msemalign : a pipeline for serial section multibeam scanning electron microscopy volume alignment

• Published in: Frontiers in neuroscience 2023-12, Vol.17, p.1281098
• Main Authors: Watkins, Paul V, Jelli, Eric, Briggman, Kevin L
• Format: Article
• Language: English
• Subjects: alignment; Datasets; Micrography; multibeam; Neural networks; Neuroscience; Organelles; pipeline; Retina; Scanning electron microscopy; SEM; serial section electron microscopy; Silicon wafers
• ISSN: 1662-4548; 1662-453X; 1662-453X
• DOI: 10.3389/fnins.2023.1281098

Serial section multibeam scanning electron microscopy (ssmSEM) is currently among the fastest technologies available for acquiring 3D anatomical data spanning relatively large neural tissue volumes, on the order of 1 mm or larger, at a resolution sufficient to resolve the fine detail of neuronal morphologies and synapses. These petabyte-scale volumes can be analyzed to create connectomes, datasets that contain detailed anatomical information including synaptic connectivity, neuronal morphologies and distributions of cellular organelles. The mSEM acquisition process creates hundreds of millions of individual image tiles for a single cubic-millimeter-sized dataset and these tiles must be aligned to create 3D volumes. Here we introduce , an alignment pipeline that strives for scalability and design simplicity. The pipeline can align petabyte-scale datasets such that they contain smooth transitions as the dataset is navigated in all directions, but critically that does so in a fashion that minimizes the overall magnitude of section distortions relative to the originally acquired micrographs.