A5101646910- Retinal Imaging and Analysis
- Optical Coherence Tomography Applications
- EEG and Brain-Computer Interfaces
- Neural dynamics and brain function
- Glaucoma and retinal disorders
- Retinal Diseases and Treatments
- Blind Source Separation Techniques
- Retinal and Optic Conditions
- ECG Monitoring and Analysis
- Functional Brain Connectivity Studies
- stochastic dynamics and bifurcation
- Medical Image Segmentation Techniques
- Time Series Analysis and Forecasting
- Chaos control and synchronization
University of Jinan
2014-2022
Based on the nonlinear time series prediction，a feature extraction method for epileptic EEG signals using prediction is proposed to automatically detect from recordings. To reconstruct phase space，the approach of determining embedding dimension based predictability used determine signals. The experimental results show that extracted with could clearly distinguish normal EEG，and fit small set and stable noise.
Automated lesion segmentation is one of the important tasks for quantitative assessment retinal diseases in SD-OCT images. Recently, deep convolutional neural networks (CNN) have shown promising advancements field automated image segmentation, whereas they always benefit from large-scale datasets with high-quality pixel-wise annotations. Unfortunately, obtaining accurate annotations expensive both human effort and finance. In this paper, we propose a weakly supervised two-stage learning...
Abstract Obtaining accurate segmentation of central serous chorioretinopathy in spectral‐domain optical coherence tomography (SD‐OCT) is critical for the determination disease severity. Although existing methods achieve considerable results, they heavily depend on large‐scale data with high‐quality annotations. Also, lesions bear a large shape variation across different patients, which are often difficult to encode. To address above problems, we propose fine‐to‐coarse‐to‐fine weakly...
BACKGROUND: The nervous system senses and transmits information through the firing behavior of neurons, this process is affected by various noises.However, in previous study influence noise on nerve discharge, channel some effects not clear, difference from other noises was examined.OBJECTIVE: To construct ion which more biologically significant, to clarify basic characteristics random rhythm neurons generated different types acting channels.Method: Based dynamics channel, we constructed...
The study of epilepsy detection has great clinical significance. focus this is feature extraction method, which significant impacts on the performance detection. Recently, statistic properties complex network show ability to describe dynamics nonlinear time series. In paper, a method epileptic EEG, based statistical weighted network, proposed. EEG first constructed and vertex strength distribution converted studied. Then mean value defined extracted as classification feature. Experimental...