发表机构
A.I. Virtanen Institute for Molecular Sciences, University of Eastern Finland; Electron Microscopy Unit, Institute of Biotechnology, University of Helsinki（东芬兰大学A.I.维尔塔宁分子科学研究所; 赫尔辛基大学生物技术研究所电子显微镜部门）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本文提出一种无需人工提示的全自动三维树突实例分割流水线，整合YOLOv6引导SAM提示、掩膜细化、随机森林实例链接及nnU-Net高分辨率细化，在SBF-SEM数据上实现高语义精度（Dice 0.93/0.91），为棘级分析奠定基础。
AI 中文摘要
在连续块面扫描电子显微镜（SBF-SEM）中对单个树突进行准确的三维（3D）重建对于量化大脑中的结构可塑性至关重要，然而大规模手动标注是不可行的。我们提出了一种用于三维树突实例分割的全自动流水线，该流水线将YOLOv6引导的Segment Anything Model（SAM）在下采样切片上的提示、迭代二维掩膜细化、随机森林三维实例链接以及使用nnU-Net在原生分辨率下的实例感知高分辨率细化统一到一个系统中，在推理时无需手动提示。应用于来自一只对照大鼠和一只毛果芸香碱诱导的癫痫大鼠的海马CA1 SBF-SEM数据集，我们的流水线重建出连贯、分离良好的树突，具有较高的语义准确性（Dice 0.93和0.91）以及在对照组织上强大的实例级性能，而对更具挑战性的癫痫组织的分析表明，密集区域中的实例识别是主要剩余限制。高分辨率细化阶段恢复了细小的树突突起，为下游棘级分析提供了基础。代码可在以下网址获取：https://github.com/ZE-WEN/dendrite-3d-instance-seg。
英文摘要
Accurate three-dimensional (3D) reconstruction of individual dendrites in serial block-face scanning electron microscopy (SBF-SEM) is essential for quantifying structural plasticity in the brain, yet manual annotation at scale is infeasible. We present a fully automatic pipeline for 3D dendrite instance segmentation that unifies YOLOv6-guided Segment Anything Model (SAM) prompting on downsampled slices, iterative two-dimensional mask refinement, random forest 3D instance linking, and instance-aware high-resolution refinement using nnU-Net at native resolution into a single system requiring no manual prompting at inference. Applied to hippocampal CA1 SBF-SEM datasets from a control rat and a pilocarpine- induced epileptic rat, our pipeline reconstructs coherent, well- separated dendrites with high semantic accuracy (Dice 0.93 and 0.91) and strong instance-level performance on control tissue, while analysis of the more challenging epileptic tissue identifies instance recognition in dense regions as the principal remaining limitation. The high-resolution refinement stage recovers thin dendritic protrusions, providing a basis for downstream spine- level analysis. Code is available at https://github.com/ ZE-WEN/dendrite-3d-instance-seg.
CommentsAccepted at 2026 IEEE-EMBS Conference on Biomedical Engineering and Sciences (IECBES)
