Xiayu Xu

Dr. Xiayu Xu

Key Laboratory of Biomedical Information Engineering of Ministry of Education, School of Life Science and Technology, Xi’an Jiaotong University, Xi’an 710000, China
orcid

Research Focus & Metrics

Academic Career Length

10Years (2017-Present)

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

Representative Publications

View All Publications
1 April 2017 in Computer Methods and Programs in Biomedicine
Verified
Journal Article
Closed access
Xiayu XuXiayu Xu
Xiayu Xu
WDWenxiang Ding
Wenxiang Ding
MAMichael D. Abràmoff
Michael D. Abràmoff
RCRuofan Cao
Ruofan Cao

11 January 2022 in IEEE Transactions on Medical Imaging
Verified
Journal Article
Closed access
GXGang Xing
Gang Xing
LCLi Chen
Li Chen
HWHualin Wang
Hualin Wang
JZJiong Zhang
Jiong Zhang
DSDongke Sun
Dongke Sun
Xiayu XuXiayu Xu
Xiayu Xu
The segmentation of pathological fluid lesions in optical coherence tomography (OCT), including intraretinal fluid, subretinal fluid, and pigment epithelial detachment, is of great importance for the diagnosis and treatment of various eye diseases such as neovascular age-related macular degeneration and diabetic macular edema. Although significant progress has been achieved with the rapid development of fully convolutional neural networks (FCN) in recent years, some important issues remain unsolved. First, pathological fluid lesions in OCT show large variations in location, size, and shape, imposing challenges on the design of FCN architecture. Second, fluid lesions should be continuous regions without holes inside. But the current architectures lack the capability to preserve the shape prior information. In this study, we introduce an FCN architecture for the simultaneous segmentation of three types of pathological fluid lesions in OCT. First, attention gate and spatial pyramid pooling modules are employed to improve the ability of the network to extract multi-scale objects. Then, we introduce a novel curvature regularization term in the loss function to incorporate shape prior information. The proposed method was extensively evaluated on public and clinical datasets with significantly improved performance compared with the state-of-the-art methods.

15 June 2018 in Biomedical Optics Express
Verified
Journal Article
Open access
PDF file
Xiayu XuXiayu Xu
Xiayu Xu
RWRendong Wang
Rendong Wang
PLPeilin Lv
Peilin Lv
BGBin Gao
Bin Gao
CLChan Li
Chan Li
FXFeng Xu
Feng Xu
The segmentation and classification of retinal arterioles and venules play an important role in the diagnosis of various eye diseases and systemic diseases. The major challenges include complicated vessel structure, inhomogeneous illumination, and large background variation across subjects. In this study, we employ a fully convolutional network to simultaneously segment arterioles and venules directly from the retinal image, rather than using a vessel segmentation-arteriovenous classification strategy as reported in most literature. To simultaneously segment retinal arterioles and venules, we configured the fully convolutional network to allow true color image as input and multiple labels as output. A domain-specific loss function was designed to improve the overall performance. The proposed method was assessed extensively on public data sets and compared with the state-of-the-art methods in literature. The sensitivity and specificity of overall vessel segmentation on DRIVE is 0.944 and 0.955 with a misclassification rate of 10.3% and 9.6% for arteriole and venule, respectively. The proposed method outperformed the state-of-the-art methods and avoided possible error-propagation as in the segmentation-classification strategy. The proposed method was further validated on a new database consisting of retinal images of different qualities and diseases. The proposed method holds great potential for the diagnostics and screening of various eye diseases and systemic diseases.

10 July 2022 in Medical Image Analysis
Verified
Journal Article
Closed access
HWHualin Wang
Hualin Wang
YZYuhong Zhou
Yuhong Zhou
JZJiong Zhang
Jiong Zhang
JLJianqin Lei
Jianqin Lei
DSDongke Sun
Dongke Sun
Xiayu XuXiayu Xu
Xiayu Xu

29 April 2019 in Current Eye Research
Verified
Journal Article
Closed access
CWChan Wen
Chan Wen
CPCheng Pei
Cheng Pei
Xiayu XuXiayu Xu
Xiayu Xu
JLJianqin Lei
Jianqin Lei
Purpose: To assess the effect of axial length (AL) on the quantification of superficial vessel density of both macular and disc region using swept source optical coherence tomography angiography (SSOCTA). Methods: This is a cross-sectional clinical study. Seventy-five eyes from 75 Chinese healthy participants (56 females) with a mean age of 26.6±6.8 (range 19-50) years were included in this study. All eyes were imaged with SSOCTA, using a 3×3mm scan pattern centered on the macular and optic disc respectively, and the superficial layer was used for evaluation. The image size was corrected with AL using Bennett formula. Outcome measurements included perfusion density (PD), vessel length density (VLD) in parafoveal and disc regions, averaged peripapillary large vessel diameter and area of foveal avascular zone (FAZ). Image processing and measurements was performed using Image J software. Multivariate regression analysis adjusting for age and signal strength was used to assess the influence of AL on the metrics. Results: AL was the only predictive factor for parafoveal PD (β=-0.273, P=0.047) and VLD (β=-0.396, P=0.003). While there was no correlation between AL and area of FAZ, large vessel diameter, or the vessel density on any location in disc region. Age was the only predictor for PD (β=-0.287, P=0.024) and VLD (β=-0289, P=0.023) on optic nerve head. Conclusions: AL was negatively correlated with superficial parafoveal microvasculature, but not correlated with peripapillary capillaries, suggesting that the inner retina stretches more in the distal end of the disc with increased AL.

13 October 2022 in IEEE Transactions on Medical Imaging
Verified
Journal Article
Closed access
Xiayu XuXiayu Xu
Xiayu Xu
PYPeiwei Yang
Peiwei Yang
HWHualin Wang
Hualin Wang
ZXZhanfeng Xiao
Zhanfeng Xiao
GXGang Xing
Gang Xing
JLJianqin Lei
Jianqin Lei
Automatic segmentation and differentiation of retinal arteriole and venule (AV), defined as small blood vessels directly before and after the capillary plexus, are of great importance for the diagnosis of various eye diseases and systemic diseases, such as diabetic retinopathy, hypertension, and cardiovascular diseases. Optical coherence tomography angiography (OCTA) is a recent imaging modality that provides capillary-level blood flow information. However, OCTA does not have the colorimetric and geometric differences between AV as the fundus photography does. Various methods have been proposed to differentiate AV in OCTA, which typically needs the guidance of other imaging modalities. In this study, we propose a cascaded neural network to automatically segment and differentiate AV solely based on OCTA. A convolutional neural network (CNN) module is first applied to generate an initial segmentation, followed by a graph neural network (GNN) to improve the connectivity of the initial segmentation. Various CNN and GNN architectures are employed and compared. The proposed method is evaluated on multi-center clinical datasets, including 3×3 mm 2 and 6×6 mm 2 OCTA. The proposed method holds the potential to enrich OCTA image information for the diagnosis of various diseases.