Enhanced Software Tools for Detecting Anatomical Differences in Image Data Sets

用于检测图像数据集中的解剖差异的增强软件工具

• 批准号: 10265564
• 负责人: Beau M Ances
• 金额: $ 101.18万
• 依托单位: KITWARE, INC.
• 依托单位国家: 美国
• 财政年份: 2018
• 资助国家: 美国
• 起止时间: 2018-09-18 至 2024-08-31
• 项目状态: 已结题
• 来源: https://reporter.nih.gov/project-details/10265564
• 关键词: Affect; Algorithmic Software; Algorithms; Anatomy; Blood flow; Brain; Clinical; Clinical Research; Computer software; Data; Data Analytics; Data Set; Databases; Detection; Deterioration; Diffuse; Disease; Drug Screening; Goals; Grain; HIV; Image; Image Analysis; Internet; Joints; Label; Lead; Machine Learning; Measures; Medical Imaging; Metabolic; Methodology; Methods; Modeling; Monitor; Nature; Nerve Degeneration; Neurodegenerative Disorders; Neurologic; Neurologic Effect; Neurosurgeon; Online Systems; Outcome; Performance; Pharmaceutical Preparations; Pharmacotherapy; Phase; Population Analysis; Population Study; Positioning Attribute; Process; Questionnaires; Research; Research Personnel; Services; Shapes; Software Tools; Software Validation; Source; Statistical Data Interpretation; Technology; Testing; Time; Training; Universities; Variant; Visualization; Washington; analysis pipeline; base; data access; data infrastructure; deep learning; experience; gray matter; high throughput screening; image registration; imaging capabilities; improved; insight; interest; metabolic rate; morphometry; nervous system disorder; neurodegenerative dementia; novel; programs; prototype; regional difference; research and development; shape analysis; software development; software infrastructure; task analysis; tool; usability; web app; web services; white matter

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 affect 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 of discovering 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.

项目摘要 形态测量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为大脑解剖结构的微妙和变化， 可以是非局部的性质，并影响白色和灰质的数量以及相对定位， 局部大脑解剖的形状。最先进的形态测量方法集中于局部物质分布或 先天选择的解剖结构的形状变化，但难以检测整体或区域的恶化， 物质;在许多神经退行性过程中的重要作用。提案小组最近开发了一个 基于不平衡最佳运输的形态测量分析，称为UTM，它承诺能够 发现物质的局部和全局改变，而不需要先验地选择 兴趣该提案的目标是将UTM技术开发成自动化的软件工具， 大神经成像数据集的高通量筛选。一种更灵敏的自动化 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， 更有效地筛选药物相关效应。