High-performance laser speckle contrast image vascular segmentation without delicate pseudo-label reliance  

作　　者：Shenglan Yao Huiling Wu Suzhong Fu Shuting Ling Kun Wang Hongqin Yang Yaqin He Xiaolan Ma Xiaofeng Ye Xiaofei Wen Qingliang Zhao 

机构地区：[1]State Key Laboratory of Vaccines for Infectious Diseases,Xiang An Biomedicine Laboratory,Department of Vascular&Tumor Interventional Radiology,The First A±liated Hospital of Xiamen University,School of Medicine,School of Public Health,Xiamen University,Xiamen 361102,P.R.China [2]The Key Laboratory of Optoelectronic Science and Technology for Medicine of Ministry of Education,Fujian Normal University,Fuzhou 350117,P.R.China [3]Department of Oncology Surgery,General Hospital of Ningxia Medical University,Yinchuan 750004,P.R.China

出　　处：《Journal of Innovative Optical Health Sciences》2025年第1期117-133,共17页创新光学健康科学杂志(英文)

基　　金：supported by grants fromthe State Key Laboratory of Vaccines for Infectious Diseases,Xiang An Biomedicine Laboratory(2023XAKJ0101031);National Natural Science Foundation of China(81971665);Natural Science Foundation of Fujian Province(2021J011366);Medical and Health Guidance Project of Xiamen(3502Z20214ZD1016);Xiamen Health High-Level Talent Training Program,Ningxia Hui Autonomous Region Key Research and Development Program(2022BEG03127);Fundamental Research Funds for the Central Universities of China(20720210117);Fujian Province Science and Technology Plan Guiding Project(2022Y0002);National Natural Science Foundation of China(62005048);Natural Science Foundation of Fujian Province(2020J01158);Ministry of Education Industry-university Cooperative Education Project(220606053295218);XMU Undergraduate Innovation and Entrepreneurship Training Programs(2023X805,2023X808,2023Y1109).

摘　　要：Laser speckle contrast imaging(LSCI)is a noninvasive,label-free technique that allows real-time investigation of the microcirculation situation of biological tissue.High-quality microvascular segmentation is critical for analyzing and evaluating vascular morphology and blood flow dynamics.However,achieving high-quality vessel segmentation has always been a challenge due to the cost and complexity of label data acquisition and the irregular vascular morphology.In addition,supervised learning methods heavily rely on high-quality labels for accurate segmentation results,which often necessitate extensive labeling efforts.Here,we propose a novel approach LSWDP for high-performance real-time vessel segmentation that utilizes low-quality pseudo-labels for nonmatched training without relying on a substantial number of intricate labels and image pairing.Furthermore,we demonstrate that our method is more robust and effective in mitigating performance degradation than traditional segmentation approaches on diverse style data sets,even when confronted with unfamiliar data.Importantly,the dice similarity coefficient exceeded 85%in a rat experiment.Our study has the potential to efficiently segment and evaluate blood vessels in both normal and disease situations.This would greatly benefit future research in life and medicine.

关 键 词：Biomedical imaging laser speckle contrast imaging vessel segmentation weakly supervised learning MICROCIRCULATION 

分 类 号：TN24[电子电信—物理电子学] TP391.41[自动化与计算机技术—计算机应用技术]