Wei Xiong

Wei Xiong

Auto-generated profile, based on publicly available information

Wei Xiong

Institute for Infocomm Research

Research Focus & Metrics

Academic Career Length

21Years (2006-Present)

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

Representative Publications

View All Publications
8 May 2023 in IEEE Journal of Biomedical and Health Informatics
Verified
Journal Article
Closed access
LQLiang Qiu
Liang Qiu
JCJierong Cheng
Jierong Cheng
HGHuxin Gao
Huxin Gao
WXWei Xiong
Wei Xiong
Hongliang RenHongliang Ren
Hongliang Ren
Distributed big data and digital healthcare technologies have great potential to promote medical services, but challenges arise when it comes to learning predictive model from diverse and complex e-health datasets. Federated Learning (FL), as a collaborative machine learning technique, aims to address the challenges by learning a joint predictive model across multi-site clients, especially for distributed medical institutions or hospitals. However, most existing FL methods assume that clients possess fully labeled data for training, which is often not the case in e-health datasets due to high labeling costs or expertise requirement. Therefore, this work proposes a novel and feasible approach to learn a Federated Semi-Supervised Learning (FSSL) model from distributed medical image domains, where a federated pseudo-labeling strategy for unlabeled clients is developed based on the embedded knowledge learned from labeled clients. This greatly mitigates the annotation deficiency at unlabeled clients and leads to a cost-effective and efficient medical image analysis tool. We demonstrated the effectiveness of our method by achieving significant improvements compared to the state-of-the-art in both fundus image and prostate MRI segmentation tasks, resulting in the highest Dice scores of 89.23 and 91.95 respectively even with only a few labeled clients participating in model training. This reveals the superiority of our method for practical deployment, ultimately facilitating the wider use of FL in healthcare and leading to better patient outcomes.

27 May 2019 in IEEE/ACM Transactions on Computational Biology and Bioinformatics
Verified
Journal Article
Closed access
TKTitinunt Kitrungrotsakul
Titinunt Kitrungrotsakul
XHXian-Hau Han
Xian-Hau Han
YIYutaro Iwamoto
Yutaro Iwamoto
STSatoko Takemoto
Satoko Takemoto
HYHideo Yokota
Hideo Yokota
YCYen-Wei Chen
Yen-Wei Chen
Mitosis detection is one of the challenging steps in biomedical imaging research, which can be used to observe the cell behavior. Most of the already existing methods that are applied in detecting mitosis usually contain many nonmitotic events (normal cell and background) in the result (false positives, FPs). In order to address such problem, in this study, we propose to apply 2.5-dimensional (2.5D) networks called CasDetNet_CLSTM, which can accurately detect mitotic events in 4D microscopic images. This CasDetNet_CLSTM involves a 2.5D faster region-based convolutional neural network (Faster R-CNN) as the first network, and a convolutional long short-term memory (CLSTM) network as the second network. The first network is used to select candidate cells using the information from nearby slices, whereas the second network uses temporal information to eliminate FPs and refine the result of the first network. Our experiment shows that the precision and recall of our networks yield better results than those of other state-of-the-art methods.

1 March 2010 in IEEE Transactions on Biomedical Engineering
Verified
Journal Article
Closed access
WXWei Xiong
Wei Xiong
SOSim-Heng Ong
Sim-Heng Ong
JLJoo-Hwee Lim
Joo-Hwee Lim
KFKelvin WC Foong
Kelvin WC Foong
JLJiang Liu
Jiang Liu
KTKevin S. W. Tan
Kevin S. W. Tan
Cell enumeration and diagnosis using peripheral blood smears are routine tasks in many biological and pathological examinations. Not every area in the smear is appropriate for such tasks due to severe cell clumping or sparsity. Manual working-area selection is slow, subjective, inconsistent, and statistically biased. Automatic working-area classification can reproducibly identify appropriate working smear areas. However, very little research has been reported in the literature. With the aim of providing a preprocessing step for further detailed cell enumeration and diagnosis for high-throughput screening (HTS), we propose an integrated algorithm for area classification and quantify both cell spreading and cell clumping in terms of individual clumps and the occurrence probabilities of the group of clumps over the image. Comprehensive comparisons are presented to compare the effect of these quantifications and their combinations. Our experiments using images of Giemsa-stained blood smears show that the method is efficient, accurate (above 88.9% hit rates for all areas in the validation set of 140 images), and robust (above 78.1% hit rates for a test set of 4878 images). This lays a good foundation for fast working-area selection in HTS.

9 May 2019 in Computing
Verified
Journal Article
Closed access
PDF file
JJJun Jiang
Jun Jiang
LZLiangcai Zeng
Liangcai Zeng
BCBin Chen
Bin Chen
YLYang Lu
Yang Lu
WXWei Xiong
Wei Xiong

22 September 2006
Verified
Conference Paper
Closed access
SWShiqian Wu
Shiqian Wu
WLWeisi Lin
Weisi Lin
LJLijun Jiang
Lijun Jiang
WXWei Xiong
Wei Xiong
LCLihao Chen
Lihao Chen
SOSim-Heng Ong
Sim-Heng Ong
This paper presents a new method for objective measurement of out-of-focus blur images. The essential idea is to derive the point spread function (PSF) of an out-of-focus blur image from the line spread function (LSF). In this method, it is assumed that at least one sharp edge could be detected. Then, the LSF can be constructed from the edge(s). This approach has fast speed as it works in spatial domain without complex Fourier transform or iterative computation. Moreover, a generic criterion for out-of-focus blur measurement is proposed and it can be applied to all images without depending on image contents. The experimental results validate the accuracy and efficiency of the proposed method

19 January 2012
Verified
Book Chapter
Closed access
PDF file
JZJiayin Zhou
Jiayin Zhou
WXWei Xiong
Wei Xiong
FDFeng Ding
Feng Ding
WHWeimin Huang
Weimin Huang
TQTian Qi
Tian Qi
SVSudhakar Venkatesh
Sudhakar Venkatesh