A5100406043- Medical Imaging Techniques and Applications
- Radiomics and Machine Learning in Medical Imaging
- Medical Image Segmentation Techniques
- Advanced Steganography and Watermarking Techniques
- Digital Media Forensic Detection
- Advanced Neural Network Applications
- Video Surveillance and Tracking Methods
- Liver Disease Diagnosis and Treatment
- Advanced Image and Video Retrieval Techniques
- Advanced MRI Techniques and Applications
- Advanced X-ray and CT Imaging
- Hepatocellular Carcinoma Treatment and Prognosis
- Image Processing Techniques and Applications
- Cloud Computing and Resource Management
- Video Analysis and Summarization
- Renal cell carcinoma treatment
- Image and Video Stabilization
- Inflammatory mediators and NSAID effects
- Advanced Computing and Algorithms
- Vehicle License Plate Recognition
- Advanced Graph Neural Networks
- Generative Adversarial Networks and Image Synthesis
- Neurotransmitter Receptor Influence on Behavior
- Image and Object Detection Techniques
- Domain Adaptation and Few-Shot Learning
First Affiliated Hospital of Dalian Medical University
2025
Southern Medical University
2024-2025
Guangdong Provincial People's Hospital
2025
Dalian Medical University
2025
Wuhan University
2024
Fuzhou University
2016-2024
Shandong University of Science and Technology
2024
Northwest Normal University
2024
University of Science and Technology of China
2023
Shenzhen Third People’s Hospital
2023
Radiomics is an objective method for extracting quantitative information from medical images. However, in radiomics, standardization, overfitting, and generalization are major challenges to be overcome. Test–retest experiments can used select robust radiomic features that have minimal variation. Currently, it unknown whether they should identified each disease (disease specific) or only imaging device-specific (computed tomography [CT]-specific). Here, we performed a test–retest analysis on...
The severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) is still epidemic around the world. manipulation of SARS-CoV-2 restricted to biosafety level 3 laboratories (BSL-3). In this study, we developed a ΔN-GFP-HiBiT replicon delivery particles (RDPs) encoding dual reporter gene, GFP-HiBiT, capable producing both GFP signal and luciferase activities. Through optimal selection GFP-HiBiT demonstrated superior stability convenience for antiviral evaluation. Additionally, established RDP...
Background. Oxidative stress is one of the most critical factors that contribute to pathogenesis neuronal damage, including diabetic peripheral neuropathy (DPN). Uric acid a kind natural antioxidant plays major role in capacity against oxidative stress. Here, we aim determine serum uric (SUA) DPN patients with type 2 diabetes mellitus (T2DM). Patients and Methods. 106 T2DM were recruited divided into group control group. Clinical parameters, especially for motor nerve fiber conduction...
Previous observational studies have indicated a correlation between the skin microbiome and Type 2 diabetes (T2DM). It is hypothesized that this causal relationship may be influenced by inflammatory responses. However, these factors as determinants of T2DM remain largely unexplored. This study incorporated data from GWAS database on microbiome, 91 types cytokines, T2DM. We employed two-sample MR multivariable methods to assess T2DM, investigate whether affected cytokines. The results...
The neutrophil-percentage-to-albumin ratio (NPAR) has emerged as a concise and effective biomarker for assessing systemic inflammatory status, with established prognostic value mortality risk across various disease populations. This study aimed to elucidate the association between NPAR both all-cause cardiovascular in patients diabetes prediabetes. A cohort of 8560 prediabetes was recruited from National Health Nutrition Examination Survey (NHANES), outcomes tracked through Death Index up...
Although a large number of functional magnetic resonance imaging (fMRI) studies have investigated the neural bases empathy, little is known about its spatiotemporal dynamics or modulation by level friendship between observer and agent who being hurt. Moreover, most previous on empathy focused for pain rather than positive emotions, such as happiness. In present study, we addressed this question investigating brain two different kinds (empathy pain, happiness) with behavioral priming task...
Abstract Efficient allocation of tasks and resources is crucial for the performance heterogeneous cloud computing platforms. To achieve harmony between task completion time, device power consumption, load balance, we propose a Graph neural network-enhanced Elite Particle Swarm Optimization (EPSO) model collaborative scheduling, namely GraphEPSO. Specifically, first construct Directed Acyclic (DAG) to complicated tasks, thereby using Neural Network (GNN) encode information sets resources....
Insulin resistance (IR) is a pivotal factor in the pathogenesis of type 2 diabetes mellitus (T2DM) and non-alcoholic fatty liver disease (NAFLD). Nevertheless, impact IR on cognitive dysfunction T2DM patients with NAFLD remains inadequately understood. We aim to investigate effect mild impairment (MCI) individuals NAFLD.143 were categorized into Non-MCI MCI groups, as well Non-NAFLD groups. Clinical parameters preference test outcomes compared. Correlation regression analyses executed...
Two main restrictions exist in state-of-the-art text detection algorithms: 1. Illumination variance; 2. Text-background contrast variance. This paper presents a robust characterization approach based on local Haar binary pattern (LHBP) to address these problems. Based LHBP, coarse-to-fine framework is presented precisely locate lines scene images. Firstly, threshold-restricted extracted from high-frequency coefficients of pyramid wavelet. It preserves and uniforms inconsistent...
With the advent of digital technology, image has gradually taken place original analog photograph, and forgery become more easy indiscoverable. Image splicing is a commonly used technique in tampering. To implement detection blind, passive effective scheme was proposed this paper. can be treated as two-class pattern recognition problem, model based on moment features some quality metrics (IQMs) extracted from given test image, which are sensitive to spliced image. Artificial neural network...
This study delves into the role of N-terminal propeptide type III collagen (PIIINP) in diagnosis and management liver pathological changes associated with non-alcoholic steatohepatitis (NASH).
Automatic segmentation and centerline extraction of blood vessels from retinal fundus images is an essential step to measure the state achieve goal auxiliary diagnosis. Combining information vessel segments can help improve continuity results performance. However, previous studies have usually treated these two tasks as separate research topics. Therefore, we propose a novel multitask learning network (MSC-Net) for extraction. The uses multibranch design combine between tasks. Channel atrous...