Anatomy Directly from Imagery: General-purpose, Scalable, and Open-source Machine Learning Approaches

直接从图像进行解剖：通用、可扩展和开源机器学习方法

• 批准号: 9803774
• 负责人: Shireen Youssef Elhabian
• 金额: $ 63.18万
• 依托单位: UNIVERSITY OF UTAH
• 依托单位国家: 美国
• 财政年份: 2019
• 资助国家: 美国
• 起止时间: 2019-07-01 至 2023-05-31
• 项目状态: 已结题
• 来源: https://reporter.nih.gov/project-details/9803774
• 关键词: Address; Adoption; Age; Algorithms; Anatomic Models; Anatomic Surface; Anatomy; Area; Biological; Biological Process; Biological Sciences; Biological Testing; Biology; Biomedical Research; Brain; Bypass; Cardiology; Cessation of life; Clinical; Clinical Data; Cloud Computing; Collection; Communities; Complex; Complex Analysis; Computational Technique; Computer Simulation; Computer software; Computers; Custom; Data; Data Set; Databases; Development; Disease; Felis catus; Funding; Generations; Geometry; Goals; Human; Ice; Image; Imagery; Injury; Intuition; Laboratory Research; Learning; Machine Learning; Magnetic Resonance Imaging; Mathematical Computing; Measures; Medical; Medicine; Mission; Modeling; Modernization; Modification; Morphogenesis; National Institute of General Medical Sciences; Occupations; Online Systems; Organism; Orthopedics; Pathologic; Population; Reproducibility; Research; Research Personnel; Resolution; Science; Scientist; Shapes; Site; Software Engineering; Software Tools; Specialist; Speed; Statistical Data Interpretation; Structure; Supervision; Surface; Techniques; Technology; Time; Training; Variant; Visual; Visualization software; Work; base; biomedical resource; clinical care; clinical investigation; clinically relevant; cohort; computerized tools; computing resources; deep learning; experience; flexibility; global health; graphical user interface; image archival system; image processing; imaging Segmentation; in vivo imaging; innovation; machine learning algorithm; model development; multidisciplinary; open source; particle; preference; software development; tool; usability; user-friendly

Project Summary The form (or shape) and function relationship of anatomical structures is a central theme in biology where abnor- mal shape changes are closely tied to pathological functions. Morphometrics has been an indispensable quan- titative tool in medical and biological sciences to study anatomical forms for more than 100 years. Recently, the increased availability of high-resolution in-vivo images of anatomy has led to the development of a new generation of morphometric approaches, called statistical shape modeling (SSM), that take advantage of modern computa- tional techniques to model anatomical shapes and their variability within populations with unprecedented detail. SSM stands to revolutionize morphometric analysis, but its widespread adoption is hindered by a number of sig- nificant challenges, including the complexity of the approaches and their increased computational requirements, relative to traditional morphometrics. Arguably, however, the most important roadblock to more widespread adop- tion is the lack of user-friendly and scalable software tools for a variety of anatomical surfaces that can be readily incorporated into biomedical research labs. The goal of this proposal is thus to address these challenges in the context of a flexible and general SSM approach termed particle-based shape modeling (PSM), which automat- ically constructs optimal statistical landmark-based shape models of ensembles of anatomical shapes without relying on any specific surface parameterization. The proposed research will provide an automated, general- purpose, and scalable computational solution for constructing shape models of general anatomy. In Aim 1, we will build computational and machine learning algorithms to model anatomies with complex surface topologies (e.g., surface openings and shared boundaries) and highly variable anatomical populations. In Aim 2, we will introduce an end-to-end machine learning approach to extract statistical shape representation directly from im- ages, requiring no parameter tuning, image pre-processing, or user assistance. In Aim 3, we will provide intuitive graphical user interfaces and visualization tools to incorporate user-defined modeling preferences and promote the visual interpretation of shape models. We will also make use of recent advances in cloud computing to enable researchers with limited computational resources and/or large cohorts to build and execute custom SSM work- flows using remote scalable computational resources. Algorithmic developments will be thoroughly evaluated and validated using existing, fully funded, large-scale, and constantly growing databases of CT and MRI images lo- cated on-site. Furthermore, we will develop and disseminate standard workflows and domain-specific use cases for complex anatomies to promote reproducibility. Efforts to develop the proposed technology are aligned with the mission of the National Institute of General Medical Sciences (NIGMS), and its third strategic goal: to bridge biology and quantitative science for better global health through supporting the development of and access to computational research tools for biomedical research. Our long-term goal is to increase the clinical utility and widespread adoption of SSM, and the proposed research will establish the groundwork for achieving this goal.

项目概要 解剖结构的形式（或形状）和功能关系是生物学的中心主题，其中 畸形的形状变化与病理功能密切相关。形态计量学已成为不可缺少的计量学 100 多年来，它一直是医学和生物科学领域研究解剖形态的有力工具。最近， 高分辨率体内解剖图像的可用性的增加导致了新一代的开发 形态测量方法，称为统计形状建模（SSM），利用现代计算 以前所未有的细节对人群中的解剖形状及其变异性进行建模的技术。 SSM 将为形态测量分析带来革命性的变化，但其广泛采用受到许多因素的阻碍。 严峻的挑战，包括方法的复杂性及其增加的计算要求， 相对于传统的形态测量学。然而，可以说，更广泛采用的最重要障碍是 问题是缺乏适用于各种解剖表面的用户友好且可扩展的软件工具，可以轻松地 并入生物医学研究实验室。因此，本提案的目标是解决这些挑战 灵活且通用的 SSM 方法称为基于粒子的形状建模 (PSM)，该方法自动 icly 构建了解剖形状整体的基于统计地标的最佳形状模型，而无需 依赖于任何特定的表面参数化。拟议的研究将提供一个自动化的、通用的 用于构建一般解剖形状模型的目的和可扩展的计算解决方案。在目标 1 中，我们 将构建计算和机器学习算法来模拟具有复杂表面拓扑的解剖结构 （例如，表面开口和共享边界）和高度可变的解剖群体。在目标 2 中，我们将 引入端到端机器学习方法，直接从图像中提取统计形状表示 年龄，不需要参数调整、图像预处理或用户帮助。在目标 3 中，我们将提供直观的 图形用户界面和可视化工具可合并用户定义的建模首选项并促进 形状模型的视觉解释。我们还将利用云计算的最新进展来实现 计算资源有限和/或大型群体的研究人员构建和执行定制 SSM 工作 使用远程可扩展计算资源流动。算法的发展将得到彻底的评估和 使用现有的、资金充足、大规模且不断增长的 CT 和 MRI 图像数据库进行验证 现场提供。此外，我们将开发和传播标准工作流程和特定领域的用例 用于复杂的解剖结构以提高再现性。开发拟议技术的努力与 国家普通医学科学研究所 (NIGMS) 的使命及其第三个战略目标： 生物学和定量科学通过支持开发和获取来改善全球健康 用于生物医学研究的计算研究工具。我们的长期目标是提高临床实用性和 SSM 的广泛采用，拟议的研究将为实现这一目标奠定基础。