DEVELOPMENT OF AUTOMATED SEGMENTATION TOOL FOR MOUSE BRAIN

小鼠大脑自动分割工具的开发

• 批准号: 8363167
• 负责人: Teresa Wu
• 金额: $ 1.23万
• 依托单位: DUKE UNIVERSITY
• 依托单位国家: 美国
• 财政年份: 2011
• 资助国家: 美国
• 起止时间: 2011-07-01 至 2012-06-30
• 项目状态: 已结题
• 来源: https://reporter.nih.gov/project-details/8363167
• 关键词: Brain; Classification; Data; Detection; Development; Face; Funding; Grant; Literature; Machine Learning; Methodology; Microscopy; Microtus; Mus; National Center for Research Resources; Positron-Emission Tomography; Principal Investigator; Research; Research Infrastructure; Research Personnel; Resources; Sample Size; Source; Structure; Techniques; Text; Touch sensation; United States National Institutes of Health; cost; optical character recognition; tool

This subproject is one of many research subprojects utilizing the resources provided by a Center grant funded by NIH/NCRR. Primary support for the subproject and the subproject's principal investigator may have been provided by other sources, including other NIH sources. The Total Cost listed for the subproject likely represents the estimated amount of Center infrastructure utilized by the subproject, not direct funding provided by the NCRR grant to the subproject or subproject staff. MR microscopy - shared MR mouse brain data with the investigator. Develop methodology for automated segmentation of the mouse brain into neuroanatomical structures. In specifically, we are planning to explore the applicability of Support Vector Machine (SVM) and Markov Random Field (MRF) for mouse brain segmentation. SVMs have been applied to numerous fields including classification of brain PET images, optical character recognition, object detection, face verification, text categorization and so on. To our knowledge, applying SVM to classify mouse brain structures has been less touched. Recently literature indicates Ali et al (2005) explored the use of Markov Random Field (MRF) for mouse brain segmentation. Given smaller sample size of subjects, SVM tends to have superior results than techniques such as MRF. Therefore, we would like to first conduct comparison study. We will compare the segmentation results of SVM with that of MRF.

这个子项目是许多利用资源的研究子项目之一 由NIH/NCRR资助的中心拨款提供。子项目的主要支持 子项目的主要研究者可能是由其他来源提供的， 包括其它NIH来源。 列出的子项目总成本可能 代表子项目使用的中心基础设施的估计数量， 而不是由NCRR赠款提供给子项目或子项目工作人员的直接资金。 MR显微镜检查-与研究者共享MR小鼠脑数据。 开发将小鼠大脑自动分割成神经解剖结构的方法。具体来说，我们计划探索支持向量机（SVM）和马尔可夫随机场（MRF）的小鼠大脑分割的适用性。支持向量机已被广泛应用于脑PET图像分类、光学字符识别、目标检测、人脸识别、文本分类等领域，但目前将支持向量机应用于小鼠脑结构分类的研究较少。最近的文献表明，Ali等人（2005）探索了马尔可夫随机场（MRF）用于小鼠脑分割。由于受试者的样本量较小，SVM往往比MRF等技术具有上级结果。因此，我们想先进行比较研究。我们将比较SVM和MRF的分割结果。