A5021467649- Radiomics and Machine Learning in Medical Imaging
- MRI in cancer diagnosis
- AI in cancer detection
- Medical Image Segmentation Techniques
- Advanced MRI Techniques and Applications
- Brain Tumor Detection and Classification
- Medical Imaging Techniques and Applications
- Multimodal Machine Learning Applications
- Advanced Neural Network Applications
- EEG and Brain-Computer Interfaces
- Natural Language Processing Techniques
- Functional Brain Connectivity Studies
- Digital Imaging for Blood Diseases
- Domain Adaptation and Few-Shot Learning
- Smart Agriculture and AI
- Neural dynamics and brain function
- Mosquito-borne diseases and control
Shantou University
2023-2025
Shenzhen University
2021-2024
First Affiliated Hospital of Shantou University Medical College
2023
Shenzhen University Health Science Center
2021-2022
Abstract Background Semisupervised strategy has been utilized to alleviate issues from segmentation applications due challenges in collecting abundant annotated masks, which is an essential prerequisite for training high‐performance 3D convolutional neural networks (CNNs) . Purpose Existing semisupervised methods are mainly concerned with how generate the pseudo labels regularization but not evaluate quality of explicitly. To this problem, we offer a simple yet effective reciprocal learning...
<italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Goal</i> : The purpose of this work is to improve malaria diagnosis efficiency by integrating smartphones with microscopes. This integration involves image acquisition and algorithmic detection parasites in various thick blood smear (TBS) datasets sourced from different global regions, including low-quality images Sub-Saharan Africa. xmlns:xlink="http://www.w3.org/1999/xlink">Methods:</i>...
Breast cancer is the most common malignant tumor among women and second cause of cancer-related death. Early diagnosis in clinical practice crucial for timely treatment prognosis. Dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) has revealed great usability preoperative assessing therapy effects thanks to its capability reflect morphology dynamic characteristics breast lesions. However, existing computer-assisted algorithms only consider conventional radiomic features when...
The fragmentation of the functional brain network has been identified through connectivity (FC) analysis in studies investigating anesthesia-induced loss consciousness (LOC). However, it remains unclear whether mild sedation anesthesia can cause similar effects. This paper aims to explore changes local-global topology during anesthesia, better understand macroscopic neural mechanism underlying sedation. We analyzed high-density EEG from 20 participants undergoing and moderate propofol...
Aphasia, affecting one-third of stroke survivors, impairs language comprehension and speech production, leading to challenges in daily interactions, social isolation, economic losses. Assessing aphasia is crucial for effective rehabilitation recovery patients. However, the conventional behavioral-based evaluation, reliant on pathologists, susceptible individual variability, resulting high labor costs, time-consuming processes, low robustness. To address these limitations, this study...
Breast dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) plays an important role in the screening and prognosis assessment of high-risk breast cancer. The segmentation cancerous regions is essential useful for subsequent analysis MRI. To alleviate annotation effort to train networks, we propose a weakly-supervised strategy using extreme points as annotations cancer segmentation. Without any bells whistles, our focuses on fully exploiting learning capability routine training...