A5101883693- Medical Image Segmentation Techniques
- Advanced Neural Network Applications
- Radiomics and Machine Learning in Medical Imaging
- Medical Imaging and Analysis
- Advanced Image and Video Retrieval Techniques
- Image and Object Detection Techniques
- Brain Tumor Detection and Classification
- Retinal Imaging and Analysis
- Advanced Radiotherapy Techniques
- Video Surveillance and Tracking Methods
- Medical Imaging Techniques and Applications
- AI in cancer detection
- Visual Attention and Saliency Detection
- Image Processing Techniques and Applications
- Image Retrieval and Classification Techniques
- Robotics and Sensor-Based Localization
- Advanced Image Fusion Techniques
- Reinforcement Learning in Robotics
- Handwritten Text Recognition Techniques
- Vehicle License Plate Recognition
- Advanced Steganography and Watermarking Techniques
- Digital Imaging for Blood Diseases
- Advanced Vision and Imaging
- Digital Media Forensic Detection
- Image Enhancement Techniques
Central South University
2016-2025
State Key Laboratory of Surface Physics
2024
Fudan University
2024
Northeastern University
2009-2023
Tongji University
2023
National University of Defense Technology
2017-2022
Beijing Academy of Artificial Intelligence
2021-2022
Hebei University of Economics and Business
2021
Universidad del Noreste
2021
Changsha University of Science and Technology
2020
Medical images edge detection is an important work for object recognition of the human organs and it pre-processing step in medical image segmentation 3D reconstruction. Conventionally, detected according to some early brought forward algorithms such as gradient-based algorithm template-based algorithm, but they are not so good noise detection. In this paper, basic mathematical morphological theory operations introduced at first, then a novel proposed detect lungs CT with salt-and-pepper...
Liver tumor segmentation plays an essential role in diagnosis and treatment of hepatocellular carcinoma or metastasis. However, accurate automatic remains a challenging task, owing to vague boundaries large variations shapes, sizes, locations liver tumors. In this paper, we propose novel hybrid end-to-end network, called TD-Net, which incorporates Transformer direction information into convolution network segment from CT images automatically. The proposed TD-Net is composed shared encoder,...
RGBT tracking is rapidly developing due to its complementary advantages of RGB and thermal frames. Existing methods with high accuracy track at a lower speed, do not make full use the hierarchical information in feature extraction historical sequences. To address these issues, novel dual-modality space-time memory (DMSTM) network proposed for robust tracking. Specifically, DMSTM divided into three modules. The first module backbone that utilizes both shallow deep by aggregating maps...
Vessel segmentation in retinal fundus images is a preliminary step to clinical diagnosis for some systemic diseases and eye diseases. The performances of existing methods segmenting small vessels which are usually more importance than the main not satisfactory use. In this paper, we present method both peripheral vessel segmentation. A local gray-level change enhancement algorithm called gray-voting used enhance vessels, while two-dimensional Gabor wavelet extract vessels. We fuse results...
Edge detection is an important pre-processing step in image analysis. Conventionally, mathematical morphology edge methods use single and symmetrical structure elements. But they are difficult to detect complex feature, because only sensitive which has the same direction of This paper proposed a novel algorithm based on multi-structure elements eight different directions. We got results by using morphological gradient respectively, final result was synthetic weighted method. The experimental...
Aiming at improving the performance of scale invariant feature transform (SIFT) algorithm during registration optical and synthetic aperture radar (SAR) images, a new SIFT is proposed. Firstly, nonlinear diffusion space SAR images constructed by using filtering, uniform gradient information calculated multi-scale Sobel operator exponential weighted mean ratio respectively. Then, after removing first layer with image blocking strategy, partitioned, Harris points are extracted on basis...
The use of convolution neural networks (CNN) to accurately predict dose distributions can accelerate intensity-modulated radiation therapy (IMRT) planning. purpose our study is develop a novel deep learning architecture for precise voxel-level prediction on brain tumors.A dataset 120 patients with tumors built the retrospective study. are predicted by designed end-to-end model called TS-Net, in which transformer encoder module utilized obtain abundant global features long-range correlations...
Liver cancer is a major global health challenge, significantly contributing to mortality rates. The accurate segmentation of liver and tumors from clinical CT images plays crucial role in selecting therapeutic strategies for disease treatment monitoring but remains challenging due shape variability, proximity other organs, low contrast between healthy tissues, unclear lesion boundaries. To address these challenges, we propose the Deep Residual Dual-Attention Network (DRDA-Net), novel model...