are well-suited for handling such event streams due to their inherent temporal information processing capability. However, existing SNNs only transmit membrane potential across timesteps, neglecting spatial dependencies and failing to extract complex temporal features.

Awakening, condensation, and sedimentation: the correlation mechanism between topics and emotions in online public opinion from the psychosocial anchoring perspective.

Emotions significantly shape how publics interpret and engage with crises on social media, yet most public-opinion research treats thematic structures and affective dynamics in isolation. Drawing on social representation theory and psychosocial anchoring, this mixed-methods study examines the interplay of topics and emotions during the 2023 "Rat Head and Duck Neck" food safety incident on Chinese social media. By analyzing posts through LDA topic modeling, TextCNN-based sentiment analysis, and qualitative content analysis, the analysis reveals three dominant emotions: disgust, anger, and satire, and three central topics: food, trust, and power.

Beyond single perspective bias: Fusing personalized and common preferences for comprehensive personal preference learning.

In recommendation systems, Graph Convolutional Network (GCN)-based models are generally influenced by popular items. Over-emphasizing these items can lead to a single-perspective bias that overshadows the learning of the user's personalized preferences. Therefore, existing GCN-based models usually suppress information from popular items.

A Generalized and Interpretable Multi-Label Multi-Disease Screening System for Ocular Anterior Segment Disease Detection.

Objective: To develop and validate a multi-label, multi-disease, well-generalized, and interpretable screening system applied to the detection of common ocular anterior segment diseases based on ocular surface slit-lamp images.

Design: A multicenter artificial intelligence diagnostic study.

Participants: A total of 1990 patients were randomly selected from 2 medical centers: the Second Affiliated Hospital of Zhejiang University and the Affiliated People's Hospital of Ningbo University, between November 2016 and March 2022.

Artificial intelligence-enhanced ultrasound imaging for thyroid nodule detection and malignancy classification: a study on YOLOv11.

Background: Thyroid nodules are a common clinical concern, with accurate diagnosis being critical for effective treatment and improved patient outcomes. Traditional ultrasound examinations rely heavily on the physician's experience, which can lead to diagnostic variability. The integration of artificial intelligence (AI) into medical imaging offers a promising solution for enhancing diagnostic accuracy and efficiency.

Novel RANSAC-based method for detecting and estimating externally attached marker spheres in craniomaxillofacial CT images.

Background: The precision of image-physical space registration using spherical markers in craniomaxillofacial surgical navigation significantly depends on the accurate estimation of spherical parameters from computed tomography (CT) images. However, this estimation is susceptible to the abnormal points caused by artifacts, instruments interference, and other factors. To address these challenges, this study proposes a robust method to improve reproducibility in results and achieve higher accuracy on low inlier ratio data, thereby meeting the requirements of high-precision surgical applications.