数据与计算发展前沿2026，Vol.8Issue(3)：1-14,14.DOI:10.11871/jfdc.issn.2096-742X.2026.03.001
基于迁移学习与Attention U-Net的同步辐射非人灵长类脑血管图像分割算法研究
Segmentation of Non-Human Primate Cerebrovascular Images from Synchrotron Radiation Micro-Tomography Using Transfer Learning and Attention U-Net
摘要
Abstract
[Objective]To address the challenges of scarce high-quality annotations and severe artifact interference in Syn-chrotron Radiation Micro-Tomography(SR-μCT)imaging of non-human primate cerebrovasculature,this study proposes an automated segmentation method based on transfer learning and a hierarchical combined weighting strategy.[Methods]A global percentile normalization strategy is employed to suppress artifacts while maintain-ing signal consistency.A"pre-training and fine-tuning"framework is established,innovatively incorporating a hi-erarchical combined weighting strategy to synergistically reinforce the capture of micro-vessels and boundary fea-tures.[Results]Experimental results demonstrate that the proposed method comprehensively outperforms nnU-Net 3D,achieving a Dice coefficient of 0.8686,a recall of 96.93%,and a topological connectivity metric(clDice)of 0.8848.These results signify a substantial resolution to the issues of micro-vessel miss-detection and discon-nection.[Conclusions]This algorithm effectively overcomes the segmentation challenges associated with small-sample and high-resolution SR-μCT cerebrovascular imaging,laying a solid technical and data foundation for fu-ture large-scale sub-micron whole-brain imaging analysis and neurovascular network quantification in non-hu-man primates and humans.关键词
脑血管分割/同步辐射显微断层成像/迁移学习/层级化复合加权/拓扑连通性Key words
cerebrovascular segmentation/synchrotron radiation micro-tomography/transfer learning/hierarchical combined weighting/topological connectivity引用本文复制引用
叶静,王春鹏,李沁桐,陈卓,李宗泽,张家如,张祥志,胡宇光,邰仁忠..基于迁移学习与Attention U-Net的同步辐射非人灵长类脑血管图像分割算法研究[J].数据与计算发展前沿,2026,8(3):1-14,14.基金项目
中国科学院上海高等研究院创新基金"同步辐射脑成像数据中血管与神经关联定位方法研究"(2024CP003) （2024CP003）
