USING MACHINE LEARNING TO SPEED UP MANUAL IMAGE ANNOTATION

使用机器学习加速手动图像注释

• 批准号: 8171453
• 负责人: ROBERT H WATERSTON
• 金额: $ 0.05万
• 依托单位: UNIVERSITY OF WASHINGTON
• 依托单位国家: 美国
• 财政年份: 2010
• 资助国家: 美国
• 起止时间: 2010-09-01 至 2011-08-31
• 项目状态: 已结题
• 来源: https://reporter.nih.gov/project-details/8171453
• 关键词: 3-Dimensional; Benchmarking; Biological; Caenorhabditis elegans; Cell Count; Cell Cycle Progression; Cells; Computer Retrieval of Information on Scientific Projects Database; Data; Data Set; Embryo; Funding; Gene Expression; Genes; Grant; Hour; Image; Image Analysis; Individual; Institution; Label; Machine Learning; Manuals; Methodology; Microscopy; Movement; Names; Noise; Paper; Pattern Recognition; Process; Program Development; Proteins; Protocols documentation; Research; Research Personnel; Resources; Sampling; Source; Speed; Staging; Time; Training; United States National Institutes of Health; Validation; graphical user interface; programs; research study; tool

This subproject is one of many research subprojects utilizing the resources provided by a Center grant funded by NIH/NCRR. The subproject and investigator (PI) may have received primary funding from another NIH source, and thus could be represented in other CRISP entries. The institution listed is for the Center, which is not necessarily the institution for the investigator. Background Image analysis is an essential component in many biological experiments that study gene expression, cell cycle progression, and protein localization. A protocol for tracking the expression of individual C. elegans genes was developed that collects image samples of a developing embryo by 3-D time lapse microscopy. In this protocol, a program called StarryNite performs the automatic recognition of fluorescently labeled cells and traces their lineage. However, due to the amount of noise present in the data and due to the challenges introduced by increasing number of cells in later stages of development, this program is not error free. In the current version, the error correction (i.e., editing) is performed manually using a graphical interface tool named AceTree, which is specifically developed for this task. For a single experiment, this manual annotation task takes several hours. Results: In this paper, we reduce the time required to correct errors made by StarryNite. We target one of the most frequent error types (movements annotated as divisions) and train an SVM classifier to decide whether a division call made by StarryNite is correct or not. We show, via cross-validation experiments on several benchmark data sets, that the SVM successfully identifies this type of error significantly. A new version of StarryNite that includes the trained SVM classifier is available at http://starrynite.sourceforge.net. Conclusions: We demonstrate the utility of a machine learning approach to error annotation for StarryNite. In the process, we also provide some general methodologies for developing and validating a classifier with respect to a given pattern recognition task.

该子项目是利用该技术的众多研究子项目之一 资源由 NIH/NCRR 资助的中心拨款提供。子项目及 研究者 (PI) 可能已从 NIH 的另一个来源获得主要资金， 因此可以在其他 CRISP 条目中表示。列出的机构是 对于中心来说，它不一定是研究者的机构。 背景图像分析是许多研究基因表达、细胞周期进程和蛋白质定位的生物实验的重要组成部分。开发了一种用于跟踪个体线虫基因表达的方案，该方案通过 3D 延时显微镜收集发育中胚胎的图像样本。在此协议中，名为 StarryNite 的程序自动识别荧光标记的细胞并追踪其谱系。然而，由于数据中存在大量噪声，并且由于开发后期阶段细胞数量增加带来的挑战，该程序并非没有错误。在当前版本中，纠错（即编辑）是使用专门为此任务开发的名为 AceTree 的图形界面工具手动执行的。对于单个实验，此手动注释任务需要几个小时。 结果：在本文中，我们减少了纠正 StarryNite 错误所需的时间。我们针对最常见的错误类型之一（注释为除法的运动）并训练 SVM 分类器来确定 StarryNite 进行的除法调用是否正确。我们通过对多个基准数据集进行交叉验证实验表明，SVM 成功地显着识别了此类错误。包含经过训练的 SVM 分类器的 StarryNite 新版本可从 http://starrynite.sourceforge.net 获取。 结论：我们展示了机器学习方法对 StarryNite 错误注释的实用性。在此过程中，我们还提供了一些针对给定模式识别任务开发和验证分类器的通用方法。