A5100376907- Advanced Image Fusion Techniques
- Radiomics and Machine Learning in Medical Imaging
- Image and Signal Denoising Methods
- AI in cancer detection
- Image Processing Techniques and Applications
- COVID-19 diagnosis using AI
- Aviation Industry Analysis and Trends
- Robotics and Sensor-Based Localization
- Remote-Sensing Image Classification
- Air Traffic Management and Optimization
- Cardiac Imaging and Diagnostics
- Robotic Path Planning Algorithms
- Brain Tumor Detection and Classification
- Vehicle Dynamics and Control Systems
- Nanomaterials for catalytic reactions
- Magnetic Properties and Applications
- Digital Imaging for Blood Diseases
- Sparse and Compressive Sensing Techniques
- Railway Systems and Energy Efficiency
- Advanced MRI Techniques and Applications
- Mechanical Engineering and Vibrations Research
- Algebraic and Geometric Analysis
- Image Processing and 3D Reconstruction
- Infrared Target Detection Methodologies
- Indoor and Outdoor Localization Technologies
Sichuan University
2008-2023
University of South China
2022-2023
University of South Florida
2023
Jinan University
2023
Tianjin Chest Hospital
2023
University of Science and Technology of China
2023
People’s Hospital of Rizhao
2023
Qingdao University of Science and Technology
2022
Chengdu University
2013-2022
China Tobacco
2022
Acute Intracranial hemorrhage (ICH) is a life-threatening disease that requires emergency medical attention, which routinely diagnosed using non-contrast head CT imaging. The diagnostic accuracy of acute ICH on varies greatly among radiologists due to the difficulty interpreting subtle findings and time pressure associated with ever-increasing workload. use artificial intelligence technology may help automate process assist for more prompt better decision-making. In this work, we design deep...
For pixel‐level image fusion, the edges of source images should be as much possible integrated into fused because human visual system is sensitive to them. In this study, authors utilise multiscale edge‐preserving decomposition (MSEPD) based on weighted least squares filter fuse images. authors’ method, first, are decomposed by MSEPD a base and series detail images, respectively. Then, same scale combined via different fusion rules designed for kinds images; average‐value rule. Finally,...
Phototherapy is a conducive and non-invasive strategy for cancer therapy under light irradiation. Inspiringly, fluorescence imaging in the second near-infrared window (NIR-II, 1000-1700 nm) holds great promise imaging-guided phototherapy with deep penetration high spatiotemporal resolution. However, most phototherapeutics still face challenges, including complicated synthesis of agents, potential biotoxicity unsatisfied therapeutic outcomes. Herein, laser triggered molecular photosensitizer...
Aqueous zinc ion batteries (AZIBs) are appealing increasing attention for large-scale energy storage systems (ESS) due to their intrinsic safety, low cost, and scalability. Unfortunately, the Zn metal anode suffers from chaotic side reactions, rampant dendrite growth continuous hydrogen evolution, severely hampering application of AZIBs. Herein, trifunctional tranexamic acid (TXA) is introduced into aqueous electrolyte form unique anode/electrolyte interface, enhance steric effect regulate...
In this paper, we study the employment of multiple Unmanned Aerial Vehicles (UAVs) to monitor Points Interests (PoIs) in a disaster area, e.g., collapsed buildings after an earthquake, where UAVs can take photos and videos for people trapped at PoIs, because such valuable information is imperative make rescue decisions. Unlike most existing studies that ignored monitoring time PoIs simply minimized longest flying distance among UAVs, observe it takes PoIs. Then, possible UAV its tour may not...
In the clinical environment, myocardial infarction (MI) as one common cardiovascular disease is mainly evaluated using late gadolinium enhancement (LGE) cardiac magnetic resonance images (CMRIs). Accurate segmentation of ventricles and myocardium a prerequisite for quantitative assessment functions progression. Performing task LGE is, however, rather challenging due to heterogeneous image intensity distribution lack clear boundaries between adjacent organs tissues. this paper we propose deep...
In ground penetrating radar (GPR) records, because of different kinds noises, especially direct wave surface, the real target is not seen clearly in echo section, which makes detection targets difficult. Considering that waves among traces are change greatly and have strong correlation, so it can be restrained by certain methods. KL transform often used to pick up coherent noises random multi channel seismic records[U 4]. this paper, GPR data processing, fully uses second-order statistic...
Pneumothorax is common but a life-threatening thoracic disease, which difficult to diagnose based on chest X-ray images due its subtle characteristics and low contrast of the disease regions. We aim develop fully automatic pneumothorax segmentation method assist radiologists for timely accurate diagnosis pneumothorax. propose two-stage deep learning method. In first stage, image classified as having or not using an ensemble multiple modified U-Net models. Each model trained multitask...
Subtype classification is critical in the treatment of gliomas because different subtypes lead to options and postoperative care. Although many radiological- or histological-based glioma algorithms have been developed, most them focus on single-modality data. In this paper, we propose an innovative two-stage model classify into three (i.e., glioblastoma, oligodendroglioma, astrocytoma) based radiology histology first stage, our classifies each image as having glioblastoma not. Based obtained...
The nonsubsampled contourlet transform (NSCT) is a new multi-resolution transform, which can give an asymptotic representation of edges and contours in image by virtue its characteristics multi-direction, flexible multi-scale shift-invariant simultaneity. For fusion between visible light infrared image, this paper proposed method based on the visual region. Firstly, two original images were decomposed into different frequency sub-band coefficients using NSCT, then selection low subband...
In this paper, a new image fusion algorithm based on non-subsampled contourlet transform (NSCT) is proposed for the of multi-focus images. The selection different subband coefficients obtained by NSCT decomposition critical to fusion. So, in firstly, original images are decomposed into frequency NSCT. Secondly, low-frequency and bandpass directional discussed detail. For coefficients, non-negative matrix factorization (NMF) method adopted. regional cross-gradient that selects according...