NEURD offers automated proofreading and feature extraction for connectomics

• 成果类型: Article
• 署名作者: Celii, Brendan; Papadopoulos, Stelios; Ding, Zhuokun; Fahey, Paul G.; Wang, Eric; Papadopoulos, Christos; Kunin, Alexander B.; Patel, Saumil; Bae, J. Alexander; Bodor, Agnes L.; Brittain, Derrick; Buchanan, Joann; Bumbarger, Daniel J.; Castro, Manuel A.; Cobos, Erick; Dorkenwald, Sven; Elabbady, Leila; Halageri, Akhilesh; Jia, Zhen; Jordan, Chris; Kapner, Dan; Kemnitz, Nico; Kinn, Sam; Lee, Kisuk; Li, Kai; Lu, Ran; Macrina, Thomas; Mahalingam, Gayathri; Mitchell, Eric; Mondal, Shanka Subhra; Mu, Shang; Nehoran, Barak; Popovych, Sergiy; Schneider-Mizell, Casey M.; Silversmith, William; Takeno, Marc; Torres, Russel; Turner, Nicholas L.; Wong, William; Wu, Jingpeng; Yu, Szi-chieh; Yin, Wenjing; Xenes, Daniel; Kitchell, Lindsey M.; Rivlin, Patricia K.; Rose, Victoria A.; Bishop, Caitlyn A.; Wester, Brock; Froudarakis, Emmanouil; Walker, Edgar Y.; Sinz, Fabian; Seung, H. Sebastian; Collman, Forrest; da Costa, Nuno Macarico; Reid, R. Clay; Pitkow, Xaq; Tolias, Andreas S.; Reimer, Jacob
• 署名单位: Baylor College of Medicine; Baylor College of Medicine; Rice University; Johns Hopkins University; Johns Hopkins University Applied Physics Laboratory; Stanford University; Stanford University; Stanford University; Stanford University; Creighton University; Princeton University; Princeton University; Allen Institute for Brain Science; Princeton University; Massachusetts Institute of Technology (MIT); Foundation for Research & Technology - Hellas (FORTH); University of Washington; University of Washington Seattle; University of Washington; University of Washington Seattle; Eberhard Karls University of Tubingen; University of Gottingen; University of Gottingen; Carnegie Mellon University; Carnegie Mellon University; Rice University; Stanford University; Stanford University
• 刊物名称: Nature
• ISSN/ISSBN: 0028-1613
• DOI: 10.1038/s41586-025-08660-5
• 发表日期: 2025-04-10
• 关键词: dendritic spines; visual-cortex; electron-microscopy; pyramidal neurons; cerebral-cortex; rat; reconstruction; anatomy; cells

摘要

We are in the era of millimetre-scale electron microscopy volumes collected at nanometre resolution1,2. Dense reconstruction of cellular compartments in these electron microscopy volumes has been enabled by recent advances in machine learning3, 4, 5-6. Automated segmentation methods produce exceptionally accurate reconstructions of cells, but post hoc proofreading is still required to generate large connectomes that are free of merge and split errors. The elaborate 3D meshes of neurons in these volumes contain detailed morphological information at multiple scales, from the diameter, shape and branching patterns of axons and dendrites, down to the fine-scale structure of dendritic spines. However, extracting these features can require substantial effort to piece together existing tools into custom workflows. Here, building on existing open source software for mesh manipulation, we present Neural Decomposition (NEURD), a software package that decomposes meshed neurons into compact and extensively annotated graph representations. With these feature-rich graphs, we automate a variety of tasks such as state-of-the-art automated proofreading of merge errors, cell classification, spine detection, axonal-dendritic proximities and other annotations. These features enable many downstream analyses of neural morphology and connectivity, making these massive and complex datasets more accessible to neuroscience researchers.