Enhanced pixel-wise style fusion network for stent malapposition recognition with re-parameterizing technique in OCT

doi:10.1007/s10462-025-11465-7

CSpace

	Enhanced pixel-wise style fusion network for stent malapposition recognition with re-parameterizing technique in OCT
	Zhang, Hua 1; Zhang, Chen 2,3; Li, Jing 1,2; Xuan, Xuexi 1; Wang, Mingjie 1; Yi, Bo 1; Xia, Kai 1; Wang, Haiyan 4; Yin, Lei 1,2; Zhang, Xiaoqing 1,2,5,6
	2025-12-12
发表期刊	ARTIFICIAL INTELLIGENCE REVIEW
ISSN	0269-2821
卷号	59 期号:2 页码:26
摘要	Percutaneous coronary intervention with stent implantation has become a widely used strategy to treat coronary artery disease. Stent malapposition (SM) may increase the risk of late stent thrombosis due to stent tissue coverage reduction, attracting much attention clinically. Recently, optical coherence tomography (OCT) images have been utilized to visually assess the stent apposition/malapposition. However, automated OCT-based SM recognition has been under-explored previously. Therefore, this paper proposes a novel enhanced pixel-wise style fusion network (EPSF-Net) to recognize SM automatically from OCT images. In the EPSF-Net, considering SM information is subtle, we design a novel enhanced pixel-wise style fusion (EPSF) block, which first applies the pixel-wise style pooling to aggregate pixel-wise style context, then enhances pixel-wise style context with multi-scale learning, and finally fuses enhanced pixel-wise style context via a pixel-wise fusion operator. Moreover, the re-parameterizing technique is utilized to reduce the parameters and computational cost of EPSF at the inference stage. Additionally, considering there is no publicly available OCT dataset for SM recognition, we construct an OCT image dataset of SM, named SM-OCT, to validate the effectiveness of our method, which will be available. The extensive experiments on the SM-OCT dataset show that our proposed EPSF-Net achieves better SM recognition performance than state-of-the-art methods. Additionally, two publicly available OCT datasets are employed to verify the generalization of our method.
关键词	Coronary artery disease Stent malapposition recognition OCT Enhanced pixel-wise style fusion network Re-parameterizing
DOI	10.1007/s10462-025-11465-7
收录类别	SCI
语种	英语
WOS研究方向	Computer Science
WOS类目	Computer Science, Artificial Intelligence
WOS记录号	WOS:001662361900001
出版者	SPRINGER
引用统计
文献类型	期刊论文
条目标识符	http://119.78.100.204/handle/2XEOYT63/42902
专题	中国科学院计算技术研究所
通讯作者	Li, Jing; Yin, Lei; Zhang, Xiaoqing
作者单位	1.7th Peoples Hosp Zhengzhou, Dept Cardiol, Zhengzhou, Peoples R China 2.Henan Acad Innovat Med Sci, Inst Biol Therapy, Zhengzhou, Peoples R China 3.Guangxi Med Univ, Life Sci Inst, Nanning, Peoples R China 4.Zhengzhou Univ Aeronaut, Simulat Expt Ctr, Zhengzhou, Peoples R China 5.Chinese Acad Sci, Shenzhen Inst Adv Technol, Ctr High Performance Comp, Shenzhen, Peoples R China 6.Chinese Acad Sci, Shenzhen Inst Adv Technol, Shenzhen Key Lab Intelligent Bioinformat, Shenzhen, Peoples R China
推荐引用方式 GB/T 7714	Zhang, Hua,Zhang, Chen,Li, Jing,et al. Enhanced pixel-wise style fusion network for stent malapposition recognition with re-parameterizing technique in OCT[J]. ARTIFICIAL INTELLIGENCE REVIEW,2025,59(2):26.
APA	Zhang, Hua.,Zhang, Chen.,Li, Jing.,Xuan, Xuexi.,Wang, Mingjie.,...&Zhang, Xiaoqing.(2025).Enhanced pixel-wise style fusion network for stent malapposition recognition with re-parameterizing technique in OCT.ARTIFICIAL INTELLIGENCE REVIEW,59(2),26.
MLA	Zhang, Hua,et al."Enhanced pixel-wise style fusion network for stent malapposition recognition with re-parameterizing technique in OCT".ARTIFICIAL INTELLIGENCE REVIEW 59.2(2025):26.