Enhanced Software Tools for Detecting Anatomical Differences in Image Data Sets

项目摘要 形态计量学分析是发现疾病和药物对大脑影响的主要算法工具 解剖学。神经变性和疾病表现在大脑解剖的微妙和多样的变化中， 可以是非局部的白色和灰质的性质和效应量以及相对位置和 局部脑部解剖的形状。最新的形态测量方法专注于局部物质分布或 先天选定的解剖结构的形状变化，但难以检测到全球或区域的恶化 物质；在许多神经退化过程中起重要作用。提案团队最近开发了一种 基于非平衡最优传输的形态测量分析，称为UTM，它有望能够 无需事先选择感兴趣的解剖区域即可发现物质的局部和全局变化。 这项提案的目标是将UTM技术发展成为自动化的软件工具 高通量筛选大型神经影像数据集。更灵敏的自动化 形态分析工具将帮助研究人员发现与疾病相关的神经影响，并导致 更有效地筛选与药物相关的影响。

Project Summary Morphometric analysis is a primary algorithmic tool to discover disease and drug related effects on brain anatomy. Neurological degeneration and disease manifest in subtle and varied changes in brain anatomy that can be non-local in nature and effect amounts of white and gray matter as well as relative positioning and shapes of local brain anatomy. State-of-the-art morphometry methods focus on local matter distribution or on shape variations of apriori selected anatomies but have difficulty in detecting global or regional deterioration of matter; an important effect in many neurodegenerative processes. The proposal team recently developed a morphometric analysis based on unbalanced optimal transport, called UTM, that promises to be capable to discover local and global alteration of matter without the need to apriori select an anatomical region of interest. The goal of this proposal is to develop the UTM technology into a software tool for automated high-throughput screening of large neurological image data sets. A more sensitive automated morphometric analysis tool will help researchers to discover neurological effects related to disease and lead to more efficient screening for drug related effects.