Fluorescence imaging analysis software tools for high throughput automated workflow solution in digital pathology

用于数字病理学高通量自动化工作流程解决方案的荧光成像分析软件工具

• 批准号: 515553-2017
• 负责人: Plataniotis, Konstantinos
• 金额: $ 6.12万
• 依托单位: University of Toronto
• 依托单位国家: 加拿大
• 项目类别: Collaborative Research and Development Grants
• 财政年份: 2017
• 资助国家: 加拿大
• 起止时间: 2017-01-01 至 2018-12-31
• 项目状态: 已结题
• 来源: https://www.nserc-crsng.gc.ca/ase-oro/Details-Detailles_eng.asp?id=618713
• 关键词: Fluorescence; imaging; analysis; software; tools

In collaboration with Huron Digital Pathology Inc., of Waterloo, Ontario, the University of Toronto (UofT)team aims to develop an innovative image processing framework for the custom-tailored fluorescence imagingworkflow of Huron's next generation TissueScope. Using tools from signal & image processing, computervision, and machine learning, the applicants plan to research, develop, and test new, cutting-edge fluorescenceimaging algorithmic solutions.Despite effective utilization of existing virtual microscopes, the goal of delivering a fully integrated, scalable,certified for clinical use, digital pathology framework has not yet materialized. According to early adopters ofintegrated digital pathology the main reason for the delay is the lack of progress in integrating the digitalscanners with advanced image processing modules. The delay is attributed to hardware related issues, such asthose pertinent to the automation of the image acquisition process, and software related issues such as the useof proprietary protocols in the processing pipeline which result in a diverse set of image navigation, contrastcorrection, spectral mapping and enhancement, segmentation, and information retrieval solutions.The proposed framework will greatly decrease the time and computational complexity of the image acquisitionand scanning process while improving accuracy and reliability, and enhancing the end-user experience.

与休伦数字病理学公司合作，位于安大略滑铁卢的Huron公司，多伦多大学（UofT）团队旨在为Huron公司下一代组织镜的定制荧光成像工作流程开发一种创新的图像处理框架。申请人计划使用信号和图像处理、计算机视觉和机器学习等工具，研究、开发和测试新的尖端荧光成像算法解决方案。尽管有效利用了现有的虚拟显微镜，但提供完全集成的、可扩展的、经过临床认证的数字病理学框架的目标尚未实现。据早期采用集成数字病理学的主要原因是延迟的数字扫描仪与先进的图像处理模块集成缺乏进展.延迟归因于硬件相关问题，诸如与图像采集过程的自动化相关的问题，以及软件相关问题，诸如在处理流水线中使用专有协议，其导致图像导航、对比度校正、光谱映射和增强、分割、和信息检索解决方案。所提出的框架将大大减少图像采集和扫描过程的时间和计算复杂度，同时提高准确性和可靠性，并增强最终用户体验。