A5020634083- Medical Image Segmentation Techniques
- Advanced Neural Network Applications
- Ferroptosis and cancer prognosis
- Epigenetics and DNA Methylation
- Advanced Image and Video Retrieval Techniques
- Structural Response to Dynamic Loads
- Optical Systems and Laser Technology
- 3D Surveying and Cultural Heritage
- Computer Graphics and Visualization Techniques
- Pancreatic and Hepatic Oncology Research
- Domain Adaptation and Few-Shot Learning
- High-Velocity Impact and Material Behavior
- 3D Shape Modeling and Analysis
- Retinal Diseases and Treatments
- Remote Sensing and LiDAR Applications
- Human Pose and Action Recognition
- Winter Sports Injuries and Performance
- Cardiovascular Syncope and Autonomic Disorders
- RNA modifications and cancer
- Retinal Imaging and Analysis
- Combustion and Detonation Processes
- Medical Imaging and Analysis
- Advanced Vision and Imaging
- Optical measurement and interference techniques
- Heart Rate Variability and Autonomic Control
China University of Petroleum, East China
2022-2025
Institute of Software
2022-2024
Northwest A&F University
2023-2024
Zunyi Medical University
2024
Nanjing University of Science and Technology
2023-2024
Hubei University
2024
Nanjing Medical University
2021-2022
The Fourth People's Hospital of Zibo City
2022
Jiangsu Province Hospital
2021-2022
Kunming Medical University
2021
Accurate wind power prediction is crucial for the safe and stable operation of grid. However, generation has large random volatility intermittency, which increases difficulty prediction. In order to construct an effective model based on achieve grid dispatch after connected grid, a WT-BiGRU-Attention-TCN proposed. First, wavelet transform (WT) used reduce noises sample data. Then, temporal attention mechanism incorporated into bi-directional gated recurrent unit (BiGRU) highlight impact key...
Abstract Objective. Retinal vessel segmentation from optical coherence tomography angiography (OCTA) volumes is significant in analyzing blood supply structures and the diagnosing ophthalmic diseases. However, accurate retinal 3D OCTA remains challenging due to interference of choroidal flow signals variations structure. Approach. This paper proposes a layer attention network (LA-Net) for 3D-to-2D segmentation. The comprises projection path 2D path. key component proposed multi-scale module,...
The movement data of curling targets is great significance for the analysis and research curling. However, in real-life competitions, volume limited easy to be occluded, venue background illumination complicated. To address these challenges, a target detection model, IFCD, based on Inverted Feature Extraction Network (IFNet) proposed. IFNet allocates more resources deal with high-resolution features without introducing additional computational burdens, thus avoiding feature loss caused by...
Transformer-based models have made significant progress in edge detection, but their high computational cost is prohibitive. Recently, vision Mamba shown excellent ability efficiently capturing long-range dependencies. Drawing inspiration from this, we propose a novel detector with Mamba, termed EDMB, to generate high-quality multi-granularity edges. In combined global-local architecture, therefore it can focus on both global information and fine-grained cues. The cues play crucial role are...
Smoothing of the graph convolution is not conducive to characterizing local differences point cloud. To solve this problem, we propose a Differential Graph Convolutional Network (Differ-GCN) for cloud analysis. First, new construction strategy that can make similar nodes in space belong same graph, which better represent commonality. After that, features are extracted by similarity matrix. Some smoothing information removed optimize over-smoothing and combined with difference points get...
Abstract Background Cerebrovascular segmentation is a crucial step in the computer‐assisted diagnosis of cerebrovascular pathologies. However, accurate extraction cerebral vessels from time‐of‐flight magnetic resonance angiography (TOF‐MRA) data still challenging due to complex topology and slender shape. Purpose The existing deep learning‐based approaches pay more attention skeleton ignore contour, which limits performance structure. We aim weight contour brain shallow features when...
Background: Glioma is a prevalent type of malignant tumor. To date, there lack literature reports that have examined the association between sulfatase modifying factor 1 (SUMF1) and glioma. Methods: The levels SUMF1 were examined, their relationships with diagnosis, prognosis, immune microenvironment patients glioma investigated. Cox Lasso regression analysis employed to construct nomograms risk models associated SUMF1. functions mechanisms explored verified using gene ontology, cell...
The load-bearing capacity of reinforced concrete (RC) beams primarily relies on internal bars. However, limited research has been conducted the dynamic response these To address this gap, study established an analytical model using dimensional analysis for calculating deformation bars within RC subjected to contact explosion. Comparison with experimental data reveals that a relative error 5.22%, effectively reflecting Additionally, based model, found while does influence bars, can be...
This paper investigates the damaged area of a reinforced concrete beam under rectangular explosive contact explosion, through full-scale tests and numerical simulation. The calculation equation surface load distribution based on equivalent impulse is established, with consideration effect length height distribution, damage further proposed. Through changing mass TNT (1~6 kg) shape 1 kg explosive, 5 cases test were carried out beam. divided into three parts: blasting crater, span front face,...
Large deformation is a key issue for deformable medical image registration. Decomposing large into several small deformations an efficient solution. Current decomposition methods can be classed iteration-based and non-iterative-based approaches. However, compared to methods, have faster inference times but registration accuracy gaps. To alleviate this limitation, we design novel Non-iterative Pyramid Network (NIPNet). Firstly, Our Dual-domain Feature Extraction Module (DFEM) extracts global...
The performance of deep learning based edge detector has far exceeded that humans, but the huge computational cost and complex training strategy hinder its further development application. In this paper, we eliminate these complexities with a vanilla encoder-decoder detector. Firstly, design bilateral encoder to decouple extraction process location features semantic features. Since branch no longer provides cues for branch, richness can be compressed, which is key make our model more...