A5101411936- Photoacoustic and Ultrasonic Imaging
- Optical Imaging and Spectroscopy Techniques
- Retinal Imaging and Analysis
- Infrared Thermography in Medicine
- Radiomics and Machine Learning in Medical Imaging
- Medical Imaging and Analysis
- Thyroid Cancer Diagnosis and Treatment
- Brain Tumor Detection and Classification
- Medical Image Segmentation Techniques
- Advanced Image Fusion Techniques
- Retinal and Optic Conditions
- Muscle activation and electromyography studies
- Image and Signal Denoising Methods
- Lung Cancer Diagnosis and Treatment
- Acute Ischemic Stroke Management
- Human Pose and Action Recognition
- Grey System Theory Applications
- Fetal and Pediatric Neurological Disorders
- Intracerebral and Subarachnoid Hemorrhage Research
- Domain Adaptation and Few-Shot Learning
- Optical Coherence Tomography Applications
- Video Analysis and Summarization
- Human Motion and Animation
- Glaucoma and retinal disorders
- AI in cancer detection
Suzhou Research Institute
2022
First Affiliated Hospital of Wannan Medical College
2021
University of Liverpool
2020
The First People's Hospital of Shunde
2019
Southern Medical University
2019
North Minzu University
2019
Tianjin University
2013-2014
East China University of Science and Technology
2009
Stroke is an acute cerebral vascular disease that likely to cause long-term disabilities and death. Immediate emergency care with accurate diagnosis of computed tomographic (CT) images crucial for dealing a hemorrhagic stroke. However, due the high variability stroke's location, contrast, shape, it challenging time-consuming even experienced radiologists locate them. In this paper, we propose U-net based deep learning framework automatically detect segment hemorrhage strokes in CT brain...
This study aims to develop a computer-aided diagnosis (CADx) scheme classify between benign and malignant ground glass nodules (GGNs), fuse deep leaning radiomics imaging features improve the classification performance.We first retrospectively collected 513 surgery histopathology confirmed GGNs from two centers. Among these GGNs, 100 were 413 malignant. All tumors stage I lung adenocarcinoma. To segment we applied convolutional neural network residual architecture train build 3D U-Net. Then,...
Retinal vessel segmentation, which can obtain rich eye information, is an important indicator for examining ophthalmology and cardiovascular diseases. The existing method results in a decrease resolution due to continuous maximum pooling downsampling operations, causing the network lose detail on image when upsampling restoring feature map, ignoring small vessels or allow false positives at terminal branches. In order better solve these problems, this paper proposes combining dilated...
Laminar optical tomography (LOT) is a new mesoscopic functional imaging technique, which an extension of confocal microscope and diffuse to acquire both the coaxial off-axis scattered light at same time. In this paper, LOT system with larger detection area aiming in vivo early cervical cancer developed. The field view our 10 mm x mm. order improve image quality system, two methods were performed: correction distortion restriction returning light. performance aperture stop was assessed by...
Radiance is sensitive to the variations of tissue optical parameters, such as absorption coefficient <i>μ</i><sub>a</sub>, scattering <i>μ</i><sub>s</sub>, and anisotropy factor g. Therefore, similar fluence, radiance can be used for characterization. Compared with has advantage offering direction information light intensity. Taking advantage, parameters determined by rotating detector through 360 deg only a single optode pair. Instead translation mode in fluence-based technologies,...
In the non-invasive brain imaging with near-infrared light, precise head model is of great significance to forward and image reconstruction. To deal individual difference human tissues problem irregular curvature, in this paper, we extracted structure Mimics software from MRI a volunteer. This scheme makes it possible assign optical parameters every layer reasonably solve diffusion equation finite-element analysis. During solution inverse problem, semi-3D reconstruction algorithm adopted...
It is a difficult task to create realistic human animation because of the high complexity motion. To address this problem, new method presented for producing physically valid motion with example motions. The core our physics-based space-time optimization (PBSO). PBSO introduces physical constraints into conventional and then ensure reality edited intermediate model employed solve convergence process. original transformed simplified edited. Experiments shows captured data can be correctly...
Abstract Under current circumstances, the daily training of security team in nuclear power plant is carried out by company providing services according to requirements department, followed manual assessment and authorization among guards. There are several problems this process that can be improved: evaluation highly subjective, difficult quantify, standardize. Based on principles objectivity, unity, comprehensiveness extendibility, paper proposes an intelligent method for guard capability....