{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/large-scale-electron-microscopy-image","title":"Large-Scale Electron Microscopy Image Segmentation in Spark","arxiv_id":"1604.00385","date":"2016-04-01","proceeding":null,"authors":["Stephen M. Plaza","Stuart E. Berg"],"abstract":"The emerging field of connectomics aims to unlock the mysteries of the brain\nby understanding the connectivity between neurons. To map this connectivity, we\nacquire thousands of electron microscopy (EM) images with nanometer-scale\nresolution. After aligning these images, the resulting dataset has the\npotential to reveal the shapes of neurons and the synaptic connections between\nthem. However, imaging the brain of even a tiny organism like the fruit fly\nyields terabytes of data. It can take years of manual effort to examine such\nimage volumes and trace their neuronal connections. One solution is to apply\nimage segmentation algorithms to help automate the tracing tasks. In this\npaper, we propose a novel strategy to apply such segmentation on very large\ndatasets that exceed the capacity of a single machine. Our solution is robust\nto potential segmentation errors which could otherwise severely compromise the\nquality of the overall segmentation, for example those due to poor classifier\ngeneralizability or anomalies in the image dataset. We implement our algorithms\nin a Spark application which minimizes disk I/O, and apply them to a few large\nEM datasets, revealing both their effectiveness and scalability. We hope this\nwork will encourage external contributions to EM segmentation by providing 1) a\nflexible plugin architecture that deploys easily on different cluster\nenvironments and 2) an in-memory representation of segmentation that could be\nconducive to new advances.","url_abs":"http://arxiv.org/abs/1604.00385v1","url_pdf":"http://arxiv.org/pdf/1604.00385v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"large-scale-electron-microscopy-image","repo_url":"https://github.com/janelia-flyem/DVIDSparkServices","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"electron-microscopy-image-segmentation","task_name":"Electron Microscopy Image Segmentation"},{"task_slug":"image-segmentation","task_name":"Image Segmentation"},{"task_slug":"segmentation","task_name":"Segmentation"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}