课题基金 / 基金详情

Automated video analysis of immune cell activation and microvascular blood flow in the inflamed microcirculation

Automated video analysis of immune cell activation and microvascular blood flow in the inflamed microcirculation
自动视频分析发炎微循环中的免疫细胞激活和微血管血流
批准号:
491559-2015
负责人:
Trappenberg, Thomas
金额:
$1.82万
依托单位:
依托单位国家:
加拿大
项目类别:
Engage Grants Program
财政年份:
2015
资助国家:
加拿大
项目状态:
已结题
起止时间:
2015-01-01 至 2016-12-31

项目摘要

项目成果

Trappenberg, Thomas的其他基金

相似基金

相关文献

中文摘要
翻译
血流的特征已被证明是炎症状况的良好指标。帕纳格 制药公司正在通过研究合成大麻素对炎症的影响来开发抗炎药。 试验动物的血流量。这一发展的一个主要瓶颈是血流的定量分析 这些实验的视频。我们建议在这里开发一个基于现代机器的自动化系统 学习方法 我们将测试两种方法。一个将基于运动分割和利用以前开发的 用于显微血液分析的过滤器然后使用深度卷积分析这些数据, 网络.对于第二种方法,我们将尝试直接在时态数据上训练深度网络。这样的 预计网络将比前者更复杂。因此,训练这种网络更加困难, 因此,我们将使用预训练技术,包括无监督技术以及模拟数据。 为了生成模拟数据,我们将开发一个独特的数据模拟器,可以产生各种流量 特色 到目前为止,深度网络主要应用于静态图像中的对象识别,并且正在开发深度网络。 网络视频处理是一个很有前途的研究方向。视频分析自动化系统 可以大大加快Panag Pharma实验系统的实验过程和分析。这 将使Panag Pharma Inc.在这个发展空间的尖端优势,并可能打开一个场地, 新的发展。
英文摘要
The characteristic of blood flow has been shown to be a good indicator of inflammatory conditions. Panag Pharma Inc is developing anti-inflammatory agents by studying the effects of synthetic cannabinoids on the blood flow of test animals.. A major bottleneck for this development is the quantitative analysis of blood flow videos from these experiments. We propose here to develop an automated system based on modern machine learning methods. We will test two approaches. One will be based on motion segmentation and leveraging previously developed filters from my lab for microscopic blood analysis. These data are then analyzed with deep convolutional networks. For the second method we will attempt to train a deep network directly on the temporal data. Such a network is expected to be more complex than the former. Training such networks is hence more difficult, and we will therefore use pre-training techniques including unsupervised techniques as well as with simulated data. To generate the simulated data we will develop a unique data simulator that can produce various flow characteristics. Deep networks have so far mainly been applied to object recognition in still images, and developing deep networks for video processing is a promising research direction. An automated system for the video analysis can speed up the experimental process and analysis of Panag Pharma's experimental system considerable. This would give Panag Pharma Inc. a cutting edge advantage in this development space and could open a venue for new developments.
期刊论文(0)
专著(0)
科研奖励(0)
会议论文
Deep learning with limited data
  • 批准号:
    RGPIN-2017-05117
  • 项目类别:
    Discovery Grants Program - Individual
  • 资助金额:
    $3.79万
  • 财政年份:
    2021
  • 负责人:
    Trappenberg, Thomas
  • 依托单位:
Deep learning with limited data
  • 批准号:
    RGPIN-2017-05117
  • 项目类别:
    Discovery Grants Program - Individual
  • 资助金额:
    $1.89万
  • 财政年份:
    2020
  • 负责人:
    Trappenberg, Thomas
  • 依托单位:
Deep learning with limited data
  • 批准号:
    RGPIN-2017-05117
  • 项目类别:
    Discovery Grants Program - Individual
  • 资助金额:
    $1.89万
  • 财政年份:
    2019
  • 负责人:
    Trappenberg, Thomas
  • 依托单位:
Deep learning with limited data
  • 批准号:
    RGPIN-2017-05117
  • 项目类别:
    Discovery Grants Program - Individual
  • 资助金额:
    $1.89万
  • 财政年份:
    2018
  • 负责人:
    Trappenberg, Thomas
  • 依托单位:
海外基金