A5100402310- Advanced MRI Techniques and Applications
- Advanced Neuroimaging Techniques and Applications
- Photoacoustic and Ultrasonic Imaging
- Medical Imaging Techniques and Applications
- Industrial Vision Systems and Defect Detection
- Bone Tissue Engineering Materials
- Non-Destructive Testing Techniques
- Advanced X-ray and CT Imaging
- Advanced Image Fusion Techniques
- Complex Systems and Time Series Analysis
- MRI in cancer diagnosis
- Forest, Soil, and Plant Ecology in China
- Computer Graphics and Visualization Techniques
- Market Dynamics and Volatility
- Sparse and Compressive Sensing Techniques
- Nanoplatforms for cancer theranostics
- Graphene and Nanomaterials Applications
- Remote-Sensing Image Classification
- Advanced Fluorescence Microscopy Techniques
- Remote Sensing and Land Use
- Imbalanced Data Classification Techniques
- CO2 Reduction Techniques and Catalysts
- Pituitary Gland Disorders and Treatments
- Educational Technology and Pedagogy
- Electromagnetic wave absorption materials
Ningxia Medical University
2025
Ningxia Medical University General Hospital
2025
Ningxia Center for Diseases Prevention and Control
2025
Southeast University
2025
University of America
2024
University at Buffalo, State University of New York
2017-2024
Shandong University of Science and Technology
2022-2024
Dalian University of Technology
2024
Shandong University of Technology
2024
Liaoning Technical University
2024
With the widespread use of credit cards in online and offline transactions, card fraud has become a significant challenge financial sector. The rapid advancement payment technologies led to increasingly sophisticated techniques, necessitating more effective detection methods. While machine learning been extensively applied detection, application deep methods remains relatively limited. Inspired by brain-like computing, this work employs Continuous-Coupled Neural Network (CCNN) for detection....
Purpose: To propose a deep learning-based reconstruction framework for ultrafast and robust diffusion tensor imaging fiber tractography. Methods: We SuperDTI to learn the nonlinear relationship between diffusion-weighted images (DWIs) corresponding tensor-derived quantitative maps as well Super DTI bypasses fitting procedure, which is known be highly susceptible noise motion in DWIs. The network trained tested using datasets from Human Connectome Project patients with ischemic stroke....
Given the increasing popularity of wearable devices, this paper explores potential to use wearables for steering and driver tracking. Such capability would enable novel classes mobile safety applications without relying on information or sensors in vehicle. In particular, we study how wrist-mounted inertial sensors, such as those smart watches fitness trackers, can track wheel usage angle. tracking turning angle provide fundamental techniques improve driving detection, enhance vehicle motion...
With the innovation of photosensitizers, photodynamic therapy is now widely used in antitumor detection and treatment. Graphene quantum dots (GQDs) are proposed as a promising alternative photosensitizer due to their high biocompatibility, specific photoactivity, strong tumor concentration. However, changes host immunity triggered by GQDs have only rarely been reported. In this work, photosensitizers were conjugated polyethylene glycol (PEG) enhance solubility blood circulation. The...
Spectroscopic single-molecule localization microscopy (sSMLM) simultaneously provides spatial and spectral information of individual single-molecules emission, offering multicolor super-resolution imaging multiple molecules in a single sample with the nanoscopic resolution. However, this technique is limited by requirements acquiring large number frames to reconstruct image. In addition, sSMLM suffers from cross-talk while using dyes relatively broad bands that produce cross-color...
Although transfer entropy can test the nonlinear causal relationship between sequences, it is mainly used for stationary data. For nonstationary sequences with large fluctuations, traditional method has obvious defects. Based on entropy, this paper proposes a rolling windows. We verify that new capture dynamic order and better reveal causality time series. Furthermore, we construct an investor sentiment index based principal component analysis, proposed model, analyze information among...
Purpose To develop an ultrafast and robust MR parameter mapping network using deep learning. Theory Methods We design a learning framework called SuperMAP that directly converts series of undersampled (both in k‐space parameter‐space) parameter‐weighted images into several quantitative maps, bypassing the conventional exponential fitting procedure. also present novel technique to simultaneously reconstruct T1rho T2 relaxation maps within single scan. Full data were acquired retrospectively...
A new image segmentation algorithm based on mean shift (MS) is proposed, with an objective to single out croplands in high-resolution remote sensing imagery (HRRSI). The composed of two parts. First, order improve the discontinuity preserving smoothing MS filtering for cropland HRRSI, normal and uniform kernels are used filter inner fields boundary areas, respectively. spectral bandwidth estimation also developed better suppressing intra-field variation. Second, a two-stage region-merging...
Abstract State‐of‐health (SOH) estimation methods for Li‐ion batteries are important the safe operation of entire system. However, it is often challenging due to uncertainty within and criteria model interpretability. Belief rule base (BRB) a rule‐based expert system that has certain advantages both aspects. several problems with BRB interpretability need be solved urgently. First, knowledge credibility given subjectively, while objective information neglected considered. Second, easily...
Abstract The transcriptomic analysis was used to explore the effect of electroacupuncture therapy with distant-approximal acupoints based on hypothalamic-pituitary–testicular (HPT) gene expression patterns and pathways in oligoasthenospermia (OAT) rats. In this study, rat model OAT after intragastric administration adenine selected as research object, randomly divided into a blank group (C), (M), (D). After intervention, epididymal sperm quality serum sex hormone levels rats detected three...
MRI acceleration using deep learning (DL) convolutional neural networks (CNNs) is a novel technique with great promise. Increasing the number of layers may allow for more accurate image reconstruction. Studies on evaluating diagnostic interchangeability DL reconstructed knee magnetic resonance (MR) images are scarce. The purpose this study was to develop CNN (DCNN) an optimal accelerating imaging (MRI) acquisition by 6-fold and test quality nonaccelerated versus 15-layer DCNN or 3-layer...
The biological behaviors of magnetic graphene oxide (MGO) in a static field (SMF) are unknown. current study is to investigate the cellular behaviors, osteogenesis and mechanism BMSCs treated with MGO combined an SMF. Results showed that synthetic particles were bio-compatible could significantly improve under SMFs, as verified by elevated alkaline phosphatase activity, mineralized nodule formation, expressions mRNA protein levels. Under SMF at same intensity, addition Fe3O4 increase...
A library of 14 dynamic glycopeptide amphiphilic dendrimers composed hydrophilic and bioactive saccharides (seven kinds) as dendrons 7 hydrophobic peptides (di- tetrapeptides) arms with β-cyclodextrin (CD) a core were facially designed synthesized in several steps. Fourteen first conjugated to the C-2 C-3 positions CD, forming glycodendrons. Subsequently, seven oligopeptide introduced at C-6 CD moiety by an acylhydrazone covalent bond, resulting unique Janus precise varied molecular...
The secreting function of pituitary adenomas (PAs) plays a critical role in making the treatment strategies. However, Magnetic Resonance Imaging (MRI) analysis for is labor intensive and highly variable among radiologists. In this work, by applying convolutional neural network (CNN), we built segmentation classification model to help distinguish functioning from non-functioning subtypes with 3D MRI images 185 patients PAs (two centers). Specifically, adopts concept transfer learning uses...