{"ID":5937257,"CreatedAt":"2026-07-07T03:14:33.014478982Z","UpdatedAt":"2026-07-09T05:43:33.36049004Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2607.04696","arxiv_id":"2607.04696","title":"Probe-EM: Targeted Neuron Tracing via Training-Free Semantic Verification","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.","short_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, requiri...","url_abs":"https://arxiv.org/abs/2607.04696","url_pdf":"https://arxiv.org/pdf/2607.04696v1","authors":"[\"Liuyun Jiang\",\"Yanchao Zhang\",\"Jinyue Guo\",\"Chuanyue Chen\",\"Haiyang Yan\",\"Ye Yuan\",\"Jing Liu\",\"Hua Han\"]","published":"2026-07-06T05:56:26Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[]","has_code":false,"code_links":[{"ID":613969,"CreatedAt":"2026-07-07T03:14:33.014478982Z","UpdatedAt":"2026-07-07T03:14:33.014478982Z","DeletedAt":null,"paper_id":5937257,"paper_url":"https://arxiv.org/abs/2607.04696","paper_title":"Probe-EM: Targeted Neuron Tracing via Training-Free Semantic Verification","repo_url":"https://github.com/HeadLiuYun/Probe-EM","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}