Development of Software for Automated Quantification of Brain MR Images

描述(由申请人提供)：本申请的总体目标是开发一种用于脑部磁共振图像的自动化和定量分析工具。这项技术是基于Mori和Miller博士开发的MriStudio程序，该程序的特点是准确的多模式微分映射和可变形的图谱，其中包含对灰质和白质结构的广泛解剖学定义。该程序已经在正常和不同的患者群体中进行了广泛的准确性测试。这项第一阶段拨款将支持将现有项目整合到自动化管道中，并生成数据供FDA批准。目前，MRI的日常放射诊断几乎完全基于定性检查。然而，定量分析结果的可用性，如各种脑结构的体积，将为临床诊断和随后的患者护理提供各种好处。如果解剖状态的定量报告是可用的，它可以很容易地与正常人的结果进行比较，以估计异常的程度。与目前的自由文本格式相比，定量报告可以更容易地与临床功能相关联。量化数据可以存储为临床数据库(PACS)的一部分，该数据库是完全可搜索的，因此，可以容易地检索具有相似解剖状态的过去病例，并且可以利用过去病例的功能结果和最终诊断来丰富当前诊断。如果可以进行连续扫描，也可以很容易地意识到纵向变化。我们的具体目标是；目标1：建立一条用于全自动化的管道并测试分割精度新设计的工具将基于MriStudio平台(www.mristudio.org)。该软件专为研究用途而设计，可完全访问每个分析步骤的参数和结果。我们需要以独立于平台的方式将其转换为完全自动化的管道。然后，这条新的管道必须进行严格的准确性测试，Mori博士的实验室拥有30个训练图像数据集，对12个基底节和16个核心白质结构进行完全手动分割。我们将使用这些数据集来测试自动分割的准确性。目的2：将管道应用于正常数据并为每个年龄建立正常值范围我们将使用Mori博士实验室的儿科、年轻人和老年正常数据库来建立每个年龄的正常值和解剖变异程度。我们将对每个分割结构的体积、T2强度和DTI衍生指数进行量化。将描述量化数值和置信度的年龄相关性。这些数据将提供有关检测异常的统计能力的信息。该数据库包含成像参数的可变性，其对测量值的影响将被表征。这些信息以及各种脑部疾病的现有临床数据将用于在第二阶段研究和FDA未来的应用中评估拟议工具的有效性。 与公共健康相关：我们将开发用于自动分析脑部磁共振图像的软件。该软件提供各种脑部疾病患者的脑解剖状态的定量评估。

DESCRIPTION (provided by applicant): The overall goal of this application is to develop an automated and quantitative analysis tool for brain MR images. The technology is based on the MriStudio program developed by Drs. Mori and Miller, which is characterized by accurate multi-modal diffeomorphic mapping and deformable atlases with extensive anatomical definitions of gray and white matter structures. The program has been extensively tested for accuracy in normal and various patient groups. This Phase I grant will support the integration of existing programs into an automated pipeline and generate data for FDA approval. Currently, daily radiological diagnosis of MRI is almost exclusively based on qualitative examination. However, the availability of quantitative analysis results, such as volumes of various brain structures, would provide a variety of benefits for clinical diagnosis and subsequent patient care. If quantitative reporting of anatomical status were available, it could be readily compared with results from normals to estimate the degree of abnormalities. Compared to the current free-text format, quantitative reporting could be correlated with clinical functions more easily. Quantitativ data could be stored as a part of clinical database (PACS), which is fully searchable, and, thus, past cases with similar anatomical status could be readily retrieved and the functional outcomes and final diagnosis in past cases could be used to enrich current diagnosis. If serial scans were available, longitudinal changes could also be appreciated readily. Our specific aims are; Aim 1: Build a pipeline for full automation and test the parcellation accuracy the newly designed tools will be based on the MriStudio platform (www.mristudio.org). This software is designed for research use, with full access to parameters and results at each analysis step. We need to convert it to a fully automated pipeline in a platform-independent manner. This new pipeline then must be rigorously tested for accuracy Dr. Mori's lab has 30 training image datasets with full manual segmentation for 12 basal ganglia and 16 core white matter structures. We will use these datasets to test the accuracy of the automated segmentation. Aim 2: Apply the pipeline to normal data and establish normal ranges of values for each age we will use the pediatric, young adult, and elderly normal databases in Dr. Mori's lab to establish normal values and the degree of anatomical variability at each age. We will quantify volumes, T2 intensity, and DTI- derived indices for each parcellated structure. The age-dependency of the quantified values and confidence levels will be characterized. This data will provide information about the statistical power to detect abnormalities. The database contains variability in imaging parameters, the impact of which on the measured values will be characterized. This information, as well as the existing clinical data for various brain diseases, will be used to evaluate the efficacy of the proposed tool in the Phase II study and in the future FDA application. PUBLIC HEALTH RELEVANCE: We will develop software for automated analysis of brain MR images. This software provides quantitative assessment of brain anatomical status of various brain disease patients.