ShapeWorks in the Cloud

云中的 ShapeWorks

• 批准号: 10166337
• 负责人: Shireen Youssef Elhabian
• 金额: $ 21万
• 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 2024-05-31
• 项目状态: 已结题
• 来源: https://reporter.nih.gov/project-details/10166337
• 关键词: Address; Adherence; Administrative Supplement; Adoption; Anatomy; Applied Research; Architecture; Area; Award; Biological; Biological Sciences; Biology; Cardiology; Clinical; Clinical Data; Clinical Trials; Cloud Computing; Cloud Service; Code; Collection; Communication; Communities; Complex; Complex Analysis; Computer Models; Computer software; Computers; Coupled; Custom; Data; Data Sources; Databases; Disabled Persons; Documentation; Environment; Face; Funding; Goals; Image; Imagery; Language; Learning; Machine Learning; Mathematics; Medical; Medicine; Methods; Modeling; Morphology; Occupations; Online Systems; Orthopedics; Parents; Pathologic; Phenotype; Population; Privatization; Psychology; Readiness; Reproducibility; Research; Research Personnel; Running; Scientist; Services; Shapes; Software Design; Software Engineering; Software Tools; Source Code; Speed; Standardization; System; Techniques; Technology; Testing; Work; base; cohort; computational platform; computerized tools; computing resources; data management; design; experience; flexibility; imaging Segmentation; improved; innovation; large datasets; model development; open data; open source; particle; response; scientific computing; shape analysis; software development; statistics; tool; user-friendly

Project Summary This application is submitted in response to NOT-OD-20-073 as an administrative supplement to the parent award R01AR076120 titled: "Anatomy Directly from Imagery: General-purpose, Scalable, and Open-source Machine Learning Approaches." The form (or shape) of anatomies is the clinical language that describes abnormal mor- phologies tied to pathologic functions. Quantifying such subtle morphological shape changes requires parsing the anatomy into a quantitative description that is consistent across the population in question. For more than 100 years, morphometrics has been an indispensable quantitative tool in medical and biological sciences to study anatomical forms. But its representation capacity is limited to linear distances, angles, and areas. Sta- tistical shape modeling (SSM) is the computational extension of classical morphometric techniques to analyze more detailed representations of complex anatomy and their variability within populations The parent award ad- dresses existing roadblocks for the widespread adoption of SSM computational tools in the context of a flexible and general SSM approach termed particle-based shape modeling (PSM) and its associated suite of open-source software tools, ShapeWorks. ShapeWorks enables learning population-level shape representation via automatic dense placement of homologous landmarks on image segmentations of general anatomy with arbitrary topology. The utility of ShapeWorks has been demonstrated in a range of biomedical applications. ShapeWorks has the potential to transform the way researchers approach studies of anatomical forms, but its widespread applicability and impact to medicine and biology are hindered by computational barriers that most existing shape modeling packages face. The goal of this supplement award is to provide supplemental support for Aim 3 of the parent award to leverage best practices in software development and advances in cloud computing to enable researchers with limited computational resources and/or large-scale cohorts to build and execute custom SSM workflows us- ing remote scalable computational resources. To achieve this goal, we have developed a plan to enhance the design, implementation, and cloud-readiness of ShapeWorks and augmented our scientific team to add senior, experienced software engineers/developers who have extensive experience in professional programming, code refactoring, and scientific computing. This award will provide our team with the support necessary to (Aim 1) de- sign ShapeWorks as a collection of modular and reusable services, (Aim 2) decouple ShapeWorks services from explicitly encoded data sources, and (Aim 3) refactor ShapeWorks to scale efficiently on the cloud. All software development will be performed in adherence to software engineering practices and design principles, including coding style, documentation, and version control. The proposed efforts will be released as open-source software in a manner consistent with the principles of reproducible research and the practices of open science. Our long- term goal is to make ShapeWorks a standard tool for shape analyses in medicine, and the work proposed herein in addition to the parent award will establish the groundwork for achieving this goal.

项目概要 本申请是针对 NOT-OD-20-073 提交的，作为家长奖励的行政补充 R01AR076120 标题：“直接从图像进行解剖：通用、可扩展和开源机器 学习方法。”解剖学的形式（或形状）是描述异常形态的临床语言。 量化这种微妙的形态形状变化需要解析。 将解剖学转化为在相关人群中一致的定量描述。 一百年来，形态计量学一直是医学和生物科学中不可或缺的定量工具 研究解剖形式。但其表示能力仅限于线性距离、角度和面积。 统计形状建模 (SSM) 是经典形态测量技术的计算扩展，用于分析 更详细地表示复杂的解剖结构及其在人群中的变异性 解决了在灵活的环境下广泛采用 SSM 计算工具的现有障碍 和通用 SSM 方法称为基于粒子的形状建模 (PSM) 及其相关的开源套件 ShapeWorks 软件工具可以通过自动学习人口级别的形状表示。 在具有任意拓扑的一般解剖学图像分割上密集放置同源地标。 ShapeWorks 的实用性已在一系列生物医学应用中得到证明。 有可能改变研究人员进行解剖形式研究的方式，但其广泛的适用性 对医学和生物学的影响受到大多数现有形状建模的计算障碍的阻碍 该补充奖励的目标是为家长的目标 3 提供补充支持。 该奖项旨在利用软件开发的最佳实践和云计算的进步来帮助研究人员 使用有限的计算资源和/或大规模队列来构建和执行自定义 SSM 工作负载 为了实现这一目标，我们制定了一项增强远程可扩展计算资源的计划。 ShapeWorks 的设计、实施和云就绪性，并增强了我们的科学团队，增加了高级、 经验丰富的软件工程师/开发人员，在专业编程、代码方面拥有丰富的经验 该奖项将为我们的团队提供（目标 1）解构所需的支持。 将 ShapeWorks 标记为模块化和可重用服务的集合，（目标 2）将 ShapeWorks 服务与 对显式数据源进行编码，并且（目标 3）重构 ShapeWorks 以在云上高效扩展所有软件。 开发将遵循软件工程实践和设计原则，包括 编码风格、文档和版本控制将作为开源软件发布。 以符合可重复研究原则和开放科学实践的方式。 长期目标是使 ShapeWorks 成为医学形状分析的标准工具，本文提出的工作 除了家长奖之外，还将为实现这一目标奠定基础。