Scientists around the world are working on mapping out the neural connections found within the brains of animals, hopefully one day leading to a complete “connectome” of the giant human brain. It is believed that once maps of healthy brains can be compared to those troubled by disease, we should have a much better understanding of what causes some ailments and how to treat them. To this end researchers at MIT have been working on getting computers to analyze digital scans of brain slices and intelligently trace observed connections within. Because it is difficult to actually teach a machine to do this, the team is utilizing computer learning to first demonstrate how humans trace connections and then have the computer imitate the same process on different slices.
With machine learning, the researchers teach computers to learn by example. They feed their computer electron micrographs as well as human tracings of these images. The computer then searches for an algorithm that allows it to imitate human performance.
After the computer is trained on the human tracings, it is applied to electron micrographs that have not been traced by humans. This new technique represents the first time that computers have been effectively taught to segment any kind of images, not just neurons.
Jain and Turaga [Viren Jain and Srinivas Turaga, computational neuroscience postdocs] have also invented new ways of evaluating how well the computer imitates humans at the task of tracing. Those measures are crucial for machine learning because the computer, just like students in a class, will not learn the desired task well unless the “exam” properly measures performance.
In their early efforts, it took the computer weeks or even months to come up with an accurate neuron-tracing algorithm. However, Jain and Turaga cut that time dramatically when they started using computers equipped with graphics processing cards, allowing them to perform computations 50 to 100 times faster. Now, it takes only days for their computer programs to produce a new tracing algorithm.
Their eventual goal is to use computers to process the bulk of the images needed to create connectomes, but they expect that humans will still need to proofread the computers’ work.
More from MIT: Mapping the brain…
Image credit: Chris Nurse, Wellcome Images