Probe-EM: Targeted Neuron Tracing via Training-Free Semantic Verification
2026-07-06 • Computer Vision and Pattern Recognition
Computer Vision and Pattern Recognition
AI summaryⓘ
The authors developed a new way to trace neurons in huge brain images without needing lots of training data. Their method uses a smart search guided by neuron shapes and checks its work using a model called NeuroSAM 2. This approach helps fix common errors in automatic neuron maps and works with an interactive tool for people to easily proofread results. Tests showed their method is better than previous ones and cuts proofreading time by about one-third.
neuron tracingelectron microscopyautomated segmentationzero-shot learningskeleton-guided searchNeuroSAMmanual proofreadingNeuroglancermorphology reconstruction
Authors
Liuyun Jiang, Yanchao Zhang, Jinyue Guo, Chuanyue Chen, Haiyang Yan, Ye Yuan, Jing Liu, Hua Han
Abstract
Establishing large-scale, high-resolution neural connectivity maps is fundamental to elucidating the structural basis of brain function. However, when processing terabyte- or petabyte-scale electron microscopy data, over-segmentation inherent in automated reconstruction algorithms remains a critical bottleneck, requiring extensive manual proofreading spanning person-years. To alleviate the heavy reliance on annotated data and the limited flexibility of conventional tracing methods, we propose a training-free, targeted neuron tracing framework. Specifically, we introduce a skeleton-guided Heuristic Spatial Search paradigm that leverages geometric priors to iteratively reconstruct neuronal morphologies through a probing-verification cycle. To achieve robust zero-shot semantic verification, we further develop a Dimension-Aware Semantic Verification strategy built upon the foundation model NeuroSAM 2. This strategy resolves intra-slice splits via Planar Ensemble Consensus and inter-slice splits via Axial Spatio-Temporal Propagation. Notably, we integrate the proposed workflow into the Neuroglancer visualization platform, enabling an interactive human-in-the-loop proofreading system. Experimental results demonstrate that the proposed method outperforms supervised baselines and reduces manual proofreading time by 33.4%. The source code is publicly available at https://github.com/HeadLiuYun/Probe-EM.