NeuroRefiner：面向3D荧光显微镜神经元分割的形态感知多智能体细化方法
NeuroRefiner: Morphology-Aware Multi-Agent Refinement for 3D Fluorescence Microscopy Neuron Segmentation
浏览论文内容
中文总结 AI 辅助
针对3D荧光显微镜神经元分割的拓扑与细节保留难题，本文提出NeuroRefiner多智能体系统结合TopoRefineNet工具，在多数据集上实现优于现有方法的分割性能，ZBFWB数据集F1分数提升3.02%。
中文摘要 AI 辅助
3D荧光显微镜中准确的神经元分割对神经科学至关重要，但神经元稀疏且细长的形态给现有分割方法带来了巨大挑战，这些方法难以同时保留局部细节与全局拓扑，导致分割结果碎片化。为解决该问题，本文提出NeuroRefiner，这是一种模拟人类专家迭代全局观察与局部编辑工作流程的多智能体系统，具体包含三个协作智能体，分别负责诊断拓扑错误、生成修正指令、验证细化质量。为实现智能体指令引导的分割细化，本文提出TopoRefineNet，一种基于3D U-Net的专用工具，利用跨模态特征融合生成细化掩码。通过多轮智能体推理与体素级编辑，NeuroRefiner可生成拓扑更准确、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优于现有最优方法，尤其在具有挑战性的ZBFWB数据集上F1分数提升了3.02%。
英文摘要
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.
发表机构
- Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）
- University of Chinese Academy of Sciences（中国科学院大学）
- Beijing Normal University（北京师范大学）
机构由 AI 辅助整理，请以论文原文为准。
