A5061461560- Functional Brain Connectivity Studies
- Advanced Neuroimaging Techniques and Applications
- Medical Image Segmentation Techniques
- Advanced MRI Techniques and Applications
- Scoliosis diagnosis and treatment
- Acute Ischemic Stroke Management
- Medical Imaging and Analysis
- Cerebrovascular and Carotid Artery Diseases
- Medical Imaging Techniques and Applications
- Face and Expression Recognition
- AI in cancer detection
- Neural Networks and Applications
- Dementia and Cognitive Impairment Research
- Coronary Interventions and Diagnostics
- Spinal Fractures and Fixation Techniques
- Cardiovascular Health and Disease Prevention
- Machine Learning and ELM
- Spine and Intervertebral Disc Pathology
- Image Retrieval and Classification Techniques
- EEG and Brain-Computer Interfaces
- Advanced Neural Network Applications
- Brain Tumor Detection and Classification
- MRI in cancer diagnosis
- Sparse and Compressive Sensing Techniques
- Photoacoustic and Ultrasonic Imaging
Animal Science Research Institute
2025
Beihang University
2018-2025
Guizhou Academy of Agricultural Sciences
2022-2024
Hebei University of Engineering
2011-2024
Bayer (Germany)
2024
Weifang University
2023
Chinese University of Hong Kong
2013-2022
Baoding People's Hospital
2022
Anyang Normal University
2021
Southeast University
2021
Cerebral microbleeds (CMBs) are small haemorrhages nearby blood vessels. They have been recognized as important diagnostic biomarkers for many cerebrovascular diseases and cognitive dysfunctions. In current clinical routine, CMBs manually labelled by radiologists but this procedure is laborious, time-consuming, error prone. paper, we propose a novel automatic method to detect from magnetic resonance (MR) images exploiting the 3D convolutional neural network (CNN). Compared with previous...
Acute ischemic stroke is recognized as a common cerebral vascular disease in aging people. Accurate diagnosis and timely treatment can effectively improve the blood supply of area reduce risk disability or even death. Understanding location size infarcts plays critical role decision. However, manual localization quantification lesions are laborious time-consuming. In this paper, we propose novel automatic method to segment acute from diffusion weighted images (DWIs) using deep 3-D...
Distal radius fracture is common in the general population. Fracture management includes a plaster cast, splint and synthetic material cast to immobilise injured arm. Casting complications are those conventional casting technologies. 3D printing technology rapidly increasing application rehabilitation. However, there no clinical study investigating of 3D–printed orthopaedic for treatment bone fractures. We have developed patient-specific fabricated by printing. This pioneering aims use casts...
Two point four out of 100 people suffer from one or more fractures in the course average lifetimes. Traditional casts are featured as cumbersome structures that result high risk cutaneous complications. Clinical demands for developing a hygienic cast have gotten and attention. 3D printing technique is rapidly growing fabrication custom-made rehabilitation tools. The objective this study to develop rapid intelligent modeling patient-specific orthopedic produced by technologies. A model...
The generalization error bounds found by current models using the number of effective parameters a classifier and training samples are usually very loose. These intended for entire input space. However, support vector machine (SVM), radial basis function neural network (RBFNN), multilayer perceptron (MLPNN) local learning machines solving problems treat unseen near to be more important. In this paper, we propose localized model which from above within neighborhood stochastic sensitivity...
Intensity normalization is an important preprocessing step in brain magnetic resonance image (MRI) analysis. During MR acquisition, different scanners or parameters would be used for scanning subjects the same subject at a time, which may result large intensity variations. This variation will greatly undermine performance of subsequent MRI processing and population analysis, such as registration, segmentation, tissue volume measurement. In this work, we proposed new histogram method to...
Individuals diagnosed with mild cognitive impairment (MCI) are at high risk of transition to Alzheimer's disease (AD). However, little is known about functional characteristics the conversion from MCI AD. Resting-state magnetic resonance imaging was performed in 25 AD patients, 31 and 42 well-matched normal controls baseline. Twenty-one patients converted approximately 24 months follow-up. Functional connectivity strength (FCS) seed-based analyses were used assess differences among groups....
Newtonian fluid model has been commonly applied in simulating cerebral blood flow intracranial atherosclerotic stenosis (ICAS) cases using computational dynamics (CFD) modeling, while is a shear-thinning non-Newtonian fluid. We aimed to investigate the differences of hemodynamic metrics quantified CFD models built with and assumptions, patients ICAS.We virtual artery an eccentric 75% performed static simulation. also constructed three ICAS different severities luminal stenosis. simulations...
Background and Purpose— We explored the association between pulsatility index (PI) as derived from transcranial Doppler ultrasound with various measures of small vessel disease in community. Methods— performed magnetic resonance imaging 205 consecutive community-dwelling elderly subjects who were participants Shanghai Aging Study. investigated middle cerebral artery (MCA) PI white matter lesions (WML), lacunes, microbleeds. Results— Multiple logistic regression found that MCA was associated...
Despite the known morphological differences (e.g., brain shape and size) in brains of populations different origins age race), Chinese atlas is less studied. In current study, we developed a statistical based on multi-center high quality magnetic resonance imaging (MRI) dataset 2020 adults (18-76 years old). We constructed 12 from 20 year to 75 at 5 interval. New standard space, coordinates, area labels were further defined. The new was validated registration segmentation. It found that, as...
Objective To compare the bone healing effects of denosumab and alendronate in female rheumatoid arthritis (RA) patients by high‐resolution peripheral quantitative computed tomography. Methods This is a post hoc analysis randomized controlled trial. Forty were 1:1 ratio to receive either subcutaneous (60 mg) once or oral (70 weekly for 6 months. The size individual erosions presence extent erosion‐associated sclerosis (marginal osteosclerosis) measured second metacarpal head nondominant hand...
Niacin reduces plasma triglycerides, but it may increase free fatty acids and insulin resistance during long-term treatment. We examined the effect of extended-release niacin on liver fat content in Chinese patients with dyslipidemia whether common diacylglycerol acyltransferase-2 (DGAT2) polymorphisms influenced this effect. The 39 (baseline content: 12.8 ± 7.6%, triglycerides: 3.30 1.67 mmol/l) were treated niacin, gradually increasing dose to 2 g/day for a total 23 weeks....
Medical imaging currently plays a crucial role throughout the entire clinical applications from medical scientific research to diagnostics and treatment planning. However, procedures are often computationally demanding due large three-dimensional (3D) datasets process in practical applications. With rapidly enhancing performances of graphics processors, improved programming support, excellent price-to-performance ratio, processing unit (GPU) has emerged as competitive parallel computing...
Liver segmentation is an essential procedure in computer-assisted surgery, radiotherapy, and volume measurement. It still a challenging task to extract liver tissue from 3D CT images owing nearby organs with similar intensities. In this paper, automatic approach integrating multi-dimensional features into graph cut refinement developed validated. Multi-atlas utilized estimate the coarse shape of on target image. The unsigned distance field based initial then calculated throughout whole...
This pilot study is aimed at investigating the mechanical characteristics of a cast-wrapped fractured forearm and performing clinical comparative our own developed 3D-printed orthopedic cast.An integrated finite element (FE) model including cast wrapping was created. The distal radial ulna in this cut through to mimic bone fracture. A 400 N force 1 Nm rotation moment, which were much larger than loading conditions encountered daily life for human being, applied on palm. We conducted by using...
Introduction The primary objective of the current study was to evaluate effects Flammulina velutipes mushroom residue (FVMR) in a fermented total mixed ration (FTMR) diet on fattening effect and rumen microorganisms Guizhou black male goats. Methods A 22 goats were allocated into two groups using Randomized Complete Block Design (RCBD) experimental design. average initial weight 22.41 ± 0.90 kg with 11 each group. control group (group I) fed traditional fermentation without FVMR. Group II...
The support vector machine (SVM) has been demonstrated to be a very effective classifier in many applications, but its performance is still limited as the data distribution information underutilized determining decision hyperplane. Most of existing kernels employed nonlinear SVMs measure similarity between pair pattern images based on Euclidean inner product or distance corresponding input patterns, which ignores tendency and makes SVM essentially "local" classifier. In this paper, we...
The one-class classification problem aims to distinguish a target class from outliers. spherical classifier (SOCC) solves this by finding hypersphere with minimum volume that contains the data while keeping outlier samples outside. SOCC achieves satisfactory performance only when have same distribution tendency in all orientations. Therefore, of is limited way many superfluous outliers might be mistakenly enclosed. authors propose exploit structures obtained via unsupervised methods such as...