A5042992199- Medical Image Segmentation Techniques
- Image and Signal Denoising Methods
- Ultrasound Imaging and Elastography
- Photoacoustic and Ultrasonic Imaging
- Image Processing Techniques and Applications
- Advanced Image Fusion Techniques
- Robotic Path Planning Algorithms
- Ultrasonics and Acoustic Wave Propagation
- Cerebrovascular and Carotid Artery Diseases
- Robotics and Sensor-Based Localization
- Advanced Image Processing Techniques
- Cardiovascular Health and Disease Prevention
- Image and Object Detection Techniques
- Advanced Vision and Imaging
- AI in cancer detection
- Ultrasound and Hyperthermia Applications
- Advanced Image and Video Retrieval Techniques
- Medical Imaging Techniques and Applications
- Retinal Imaging and Analysis
- Advanced Neural Network Applications
- Image Retrieval and Classification Techniques
- Flow Measurement and Analysis
- Medical Imaging and Analysis
- Radiomics and Machine Learning in Medical Imaging
- Computer Graphics and Visualization Techniques
Huazhong University of Science and Technology
2016-2025
Fujian Agriculture and Forestry University
2024
Wuhan University
2022-2024
City University of Hong Kong, Shenzhen Research Institute
2022-2024
North China Electric Power University
2023
Xidian University
2020-2023
China Electric Power Research Institute
2023
Zhengzhou University
2022
Henan Provincial People's Hospital
2022
Nanchang University
2022
A new variant of particle swarm optimization (PSO), named phase angle-encoded and quantum-behaved (θ-QPSO), is proposed. Six versions θ-QPSO using different mappings are presented compared through their application to solve continuous function problems. Several representative benchmark functions selected as testing functions. The real-valued genetic algorithm (GA), differential evolution (DE), standard ( θ-PSO), (QPSO), tested with each other on the unimodal multimodal To corroborate results...
This paper presents a hybrid differential evolution (DE) with quantum-behaved particle swarm optimization (QPSO) for the unmanned aerial vehicle (UAV) route planning on sea. The proposed method, denoted as DEQPSO, combines DE algorithm QPSO in an attempt to further enhance performance of both algorithms. UAV sea is formulated problem. A simple method pretreatment terrain environment proposed. novel planner designed generate safe and flyable path presence different threat environments based...
Based on evolutionary computation, a novel real-time route planner for unmanned air vehicles is presented. In the planner, individual candidates are evaluated with respect to workspace so that computation of configuration space not required. The incorporates domain-specific knowledge, can handle unforeseeable changes environment, and take into account different kinds mission constraints such as minimum leg length flying altitude, maximum turning angle, fixed approach vector goal position....
Quantification of carotid plaques has been shown to be important for assessing as well monitoring the progression and regression atherosclerosis. Various metrics have proposed methods measurements ranging from manual tracing automated segmentations also investigated. Of those metrics, quantification by measuring vessel-wall-volume (VWV) using segmented media-adventitia (MAB) lumen-intima (LIB) boundaries sensitive temporal changes in plaque burden. Thus, semi-automatic MAB LIB segmentation...
Medical image classification plays an important role in disease diagnosis since it can provide reference information for doctors. The supervised convolutional neural networks (CNNs) such as DenseNet the versatile and effective method medical tasks, but they require large amounts of data with labels involve complex time-consuming training process. unsupervised CNNs principal component analysis network (PCANet) need no cannot desirable accuracy. To realize accurate case a small dataset, we...
In the field of disease diagnosis where only a small dataset medical images may be accessible, light-weight convolutional neural network (CNN) has become popular because it can help to avoid over-fitting problem and improve computational efficiency. However, feature extraction capability CNN is inferior that heavy-weight counterpart. Although attention mechanism provides feasible solution this problem, existing modules, such as squeeze excitation module block module, have insufficient...
Measurement of total-plaque-area (TPA) is important for determining long term risk stroke and monitoring carotid plaque progression. Since delineation plaques required, a deep learning method can provide automatic segmentations TPA measurements; however, it requires large datasets manual annotations training with unknown performance on new datasets. A UNet++ ensemble algorithm was proposed to segment from 2D ultrasound images, trained three small (n = 33, 34 subjects) tested 44 subjects the...
Real-time needle segmentation and tracking is very important in image-guided surgery, biopsy, therapy. Due to its robustness the addition of extraneous noise, Hough Transform one most powerful line-detection techniques nowadays has been widely used different areas. Unfortunately, high computation needs often prevent it from being applied real-time applications without help specially designed hardware. In order solve this problem, a variety fast implementation algorithms have proposed....
Vessel-wall-volume (VWV) is an important three-dimensional ultrasound (3DUS) metric used in the assessment of carotid plaque burden and monitoring changes atherosclerosis response to medical treatment. To generate VWV measurement, we proposed approach that combined a voxel-based fully convolution network (Voxel-FCN) continuous max-flow module automatically segment media-adventitia (MAB) lumen-intima boundaries (LIB) from 3DUS images. Voxel-FCN includes encoder consisting general 3D CNN...
Track-Before-Detect (TBD) approaches have important applications such as the detection of small, dim targets in a long-range Infrared Detection and Tracking (IRDT) system. The movement model target limited by TBD is extended to that with constant acceleration this work. An algorithm based on linear variant-coefficient difference equation for moving indication proposed. Moreover, parametric models background, paper presents an analysis its optimal signal-to-noise ratio (SNR) gain versus...
Nanobubbles and microbubbles are non-invasive ultrasound imaging contrast agents that may potentially enhance diagnosis of tumors. However, to date, both nanobubbles display poor in vivo tumor-selectivity over non-targeted organs such as liver. We report here cyanine 5.5 conjugated (cy5.5-nanobubbles) a biocompatible chitosan–vitamin C lipid system dual ultrasound-fluorescence agent achieved tumor-selective mouse tumor model. Cy5.5-nanobubble suspension contained single bubble spheres...
Vascular segmentation plays an important role in medical image analysis. A novel technique for the automatic extraction of vascular trees from 2D images is presented, which combines Hessian-based multiscale filtering and a modified level set method. In proposed algorithm, morphological top-hat transformation firstly adopted to attenuate background. Then used enhance structures by combining Hessian matrix with Gaussian convolution tune response specific scales. Because tends blur vessel...