Highly Automated Analysis of 4-D Cardiovascular MR Data

描述（由申请人提供）： 磁共振（MR）成像在先天性心脏病的诊断和治疗中发挥着越来越重要的作用。通常，心血管MR数据进行定性分析。增强的计算能力和定量图像分析应提供快速，全面和可重复的评估4维MR数据集。从开发一种通用的心脏图像分割方法开始，该建议侧重于两组受试者-术后法洛四联症患者和结缔组织疾病患者。这些患者需要分别对右心室功能和主动脉尺寸进行准确的连续评估。在本提案中，基于主动外观模型（AAM）的图像分析方法将应用于这两项任务。在训练过程中，AAM是从手动分析的图像示例中自动构建的。在分析阶段，AAM允许使用其学习到的关于感兴趣对象（心室和胸主动脉）的允许形状和外观的知识来完全自动地分割图像数据。驱动该提议的假设是a）基于主动外观模型的分割可以提供对心血管MR图像的自动化、可再现的评估，并且通过分析四维数据来增加这些研究的信息内容（3-D +时间），消除了操作员的可变性和劳动密集型边界跟踪，以及B）心室和主动脉表面形态和运动的完整4-D数据集将提供疾病状态的新的定量指标。我们建议：I）开发并验证基于主动外观模型（AAM）的方法，用于从体积MR图像中对左心室和右心室以及胸主动脉进行3-D和4-D（3-D +时间）分割。2)使用4-D AAM分割方法开发并验证患者特定方法，用于对左右心室和胸主动脉进行高度自动化和可重复的系列分析。3)开发一套新的心室和主动脉形态和功能的定量指标，并验证这些测量在法洛四联症患者和结缔组织疾病患者术后的可重复性。将评估疾病状态、心室功能和主动脉大小的标准测量以及新的定量指标之间的关系。

DESCRIPTION (provided by applicant): Magnetic resonance (MR) imaging plays an increasingly important role in the diagnosis and management of congenital heart disease. Often, cardiovascular MR data are analyzed qualitatively. Enhanced computing power and quantitative image analysis should provide rapid, comprehensive and reproducible assessment of 4-dimensional MR data sets. Starting with development of a general-purpose cardiac image segmentation method, this proposal focuses on two groups of subjects - postoperative tetralogy of Fallot patients and patients with connective tissue disorders. These patients require accurate, serial assessment of right ventricular function and aortic dimensions, respectively. In this proposal, an image analysis methodology based on Active Appearance Models (AAM) will be applied to both tasks. During training, the AAM is built automatically from manually analyzed image examples. In the analysis stage, the AAM allows fully automated segmentation of image data using its learned knowledge of allowed shapes and appearances of objects of interest - the ventricles and the thoracic aorta. Hypotheses driving this proposal are that a) active appearance model-based segmentation can provide automated, reproducible assessment of cardiovascular MR images and increase the information content of these studies by analyzing data in four dimensions (3-D + time), eliminating operator variability and labor-intensive border tracing, and that b) complete 4-D data sets of ventricular and aortic surface morphology and motion will provide novel quantitative indices of disease status. We propose to: I) Develop and validate an active appearance model (AAM) based method for 3-D and 4-D (3-D + time) segmentation of the left and right ventricles and the thoracic aorta from volumetric MR images. 2) Use the 4-D AAM segmentation approach to develop and validate a patient-specific method for highly automated and reproducible serial analysis of the right and left ventricles and the thoracic aorta. 3) Develop a set of novel quantitative indices of ventricular and aortic morphology and function and validate the reproducibility of these measurements in postoperative tetralogy of Fallot patients and connective tissue disorder pa tients. The relationship between disease status, standard measures of ventricular function and aortic size, and novel quantitative indices will be assessed.