Yiqi Zhang

Yiqi Zhang

Auto-generated profile, based on publicly available information

Yiqi Zhang

Department of Electronic and Electrical Engineering, Southern University of Science and Technology, Shenzhen, China

Research Focus & Metrics

Academic Career Length

6Years (2021-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
21 July 2022 in IEEE Transactions on Medical Imaging
Verified
Journal Article
Closed access
JLJunyan Lyu
Junyan Lyu
YZYiqi Zhang
Yiqi Zhang
YHYijin Huang
Yijin Huang
LLLi Lin
Li Lin
PCPujin Cheng
Pujin Cheng
XTXiaoying TANG
Xiaoying TANG
Convolutional neural networks have been widely applied to medical image segmentation and have achieved considerable performance. However, the performance may be significantly affected by the domain gap between training data (source domain) and testing data (target domain). To address this issue, we propose a data manipulation based domain generalization method, called Automated Augmentation for Domain Generalization (AADG). Our AADG framework can effectively sample data augmentation policies that generate novel domains and diversify the training set from an appropriate search space. Specifically, we introduce a novel proxy task maximizing the diversity among multiple augmented novel domains as measured by the Sinkhorn distance in a unit sphere space, making automated augmentation tractable. Adversarial training and deep reinforcement learning are employed to efficiently search the objectives. Quantitative and qualitative experiments on 11 publicly-accessible fundus image datasets (four for retinal vessel segmentation, four for optic disc and cup (OD/OC) segmentation and three for retinal lesion segmentation) are comprehensively performed. Two OCTA datasets for retinal vasculature segmentation are further involved to validate cross-modality generalization. Our proposed AADG exhibits state-of-the-art generalization performance and outperforms existing approaches by considerable margins on retinal vessel, OD/OC and lesion segmentation tasks. The learned policies are empirically validated to be model-agnostic and can transfer well to other models. The source code is available at https://github.com/CRazorback/AADG.

13 December 2021 in Frontiers in Neuroscience
Verified
Journal Article
Open access
YZYiqi Zhang
Yiqi Zhang
ZZZhenyu Zhang
Zhenyu Zhang
LLLei Luo
Lei Luo
HTHuaiyu Tong
Huaiyu Tong
FCFei Chen
Fei Chen
SHSheng Tao Hou
Sheng Tao Hou
Previous studies showed that entrainment of light flicker at low gamma frequencies provided neuroprotection in mouse models of Alzheimer’s disease (AD) and stroke. The current study was set to explore the feasibility of using 40 Hz light flicker for human brain stimulation for future development as a tool for brain disease treatment. The effect of 40 Hz low gamma frequency light on a cohort of healthy human brains was examined using 64 channel electroencephalography (EEG), followed by microstate analyses. A random frequency light flicker was used as a negative control treatment. Light flicker at 40 Hz significantly increased the corresponding band power in the O1, Oz, and O3 electrodes covering the occipital areas of both sides of the brain, indicating potent entrainment with 40 Hz light flicker in the visual cortex area. Importantly, the 40 Hz light flicker significantly altered microstate coverage, transition duration, and the Lempel-Ziv complexity (LZC) compared to the rest state. Microstate metrics are known to change in the brains of Alzheimer’s disease, schizophrenia, and stroke patients. The current study laid the foundation for the future development of 40 Hz light flicker as therapeutics for brain diseases.