Analysis of tracking based phenotypes in CNS

该项目的目标是开发“原型和规模”动态图像识别软件，以在广泛的基于显微镜的中枢神经系统（CNS）应用中对基于跟踪的表型进行评分。目标软件工具可以灵活地教授对感兴趣的精确动态表型进行评分或筛选，并且可扩展，与成像分析平台（例如成像系统，试剂等）一起提供高通量评分。它将提供1)运动信号分解以分离异质时空模式；2)可教亚细胞目标检测；3)可教亚细胞目标跟踪；4)综合航迹表征；5)动态数据分析接口，支持动态表型发现和评分。我们建议扩展和商业化我们的跟踪技术，包括基于可教跟踪状态的跟踪，运动能量跟踪增强和跟踪分类。该工作产品将被纳入我们的旗舰产品SVCell，并通过我们的商业合作伙伴，包括尼康公司销售。假设我们的跟踪软件可用于广泛的中枢神经系统应用的准确和稳健的分析，并可扩展为动态跟踪特性的高吞吐量评分，具有高速度，准确性和可靠性。为了验证这一假设，我们提出了以下具体目标：目标1：为广泛的基于表型的跟踪优化可教跟踪模块；目标2：优化和验证基于表型跟踪的高通量评分；目标3：通过现场测试和科学合作评估SVCell跟踪beta的产品准备情况。该项目意义重大，因为需要能够灵活地筛选各种基于跟踪的高通量动态表型的技术，以支持基础研究（如表型）和应用研究（如药物发现）中实际有效的中枢神经系统相关科学项目。在延时显微镜电影中分析这些动态表型可以提供对中枢神经系统疾病形成的见解，并使早期和更有效的干预成为可能。延时显微镜图像识别可以对对抗神经系统疾病和精神疾病产生重大影响。通过量化电影中复杂的动态表型，它为科学家提供了一个强大的工具，可以发现中枢神经系统重要功能的基本机制，然后筛选作用于它们的方法。这可以使早期和更有效的治疗干预成为可能。

DESCRIPTION (provided by applicant): Project Summary The objective of this project is to develop "Prototype and Scale" kinetic image recognition software to score tracking based phenotypes in a broad range of microscopy based central nervous system (CNS) applications. The target software tool can be flexibly taught to score or screen the precise dynamic phenotypes of interest, and scalable, together with the imaging assay platform (e.g. imaging system, reagents, etc.) to provide high throughput scoring. It will provide 1) motion signal decomposition to isolate heterogeneous spatial-temporal patterns; 2) teachable subcellular object detection; 3) teachable subcellular object tracking; 4) comprehensive track characterization; and 5) kinetic data analysis interfaces to support dynamic phenotype discovery and scoring. We propose to expand and commercialize our tracking technologies including teachable tracking state based tracking, motion energy tracking enhancement and track classification. The work product will be incorporated into our flagship product SVCell, and sold through our commercial partners including Nikon Corporation. The hypothesis is that our tracking software can be used for the accurate and robust analysis of a broad range of CNS applications, and scalable for the high throughput scoring of dynamic tracking characteristics with high speed, accuracy and reliability. To test this hypothesis, we set forth the following specific aims: Aim 1: Optimize the teachable tracking module for a broad range of tracking based phenotypes; Aim 2: Optimize and validate the high throughput scoring of tracking based phenotypes; Aim 3: Evaluate the product readiness of the SVCell tracking beta through field tests and scientific collaborations. This project is significant because technologies are needed which can flexibly screen a variety of tracking based, dynamic phenotypes at high throughput to support practical and effective CNS related scientific programs in basic research (e.g. phenotyping) and applied research (e.g. drug discovery). Analysis of these dynamic phenotypes in time-lapse microscopy movies could provide insights into CNS disease formation and enable earlier and more effective interventions. PUBLIC HEALTH RELEVANCE: Project Narrative Time-lapse microscopy image recognition can make a significant impact on the fight against neurological diseases and mental illness. By quantifying complex, dynamic phenotypes in the movies, it gives scientists a powerful tool with which to discover the basic mechanisms underlying important CNS functions, and then screen methods that act on them. This could enable earlier and more effective therapeutic interventions.