A5101952356- Functional Brain Connectivity Studies
- Dementia and Cognitive Impairment Research
- Brain Tumor Detection and Classification
- EEG and Brain-Computer Interfaces
- Machine Learning in Healthcare
- Viral gastroenteritis research and epidemiology
- Advanced Neuroimaging Techniques and Applications
- Medical Image Segmentation Techniques
- Domain Adaptation and Few-Shot Learning
- Neural dynamics and brain function
- AI in cancer detection
- Respiratory viral infections research
- Advanced Neural Network Applications
- SARS-CoV-2 and COVID-19 Research
- COVID-19 diagnosis using AI
- Retinoids in leukemia and cellular processes
- Advanced Text Analysis Techniques
- Antioxidant Activity and Oxidative Stress
- Mental Health Research Topics
- Viral Infections and Immunology Research
- Alzheimer's disease research and treatments
- Traditional Chinese Medicine Studies
- Photodynamic Therapy Research Studies
- SARS-CoV-2 detection and testing
- Advanced Vision and Imaging
Shenzhen University Health Science Center
2018-2025
Shenzhen University
2017-2024
Beijing Center for Disease Prevention and Control
2012-2024
Southeast University
2015-2024
Yunnan University
2023
Software (Spain)
2023
Shenzhen Technology University
2023
Chengdu University of Traditional Chinese Medicine
2022
The People's Hospital of Guangxi Zhuang Autonomous Region
2020-2021
Tianjin University of Commerce
2020
Alzheimer's disease (AD) is an irreversible progressive neurodegenerative disorder. Mild cognitive impairment (MCI) the prodromal state of AD, which further classified into a (i.e., pMCI) and stable sMCI). With development deep learning, convolutional neural networks (CNNs) have made great progress in image recognition using magnetic resonance imaging (MRI) positron emission tomography (PET) for AD diagnosis. However, due to limited availability these data, it still challenging effectively...
In 2023, through an ongoing respiratory pathogen surveillance system, we observed from mid-September onwards, increase of illness among children aged ≤ 15 years presenting at hospital outpatient clinics in Beijing, China. Data indicated that was caused by multiple pathogens, predominantly
Accurate identification and understanding informative feature is important for early Alzheimer's disease (AD) prognosis diagnosis. In this paper, we propose a novel discriminative sparse learning method with relational regularization to jointly predict the clinical score classify AD stages using multimodal features. Specifically, apply technique expand class-specific difference include geometric information effective selection. addition, two kind of are incorporated explore intrinsic...
The demand for economical and efficient data processing has led to a surge of interest in neuromorphic computing based on emerging two-dimensional (2D) materials recent years. As rising van der Waals (vdW) p-type Weyl semiconductor with many intriguing properties, tellurium (Te) been widely used advanced electronics/optoelectronics. However, its application floating gate (FG) memory devices information never explored. Herein, an electronic/optoelectronic FG device enabled by Te-based 2D vdW...
In this paper, our goal is to design a simple learning paradigm for long-tail visual recognition, which not only improves the robustness of feature extractor but also alleviates bias classifier towards head classes while reducing training skills and overhead. We propose an efficient one-stage strategy long-tailed recognition called Global Local Mixture Consistency cumulative (GLMC). Our core ideas are twofold: (1) global local mixture consistency loss extractor. Specifically, we generate two...
Multimodal neuroimaging provides complementary information critical for accurate early diagnosis of Alzheimer's disease (AD). However, the inherent variability between multimodal neuroimages hinders effective fusion features. Moreover, achieving reliable and interpretable diagnoses in field remains challenging. To address them, we propose a novel network based on multi-fusion disease-induced learning (MDL-Net) to enhance AD by efficiently fusing data. Specifically, MDL-Net proposes joint...
Alzheimer's disease (AD) is a neurodegenerative with an irreversible and progressive process. To understand the brain functions identify biomarkers of AD early stages [also known as, mild cognitive impairment (MCI)], it crucial to build functional connectivity network (BFCN) using resting-state magnetic resonance imaging (rs-fMRI). Existing methods have been mainly developed only single time-point rs-fMRI data for classification. In fact, multiple more effective than in diagnosing diseases...
In multi-site studies of Alzheimer's disease (AD), the difference data in datasets leads to degraded performance models target sites. The traditional domain adaptation method requires sharing from both source and domains, which will lead privacy issue. To solve it, federated learning is adopted as it can allow be trained with a privacy-protected manner. this paper, we propose framework via Transformer (FedDAvT), not only protects privacy, but also eliminates heterogeneity. network used...
Automatic and accurate classification of retinal optical coherence tomography (OCT) images is essential to assist physicians in diagnosing grading pathological changes pathologic myopia (PM). Clinically, due the obvious differences position, shape, size lesion structure different scanning directions, ophthalmologists usually need combine OCT horizontal vertical directions diagnose type PM. To address these challenges, we propose a novel feature interaction Transformer network (FIT-Net) PM...