Core 1 - Computer Science and Algorithm

计算机科学核心的目标是开发一个用于图像分析的国家计算基础设施，用于生物医学研究和前沿临床研究和实践。为了实现这一广泛的目标，计算机科学核心组织为两个科学团队：算法团队和工程团队。算法团队开发图像分析的新技术，以解决临床研究人员提出的最紧迫的挑战。工程团队开发软件应用程序，提供计算平台，并为算法研究人员和临床研究人员建立软件工程实践。 假设形成和检验。算法和工程的共同努力产生了NA-MIC Kit，这是一个用于医学图像计算的开源平台，包括最终用户应用程序（3D Slicer），图像分析算法和作为插件和可重用库分发的工作流程，类似PACS的图像和数据管理平台，用于数据流和分布式计算的计算平台，以及软件工程和软件质量方法和工具。 这两个团队为NA-MIC的技术挑战带来了互补的技能。的算法 小组由来自四间学术机构的五名高级研究员领导。他们的综合背景提供了著名的变分，统计和几何方法的图像分析的专业知识。工程组由来自两个小企业，一个工业研究机构和两个学术机构的五名高级研究人员领导。他们的综合背景涵盖可视化，医学图像分析，信息系统，科学计算和软件工程。因此，NA-MIC的计算机科学核心具有独特的广度和深度，可以为医学图像计算提供国家基础设施。 为了推动国家医疗图像计算基础设施的发展， 选择了四个DBP，专注于图像分析，以了解疾病，愈合过程和适应，以及治愈和姑息治疗。这些临床应用-心房颤动、亨廷顿病、头颈癌、创伤性脑损伤-强调研究个体的病理或损伤以及病理或损伤如何随时间变化。这种背景下的图像分析需要用于图像分割、配准、统计分析和可视化的新方法和工具。分割必须是客观和稳健的，同时提供有效的交互式编辑。配准必须在计算上高效，但明确地适应纵向数据以及损伤和病理的非刚性或非光滑性质。 对变化的描述需要简明扼要，但要为结构和功能的多层面分析提供统计上可量化的结果。支持这些临床应用研究的软件工具必须足够灵活，以适应新的方法，同时执行软件工程实践，以满足临床环境的性能和稳定性要求。 下面的部分更详细地描述了算法和工程工作，包括 动机和目标，背景和背景，以及方法，以及这些小组和整个项目之间的合作计划。根据RFA的规定，在下面的方法部分以及提案的进度报告（第2.4节）中提供了初步结果。

The objective of the Computer Science Core is to develop a national computing infrastructure for image analysis to be used in biomedical research and leading-edge clinical research and practice. To meet this broad objective, the Computer Science Core is organized as two scientific teams: an Algorithms team and an Engineering team. The Algorithms team develops new techniques for image analysis to address the most pressing challenges posed by clinical researchers. The Engineering team develops software applications, delivers computational platforms, and establishes software engineering practices for algorithm researchers and for clinical hypothesis formation and testing. The combined efforts of Algorithms and Engineering produce the NA-MIC Kit, an open source platform for medical image computing that includes an end-user application (the 3D Slicer), image analysis algorithms and workflows distributed as plug-ins and reusable libraries, a PACS-like image and data management platform, computational platforms for data streaming and distributed computing, and software engineering and software quality methods and tools. The two teams bring complementary skills to the technical challenges in NA-MIC. The Algorithms group is led by five senior investigators from four academic institutions. Their combined background provides renowned expertise in variational, statistical, and geometrical approaches to image analysis. The Engineering group is led by five senior investigators from two small businesses, one industrial research facility, and two academic institutions. Their combined background spans visualization, medical image analysis, information systems, scientific computing, and software engineering. Thus, the Computer Science Core of NA-MIC is uniquely positioned with the breadth and depth to deliver a national infrastructure for medical image computing. To drive the development ofthe national infrastructure for medical image computing, this renewal has selected four DBPs that focus on the analysis of images for the understanding of disease, healing processes and adaptations, and curative and palliative therapies. These clinical applications-atrial fibrillation, Huntington's disease, head and neck cancer, traumatic brain injury-emphasize the study of an individual's pathology or injury and how that pathology or injury changes over time. Image analysis in this context requires new methods and tools for image segmentation, registration, statistical analysis, and visualization. Segmentation must be objective and robust while providing efficient interactive editing. Registration must be computationally efficient, but explicltiy accommodate longitudinal data and the nonrigid or nonsmooth nature of injuries and pathology. Characterization of change needs to be succinct and yet provide statistically quantifiable results for multidimensional analysis of structure and function. The software tools to support research in these clinical applications must be flexible enough to accommodate new methods yet enforce software engineering practices to meet the performance and stability demands of clinical settings. The sections that follow describe the Algorithms and Engineering efforts in more detail, including the motivation and aims, the background and context, and the methods, with plans for collaboration between these groups and the project as a whole. Preliminary results are presented both in the methods section below as well as in the Progress Report (Section 2.4) of the proposal, as proscribed by the RFA.