Carnegie Mellon Technique Accelerates Biological Image Analysis

Carnegie Mellon University Lane Center for Computational Biology researchers have improved an algorithm that automatically analyzes cell cultures and biological specimens. The new technique improves the efficiency of the belief propagation algorithm, a widely used method for drawing conclusions about interconnected networks and promises to allow for more accurate analysis of microscopic images created by high-speed and high-tech biological screening methods. CMU professor Geoffrey Gordon says current automated screening systems that examine cell cultures look at individual cells and do not fully consider the relationships between cells, largely because examining multiple cells simultaneously requires impractical amounts of computing time. CMU researchers were able to expand the focus from a single cell to multiple cells by increasing the efficiency of the belief propagation algorithm. The algorithm enables a computer to make inferences about a set of data by drawing from multiple sources of information. With biological specimens, the algorithm can be used to see which parts of the image are individual cells or whether the distributions of particular proteins within each cell are abnormal. However, as the number of variables increases, the belief propagation algorithm can become unwieldy, requiring excessive computing time. By improving the performance of the algorithm, the researchers say it can be applied to challenges such as text analysis, Web analysis, and medical diagnosis.
Click Here to View Full Article

Leave a Reply

Fill in your details below or click an icon to log in: Logo

You are commenting using your account. Log Out /  Change )

Google photo

You are commenting using your Google account. Log Out /  Change )

Twitter picture

You are commenting using your Twitter account. Log Out /  Change )

Facebook photo

You are commenting using your Facebook account. Log Out /  Change )

Connecting to %s

%d bloggers like this: