Researchers at the Indian Institute of Sciences (IISc) discovered a new Graphic Processing Unit (GPU) based machine learning algorithm which helps scientists in understanding and predicting connectivity between different regions of the brain in a better way.
The algorithm named Regularized, Accelerated, Linear Fascicle Evaluation, or ReAl-LiFE can rapidly analyse the enormous amounts of data generated from diffusion Magnetic Resonance Imaging (dMRI) scans of the human brain, as stated in a report by PTI.
As per the IISc press release issued on Monday, June 27, the team could evaluate dMRI data over 150 times faster than the existing state-of-the-art algorithms using ReAL-LiFE.
The Associate Professor at the Centre for Neuroscience (CNS), IISc, and corresponding author of the study published in the journal Nature Computational Science, Devarajan Sridharan said, "Tasks that previously took hours to days can be completed within seconds to minutes."
A PhD student at CNS and first author of the study, Varsha Sreenivasan, said, "Millions of neurons fire in the brain every second, generating electrical pulses that travel across neuronal networks from one point in the brain to another through connecting cables or axons."
These connections are essential for computations that the brain performs. Understanding brain connectivity is critical in uncovering brain-behaviour relationships at scale, she added.
It is said, "Conventional approaches to study brain connectivity typically use animal models, and are invasive. The dMRI scans, on the other hand, provide a non-invasive method to study brain connectivity in humans."
"The cables (axons) that connect different areas of the brain are its information highways. Because bundles of axons are shaped like tubes, water molecules move through them, along their length, in a directed manner."
The dMRI allows scientists to track this movement, in order to create a comprehensive map of the network of fibres across the brain, called a connectome. Unfortunately, it is not straightforward to pinpoint these connectomes. The data obtained from the scans only provide the net flow of water molecules at each point in the brain, the release noted.
Scientists had previously developed an algorithm called LiFE (Linear Fascicle Evaluation) to carry out this optimisation, but one of its challenges was that it worked on traditional Central Processing Units (CPUs), which made the computation time-consuming, as stated in a report by PTI.
Sridharan's team in a new study, tweaked their algorithm to cut down the computational effort involved in several ways, including removing redundant connections, thereby, improving LiFE's performance significantly, as stated in a report by PTI.
In order to speed up the algorithm, the team redesigned to work on specialised electronic chips, the kind found in high-end gaming computers called Graphics Processing Units (GPUs) which helped them in analysing data at speeds 100-150 times faster than previous ones.
Along with this, this algorithm, ReAL-LiEF was able to predict how a human test subject would behave or carry out a specific task by using connection strengths estimated for each individual. With this, the team was able to explain variations in behavioural and cognitive test scores across a group of 200 participants. Similarly, there can be medical applications too.
Sreenivasan further shared, "Data processing on large scales is becoming increasingly necessary for big-data neuroscience applications, especially for understanding healthy brain function and brain pathology. Giving an instance she says that by using the obtained connectomes, the team hopes to be able to identify early signs of aging or deterioration of brain function before they manifest behaviourally in Alzheimer's patients. The associate professor, Sridharan said, "In another study, we found that a previous version of ReAL-LiFE could do better than other competing algorithms for distinguishing patients with Alzheimer's disease from healthy controls."
"GPU-based implementation is very general, and can be used to tackle optimisation problems in many other fields as well," he adds.
