Xiong Huangrui, Zheng Siling, Qi Xiuhong, Liu Ji
School of Information Science and Technology, MoE Key Laboratory of Brain-inspired Intelligent Perception and Cognition, CAS Key Laboratory of Brain Function and Disease, University of Science and Technology of China, Hefei, China; Center for Advanced Interdisciplinary Science and Biomedicine of IHM, Division of Life Sciences and Medicine, University of Science and Technology of China, Hefei, China.
School of Information Science and Technology, MoE Key Laboratory of Brain-inspired Intelligent Perception and Cognition, CAS Key Laboratory of Brain Function and Disease, University of Science and Technology of China, Hefei, China.
J Neurosci Methods. 2025 Jul;419:110446. doi: 10.1016/j.jneumeth.2025.110446. Epub 2025 Apr 10.
Microglia are important immune cells in the central nervous system, playing a key role in various pathological processes. The morphological diversity of microglia is closely linked to the development of brain diseases, yet accurate segmentation and automatic classification of microglia remain challenging.
We proposed a workflow, μGlia-Flow, which integrates both segmentation and classification for microglia analysis. The Frangi filtering algorithm was employed for branch segmentation, and an edge-guided attention TransUNet (EGA-Net) was used for soma segmentation. A Vision Transformer (ViT) network was applied to classify different morphologies.
The Frangi filtering algorithm produces more complete branches with smoother edges and clearer structures. The EGA-Net improves Dice and IoU scores by 4.02 % and 6.75 %, respectively. ViT achieves over 99 % precision in classification. Post-processing reveals decreasing complexity during activation, validating the accuracy of μGlia-Flow.
μGlia-Flow introduces deep learning, significantly improving segmentation accuracy and addressing the parameter dependency of existing classification methods.
we present an automatic workflow for segmenting and classifying microglia, providing a powerful tool for different morphology analysis.
小胶质细胞是中枢神经系统中的重要免疫细胞，在各种病理过程中起关键作用。小胶质细胞的形态多样性与脑部疾病的发展密切相关，但小胶质细胞的精确分割和自动分类仍然具有挑战性。
我们提出了一种工作流程μGlia-Flow，它集成了用于小胶质细胞分析的分割和分类。采用Frangi滤波算法进行分支分割，并使用边缘引导注意力TransUNet（EGA-Net）进行胞体分割。应用视觉Transformer（ViT）网络对不同形态进行分类。
Frangi滤波算法产生的分支更完整，边缘更平滑，结构更清晰。EGA-Net分别将Dice和IoU分数提高了4.02%和6.75%。ViT在分类中实现了超过99%的精度。后处理显示激活过程中的复杂性降低，验证了μGlia-Flow的准确性。
μGlia-Flow引入了深度学习，显著提高了分割精度，并解决了现有分类方法的参数依赖性。
我们提出了一种用于小胶质细胞分割和分类的自动工作流程，为不同形态分析提供了一个强大的工具。
