Image-derived modeling

图像衍生建模

• 批准号: 10228750
• 负责人: Robert F Murphy
• 金额: $ 24.43万
• 依托单位: UNIVERSITY OF PITTSBURGH AT PITTSBURGH
• 依托单位国家: 美国
• 财政年份: 2012
• 资助国家: 美国
• 起止时间: 2012-09-24 至 2023-07-31
• 项目状态: 已结题
• 来源: https://reporter.nih.gov/project-details/10228750
• 关键词: Affinity; Biological; Cell model; Cells; Collection; Color; Computer Vision Systems; Computer software; Data; Dependence; Descriptor; Development; Dimensions; Disease; Electron Microscope; Funding; Galaxy; Genetic Transcription; Goals; Grant; High Performance Computing; Image; Immunoprecipitation; Individual; Knowledge; Laboratories; Learning; Link; Location; Machine Learning; Measurement; Methods; Microscope; Modeling; Molecular; Molecular Structure; Movement; Organelles; Population; Process; Protein Dynamics; Publications; Pythons; Reaction; Resolution; Running; Semantics; Shapes; Structural Models; Structure; System; Testing; Time; Training; Vesicle; Vision; Work; automated analysis; biological systems; cell type; convolutional neural network; deep learning; fluorescence microscope; improved; learning strategy; microscopic imaging; models and simulation; movie; multi-scale modeling; nonlinear regression; novel strategies; open source; simulation; software development; spatiotemporal; tool

VI. TR&D4 - Abstract The overall goal of this project is to develop tools for making maximal use of the information in biological images to enable the construction of predictive, multiscale models of structure and dynamics at the subcellular and cellular level. The tools will be especially useful for studies of how cell organization is created and maintained and how that organization differs from cell type to cell type and during disease. While existing software primarily provides descriptions of images, the focus of this project is on construction of generative models of cell organization. Generative models are learned from a collection of images and are capable of producing new images that are statistically equivalent to the images used for training. These models have distinct advantages over discriminative or descriptive approaches. They attempt to make use of all information in images, rather than to just extract selected descriptors or features. Further, while features are not useful for comparing and communicating results between different laboratories due to their dependence upon the specifics of image acquisition, generative models capture the underlying reality that gave rise to images and can therefore be compared across different microscopes and laboratories. They are also combinable and reusable, in that models can be linked together to make predictions about new relationships, and models for organelle shape and distribution learned for one cell type can be provisionally extended to new cell types. Work during the prior funding led to the development of extensive generative model capabilities that were incorporated into the open source CellOrganizer system. We propose to build upon this work to build new capabilities for constructing models that consider the extensive interrelationships between organelles and structures in cells, and for modeling the dynamics of proteins and organelles. In conjunction with TR&D3, we will also develop new methods for using images to constrain estimation of the affinities between components of a biological system. Lastly, we will develop new approaches for constructing models from both electron and fluorescence microscope images. The proposed work makes use of best available methods in machine learning and computer vision, including advanced inference methods and convolutional neural nets (so called “deep learning” methods). The work builds on the extensive progress that has been made under what was Aim 1 of TR&D3 in the prior funding period, which resulted in eleven publications that acknowledged P41 support.

六． TR&D4 - 摘要 该项目的总体目标是开发最大限度地利用生物信息的工具 图像能够构建亚细胞结构和动力学的预测性多尺度模型 和细胞水平。这些工具对于研究细胞组织是如何创建和 维持以及该组织在不同细胞类型和疾病期间有何不同。虽然现有 软件主要提供图像的描述，该项目的重点是构建生成 细胞组织模型。生成模型是从图像集合中学习的，并且能够 生成在统计上与用于训练的图像等效的新图像。这些型号有 与歧视性或描述性方法相比具有明显的优势。他们试图利用所有信息 在图像中，而不仅仅是提取选定的描述符或特征。此外，虽然功能对于 由于不同实验室对结果的依赖，因此可以比较和交流不同实验室之间的结果 图像采集的细节，生成模型捕捉产生图像和的潜在现实 因此可以在不同的显微镜和实验室之间进行比较。它们也是可以组合的并且 可重用，因为模型可以链接在一起以对新关系进行预测，并且模型可以 针对一种细胞类型学到的细胞器形状和分布可以暂时扩展到新的细胞类型。 先前资助期间的工作导致了广泛的生成模型功能的开发 合并到开源 CellOrganizer 系统中。我们建议在这项工作的基础上建立新的 构建考虑细胞器和细胞之间广泛相互关系的模型的能力 细胞结构，以及蛋白质和细胞器动力学建模。结合 TR&D3，我们 还将开发新的方法，使用图像来限制对组件之间亲和力的估计 一个生物系统。最后，我们将开发新的方法来从电子和 荧光显微镜图像。 拟议的工作利用了机器学习和计算机视觉领域的最佳可用方法，包括 高级推理方法和卷积神经网络（所谓的“深度学习”方法）。工作 建立在先前资助的 TR&D3 目标 1 下取得的广泛进展的基础上 期间，有 11 份出版物承认 P41 的支持。