用多智能体模拟专家纠错，提升3D神经元分割的连通性与细节。
NeuroRefiner: Morphology-Aware Multi-Agent Refinement for 3D Fluorescence Microscopy Neuron Segmentation
- 设计三个协作智能体，分别诊断错误、生成修正指令、验证结果。
- 在ZBFWB数据集上F1分数提升3.02%，显著优于现有方法。
- 适合需要高精度神经元结构解析的脑科学与医学图像分析者。
在荧光显微镜下精确分割3D神经元对神经科学研究至关重要。然而，神经元稀疏且细长的形态给现有分割方法带来挑战，难以同时保持局部细节和全局拓扑结构，导致结果碎片化。为此，我们提出NeuroRefiner，一个模拟人类专家工作流程的多智能体系统，包含迭代的全局观察与局部编辑。该系统由三个协作智能体组成：负责诊断拓扑错误、生成修正指令、验证优化质量。为支持智能体指导的分割优化，我们提出TopoRefineNet，一种基于3D U-Net的专用工具，利用跨模态特征融合生成精细化掩码。通过多轮智能体推理与体素级编辑，NeuroRefiner生成拓扑更准确且可解释性更强的分割结果。在BigNeuron、CWMBS和ZBFWB数据集上的实验表明，NeuroRefiner优于当前最优方法，尤其在具有挑战性的ZBFWB数据集上，F1分数提升3.02%。
原文摘要 · Abstract (English)
Accurate 3D neuron segmentation in fluorescence microscopy is critical for neuroscience. However, the sparse and elongated morphology of neurons poses significant challenges to existing segmentation methods. These methods struggle to preserve both local details and global topology, leading to fragmented results. To address this, we propose NeuroRefiner, a multi-agent system that formalizes the human expert workflow involving iterative global observation and local editing. Specifically, NeuroRefiner comprises three collaborative agents dedicated to diagnosing topological errors, generating correction instructions, and validating refinement quality. To facilitate agent instruction-guided segmentation refinement, we propose TopoRefineNet, a dedicated 3D U-Net-based tool that leverages cross-modality feature fusion to generate refined masks. Through multi-round agent reasoning and voxel-level editing, NeuroRefiner produces topologically more accurate segmentations with enhanced interpretability. Experiments on the BigNeuron, CWMBS, and ZBFWB datasets demonstrate that NeuroRefiner outperforms state-of-the-art methods, notably achieving a 3.02% improvement in F1 score on the challenging ZBFWB dataset.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。