Problem
Research questions and friction points this paper is trying to address.
3D dendrite instance segmentation
SBF-SEM
structural plasticity
manual annotation
A Fully Automatic Pipeline for 3D Dendrite Instance Segmentation in SBF-SEM
🤖 AI Summary
This study addresses the reliance on manual annotation and limited scalability in SBF-SEM dendritic 3D reconstruction by proposing a fully automated segmentation pipeline. Methodologically, it unifies multi-stage models into a single integrated system that combines YOLOv6-guided SAM prompting, iterative mask refinement, random forest-based instance linking, and nnU-Net high-resolution optimization. By innovatively coupling low-resolution guidance with native high-resolution refinement, the framework completely eliminates human intervention during inference. Experimental results demonstrate that the proposed method achieves a Dice coefficient of 0.93 on the control group dataset, effectively recovering fine protrusions and significantly enhancing semantic accuracy. These advances establish a robust foundation for spine-level fine-grained morphological analysis.
📝 Abstract
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.
Innovation
Methods, ideas, or system contributions that make the work stand out.
3D instance segmentation
Segment Anything Model (SAM)
SBF-SEM
fully automatic pipeline
high-resolution refinement
🔎 Similar Papers
