Researchers in Japan’s Okinawa Institute of Science and Technology (OIST) Graduate University have discovered a new technique to learn the human brain’s wiring using machine language to know the changes happening due to neurological or mental disorders.
Professor Kenji Doya, who leads the Neural Computation Unit at the Okinawa Institute of Science and Technology Graduate University (OIST) said, “working out how all the different brain regions are connected what we call the ‘connectome’ of the brain is vital to fully understand the brain and all the complex processes it carries out.”
To understand connectomes (map of neural connection), researchers track nerve cell fibers that extend throughout the brain. For animal experiments, scientists will inject a fluorescent tracer into multiple points in the brain and image where the nerve fibers originating from these points extend. This process needs examining hundreds of brain slices from many animals and as it is so invasive this method cannot be tried in humans.
The development of magnetic resonance imaging (MRI) has made it possible to understand the connectomes non-invasively. This technique is called diffusion MRI-based fiber tracking, it uses powerful magnetic fields to track signals from water molecules as they move or diffuse along nerve fibers.
A computer algorithm will use the water signals to estimate the path of the nerve fibers throughout the whole brain. But currently, the algorithms do not produce convincing results. Just like how photographs can look different depending on the camera settings, the parameters opted by scientists for these algorithms brings different outcomes.
Dr. Carlos Gutierrez, first author and a postdoctoral researcher in the OIST Neural Computation Unit said, “connectomes can be dominated by false positives, meaning they show neural connections that aren’t there. Furthermore, the algorithms struggle to detect nerve fibers that stretch between remote regions of the brain.”
In 2013, a Japanese government-led project called Brain/MINDS (Brain Mapping by Integrated Neurotechnology for Disease Studies) was started to map the brains of marmosets, a small monkey whose brains have a similar structure to human brains, by using both the non-invasive MRI imaging technique and the invasive fluorescent tracer technique.
The researchers in the current study have fine-tuned the most widely used parameters so that they would reliably detect long-range fibers. Instead of trying out all the different parameter combinations manually, the researchers turned to machine intelligence.
To determine the best parameters, the researchers used an algorithm. The fiber tracking algorithm calculated the connectome from the diffusion MRI data using parameters that changed or mutated in each successive generation. The parameters compete against each other and the best parameters generated connectomes that most closely matched the neural network detected by the fluorescent tracer proceeded to the next generation.
The researchers tested the algorithms using fluorescent tracer and MRI data from ten different marmoset brains. But choosing the best parameters wasn’t simple, even for machines.
Throughout the different level of this ‘survival-of-the-fittest’ process, the algorithms running for each brain exchanged their best parameters with each other, enabling the algorithms to settle on a more similar set of parameters. At the end of the process, the researchers took the best parameters and averaged them to create one shared set.
The striking difference between the images constructed by algorithms using the default and optimized parameters sends out a stark warning about MRI-based connectome research, the researchers said.
“Ultimately, diffusion MRI-based fiber tracking could be used to map the whole human brain and pinpoint the differences between healthy and diseased brains. This could bring us one step closer to learning how to treat these disorders,” said Dr. Gutierrez.