A CASE STUDY OF USING TERAGRID FOR LARGE-SCALE MEDICAL IMAGE ANALYSIS

这个子项目是利用资源的许多研究子项目之一。 由NIH/NCRR资助的中心拨款提供。对子项目的主要支持 子项目的首席调查员可能是由其他来源提供的， 包括美国国立卫生研究院的其他来源。为子项目列出的总成本可能 表示该子项目使用的中心基础设施的估计数量， 不是由NCRR赠款提供给次级项目或次级项目工作人员的直接资金。 在这项初步研究中，我们将评估TeraGrid在医学图像处理和分析方面的适用性。具体地说，我们将研究使用TeraGrid进行大规模参数研究和匿名MRI脑扫描的离线处理。我们特别感兴趣的是研究最先进的脑MRI配准和分割算法。众所周知，现有方法很难调整，并且可能需要大量时间来处理真实的高分辨率MRI数据集。我们将首先将我们实验室开发的软件以及其他图像处理工具移植到TeraGrid上。接下来，我们将使用SWIFT Engine(http://www.ci.uchicago.edu/swift/))来描述和执行我们感兴趣的典型工作流程和参数研究。这项研究的潜力是简化和加快医学图像的分析，这可能导致改进的算法，更好的准确性，并从长远来看，改善图像引导程序的结果。

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. In this pilot study we will evaluate the applicability of TeraGrid for the purposes of medical image processing and analysis. Specifically, we will study the use of TeraGrid for conducting large-scale parametric studies and off-line processing of anonymized MRI brain scans. We are particularly interested in studying state of the art algorithms for registration and segmentation of brain MRI. Existing methods are known to be difficult to tune, and may require extensive times for processing realistic high-resolution MRI datasets. We will first port software developed in our lab, together with the other image processing tools, on TeraGrid. Next, we will use Swift engine (http://www.ci.uchicago.edu/swift/) to describe and execute typical workflows and parametric studies of our interest. The potential of this study is to simplify and speed up analysis of medical images, which may result in improved algorithms, better accuracy, and improved outcomes of image-guided procedures in the long term.