Advanced Search   
  Look in
       Title     Description
  Include
       Inactive Projects
 

 
Cell Tracking
Head: Mei Chen, Phil Campbell, Lee Weiss, and Takeo Kanade
Contact: SeungIl Huh
Mailing address:
Carnegie Mellon University
Robotics Institute
5000 Forbes Avenue
Pittsburgh, PA 15213

Non-RI center(s) / consortia:
Associated center(s) / consortia:
 Medical Robotics Technology Center (MRTC)
Associated lab(s) / group(s):
 Tissue Engineering
Project Homepage
This page last updated - February 2012.
Overview
Biological engineering applies knowledge about genomics, proteomics, and cellomics to develop new diagnostics and therapeutics for medicine. The high cost and long timelines for gathering and interpreting experimental data is a barrier to efficient exploration of the complex and high-dimensional design spaces of biological-based application systems. To overcome this barrier, researchers are relying more-and-more on high-throughput micro-array technologies to simultaneously conduct hundreds to thousands of individual experiments on a single test chip. However, studying cell responses to micro-array environments (cellomics) has been limited to either single endpoint measurements or tracking a relatively few, sparsely spaced cells over time.


Based on advances in optics and imaging systems, we are developing fully-automated computer vision-based cell tracking algorithms and a web-based system that overcomes these limitations. The system tracks whole populations of cells on a test chip in real-time (i.e., image analysis be completed for each frame prior to next frame, with images typically taken at intervals of 5 to 10 minutes), not only so that results are immediately available, but so that experiments can even be modified or terminated based on real-time feedback.


Researchers can upload cell images from their database to our file server, capture microscopic images of living cells in real time and upload them, or retrieve image analysis results to check their experiment progress. Once microscopy images are uploaded to the file server, the computing clusters run cell image analysis algorithms in parallel to process images and send output results to the file server. The file server stores all image files and processed results (segmentation mask, mitosis detection, tracking trajectories and cell metrics), which can be viewed in a local graphical user interface (GUI) or through our website. Biologists can check their experiments progress conveniently (e.g. from a mobile device with internet connection), without having to wait in their lab for hours.