A5015541021- Image Processing Techniques and Applications
- Advanced Vision and Imaging
- Advanced Image Processing Techniques
- Image and Signal Denoising Methods
- Optical measurement and interference techniques
- Medical Image Segmentation Techniques
- Robotics and Sensor-Based Localization
- 3D Shape Modeling and Analysis
- Pelvic floor disorders treatments
- Medical Imaging and Analysis
- Remote Sensing and LiDAR Applications
- Brain Tumor Detection and Classification
- Advanced Image Fusion Techniques
- 3D Surveying and Cultural Heritage
- Acupuncture Treatment Research Studies
- Urinary Bladder and Prostate Research
- Image Processing and 3D Reconstruction
- Medical Imaging Techniques and Applications
- Cerebrovascular and Carotid Artery Diseases
- Advanced Numerical Analysis Techniques
- Image Enhancement Techniques
- Anorectal Disease Treatments and Outcomes
- Seismic Imaging and Inversion Techniques
- Sports injuries and prevention
- Remote-Sensing Image Classification
Huazhong University of Science and Technology
2015-2024
Chongqing Three Gorges University
2024
Yueyang Hospital
2018-2024
Shanghai University of Traditional Chinese Medicine
2018-2024
Shanghai University
2022
Hong Kong Polytechnic University
2011
Wuhan University
2006
It aimed to observe the effect of electro-acupuncture on improvement psychiatric symptoms, as well anxiety and depression in methamphetamine (MA) addicts during abstinence using randomized controlled trials.All patients present study received compulsory drug detoxification Shanghai Drug Rehabilitation Center. All were enrolled consecutively from June 2014 February 2015; data collection was completed March 2015. According randomized, single-blind control principle, 68 men MA randomly divided...
Abstract. DEM super resolution is proposed in our previous publication to improve the for a on basis of some learning examples. Meanwhile, nonlocal algorithm introduced deal with it and lots experiments show that strategy feasible. In publication, examples are defined as partial original their related high measurements due this way can avoid incompatibility between data be processed To further extent applications new strategy, should diverse easy obtain. Yet, may cause problem unrobustness....
The quality of ultrasound image is a key information in medical related application. It also an important index evaluating the performance ultrasonic imaging equipment and processing algorithms. Yet, there still no recognized quantitative standard about assessment (IQA) due to fact that IQA traditionally regarded as subjective issue, especially case images. As such, on basis convolutional neural network (CNN) quantitatively studied this paper. Firstly, dataset with 1063 images established...
BackgroundPelvic floor muscle training (PFMT) is a first-line conservative therapy for stress urinary incontinence (SUI). Electroacupuncture (EA) has been used to treat SUI recently.ObjectiveTo compare the effectiveness of PFMT + EA versus sham in women.Design, setting, and participantsA prospective, multicenter, randomized, controlled clinical trial was conducted at four hospitals China involving 304 women with from May 20, 2014 November 21, 2017. Data were analyzed April 20 December...
How to automatically detect intracranial aneurysms from Three-Dimension Time of Flight Magnetic Resonance Angiography (3D TOF MRA) images is a typical 3D image classification problem. Currently, the commonly used method Maximum Intensity Projection- (MIP-) based way. It transfers into 2D case by projecting patch planes along different directions on basis voxel’s intensity. After then, Convolutional Neural Network (CNN) established do classification. has been shown that MIP-based can reduce...
Abstract Aim To study the effect of pharmacological inhibition epidermal growth factor receptor (EGFR) on intracranial aneurysm (IA) initiation. Methods Human IA samples were analyzed for expression p‐EGFR and alpha smooth muscle actin (α‐SMA) by immunofluorescence (IF). Rat models established to evaluate ability EGFR inhibitor, erlotinib, attenuate incidence IA. We anterior cerebral artery tissues pathological proteomic detection relevant proteins, vessel casting was used aneurysms in each...
Optical coherence tomography (OCT) images are usually degraded by significant speckle noise, which will strongly hamper their quantitative analysis. However, noise reduction in OCT is particularly challenging because of the difficulty differentiating between and information components pattern. To address this problem, spiking cortical model (SCM)-based nonlocal means method presented. The proposed explores self-similarities based on rotation-invariant features image patches extracted SCM...
Speckle suppression plays an important role in improving ultrasound (US) image quality. While lots of algorithms have been proposed for 2D US denoising with remarkable filtering quality, there is relatively less work done on 3D speckle suppression, where the whole volume data rather than just one frame needs to be considered. Then, most crucial problem that computational complexity increases tremendously. The nonlocal means (NLM) provides effective method images. In this paper, a...
DEM super resolution is proposed in our previous publication to improve the for a on basis of some learning examples. Meanwhile, nonlocal algorithm introduced deal with it and lots experiments show that strategy feasible. In publication, examples are defined as partial original their related high measurements due this way can avoid incompatibility between data be processed To further extent applications new strategy, should diverse easy obtain. Yet, may cause problem unrobustness. overcome...
Background Insomnia is one of the most common symptoms among breast cancer patients, which can be present throughout all stages cancer. As a non-pharmacological alternative treatment, acupuncture has been suggested to improve sleep situations in patients with suffering from insomnia. However, there lack well-designed, high-quality clinical evidence regarding efficacy treatment cancer-related This study conducted evaluate and safety for Methods was designed as multicenter, randomized,...
Monocular depth estimation is a basic and critical task in computer vision that finds wide applications various domains, including robot navigation autonomous driving. A prevailing method nowadays leveraging hybrid datasets obtained from sensors to predict affine-invariant under supervised learning. However, the varying ranges can result an unstable network. While some loss functions have been introduced, existing methods may lead suboptimal geometric structures, such as blurred boundaries...
The vessel-wall-volume (VWV) measured based on three-dimensional (3D) carotid artery (CA) ultrasound (US) images can help to assess atherosclerosis and manage patients at risk for stroke. Manual involvement measurement work is subjective requires well-trained operators, fully automatic tools are not yet available. Thereby, we proposed a VWV framework (Auto-VWV) using CA prior-knowledge embedded U-Net (CAP-UNet) measure the from 3D US without manual intervention. Auto-VWV designed improve...
Fisheye lens can provide a wide view over 180°. It then has prominence advantages in three dimensional reconstruction and machine vision applications. However, the serious deformation image limits fisheye lens's usage. To overcome this obstacle, new rectification method named DDM (Digital Deformation Model) is developed based on two perspective transformation. type of digital grid representation each pixel CCD chip which built by interpolating difference between actual coordinate...
A method based on point cloud smoothing approaches for detecting noise and outliers is introduced. This firstly estimates thresholds according to points' shifts after smoothing, secondly identifies whose are more than the lastly removes them repeats whole process. The main difference from other methods that it tries screen out clouds rather makes points smoother by correcting their coordinates. precondition assure work will be shifted more, which requires operators possess ability of...
2D/3D registration that achieves high accuracy and real-time computation is one of the enabling technologies for radiotherapy image-guided surgeries. Recently, Convolutional Neural Network (CNN) has been explored to significantly improve efficiency registration. A pair intraoperative 2-D x-ray images synthetic data from pre-operative volume are often required model nonconvex mappings between parameters image residual. However, a large clinical dataset collection with accurate poses can be...
This paper intends to generate the approximate Voronoi diagram in geodesic metric for some unbiased samples selected from original points. The mesh model of seeds is then constructed on basis diagram. Rather than constructing all points, proposed strategy run around obstacle that distances among neighboring points are sensitive nearest neighbor definition. It obvious reconstructed level detail Hence, our main motivation deal with redundant scattered In implementation, Poisson disk sampling...