SLASH: SCALABLE LARGE ANALYTIC SEGMENTATION HYBRID

SLASH：可扩展的大型分析细分混合体

基本信息

批准号：
8163481
负责人：
Mark H Ellisman
金额：
$ 45.92万
依托单位：
UNIVERSITY OF CALIFORNIA, SAN DIEGO
依托单位国家：
美国
项目类别：
财政年份：
2011
资助国家：
美国
起止时间：
2011-05-01 至 2015-04-30
项目状态：
已结题

来源：
https://reporter.nih.gov/project-details/8163481
关键词：
Address Adoption Algorithms Area Automobile Driving Biological Cell membrane Cell physiology Cells Cellular Structures Classification Complex Computer software Computers Computers and Advanced Instrumentation Couples Cytoskeleton Data Data Set Databases Deposition Devices Disease Electron Microscopy Electrons Face Generations Goals Growth Hybrids Image Imaging Techniques Individual Institutes Internet Label Laboratories Machine Learning Manuals Methods Microscopic Mitochondria Molecular Molecular Target Names Nervous System Physiology Nervous system structure Neurofibrillary Tangles Neurons Neuropil Online Systems Organelles Participant Process Research Research Personnel Resolution Scanning Electron Microscopy Scientist Services Solutions Staining method Stains Structure Subcellular structure System Techniques Three-Dimensional Imaging Tissues Training Universities Utah Validation Work Workload biological systems cellular imaging complex biological systems data mining digital imaging electron optics flexibility image processing improved insight interest knowledge base novel prototype relating to nervous system scientific computing tomography tool web interface

项目摘要

DESCRIPTION (provided by applicant): Advanced instrumentation and cellular imaging techniques using high-throughput 3D electron microscopy are driving a new revolution in the exploration of complex biological systems by providing near seamless views across multiple scales of resolution. These datasets provide the necessary breadth and depth to analyze multicellular, cellular, and subcelluar structure across large swathes of neural tissue. While these new imaging procedures are generating extremely large datasets of enormous value, the quantities are such that no single user or even laboratory team can possibly analyze the full content of their own imaging activities through traditional means. To address this challenge, we propose to further develop and refine a prototype hybrid system for high-throughput segmentation of large neuropil datasets that: 1) advances automatic algorithms for segmentation of cellular and sub-cellular structures using machine learning techniques; 2) couples these techniques to a scalable and flexible process or tool suite allowing multiple users to simultaneously review, edit and curate the results of these automatic approaches; and, 3) builds a knowledge base of training data guiding and improving automated processing. This system will allow project scientists to select areas of interest, execute automatic segmentation algorithms, and distribute workload, curate data, and deposit final results into the Cell Centered Database (Martone et al. 2008) via accessible web-interfaces.

描述（由申请人提供）：使用高通量 3D 电子显微镜的先进仪器和细胞成像技术通过提供跨多种分辨率的近乎无缝的视图，正在推动复杂生物系统探索的一场新革命。这些数据集提供了分析大片神经组织的多细胞、细胞和亚细胞结构所需的广度和深度。虽然这些新的成像程序正在生成具有巨大价值的极其庞大的数据集，但其数量如此之大，以至于没有任何一个用户甚至实验室团队可以通过传统手段分析他们自己的成像活动的全部内容。为了应对这一挑战，我们建议进一步开发和完善用于大型神经细胞数据集高通量分割的原型混合系统：1）使用机器学习技术改进细胞和亚细胞结构分割的自动算法； 2) 将这些技术与可扩展且灵活的流程或工具套件结合起来，允许多个用户同时审查、编辑和管理这些自动方法的结果； 3）建立训练数据指导和改进自动化处理的知识库。该系统将允许项目科学家选择感兴趣的领域，执行自动分割算法，分配工作量，整理数据，并通过可访问的网络界面将最终结果存入以细胞为中心的数据库（Martone et al. 2008）。