A5039270843- Radiomics and Machine Learning in Medical Imaging
- Medical Imaging Techniques and Applications
- Video Surveillance and Tracking Methods
- Advanced Vision and Imaging
- Advanced X-ray and CT Imaging
- Peptidase Inhibition and Analysis
- Neural Networks and Applications
- Advanced MRI Techniques and Applications
- Fire Detection and Safety Systems
- Infrared Target Detection Methodologies
- Protease and Inhibitor Mechanisms
- 2D Materials and Applications
- Signaling Pathways in Disease
- Human Pose and Action Recognition
- Advanced Neural Network Applications
- Dental Radiography and Imaging
- Gas Sensing Nanomaterials and Sensors
- Video Coding and Compression Technologies
- EEG and Brain-Computer Interfaces
- Advanced Image Processing Techniques
- MXene and MAX Phase Materials
- Multisensory perception and integration
- Advanced Measurement and Detection Methods
- Cardiac Structural Anomalies and Repair
- Image Enhancement Techniques
Ruijin Hospital
2024-2025
Shanghai Jiao Tong University
2020-2025
Anyang Normal University
2023
Xi'an Jiaotong University
2017-2020
Dalian National Laboratory for Clean Energy
2017
Dalian Institute of Chemical Physics
2017
Chinese Academy of Sciences
2017
Xiangtan University
2017
Shanxi University
2013-2014
As is well known, NO2 adsorption plays an important role in gas sensing and treatment because it expands the residence time of compounds to be treated plasma–catalyst combination. In this work, behaviors mechanism over pristine Se-vacancy defect-engineered WSSe monolayers have been systematically investigated using density functional theory (DFT). The energy calculation reveals that introducing Se vacancy acould result a physical-to-chemical transition for system. vacancy, most possible...
Positron Emission Tomography (PET) has become a preferred imaging modality for cancer diagnosis, radiotherapy planning, and treatment responses monitoring. Accurate automatic tumor segmentation is the fundamental requirement these clinical applications. Deep convolutional neural networks have state-of-the-art in PET segmentation. The normalization process one of key components accelerating network training improving performance network. However, existing methods either introduce batch noise...
In recent years, visual object tracking has been widely used in military guidance, human-computer interaction, road traffic, scene monitoring and many other fields. The algorithms based on correlation filters have shown good performance terms of accuracy speed. However, their is not satisfactory scenes with scale variation, deformation, occlusion. this paper, we propose a scene-aware adaptive updating mechanism for via kernel filter (KCF). First, low complexity estimation method presented,...
Intra/inter switching-based error resilient video coding effectively enhances the robustness of streaming when transmitting over error-prone networks. But it has a high computation complexity, due to detailed end-to-end distortion prediction and brute-force search for rate-distortion optimization. In this article, Low Complexity Mode Switching based Error Resilient Encoding (LC-MSERE) method is proposed reduce complexity encoder through deep learning approach. By designing training...
In secondary hyperparathyroidism (SHPT) disease, preoperatively localizing hyperplastic parathyroid glands is crucial in the surgical procedure. These can be detected via dual-modality imaging technique single-photon emission computed tomography/computed tomography (SPECT/CT) since it has high sensitivity and provides an accurate location. However, due to possible low-uptake SPECT images, manually labeling challenging, not mention automatic label methods. this work, we present a deep...
Object tracking is an important research direction in computer vision and widely used video surveillance, security monitoring, analysis other fields. Conventional algorithms perform poorly specific scenes, such as a target with fast motion occlusion. The candidate samples may lose the true due to its motion. Moreover, appearance of change movement. In this paper, we propose object algorithm based on consistency. state transition model, are obtained by state, which predicted according...