Using Machine Learning, Researchers Can “See” How The Brain Responds To Various Scenarios

The strength of synapses, the connectors that allow nerve cells in the brain to communicate with one another, can fluctuate over time. Johns Hopkins University researchers have developed a method to see and track these changes in living animals. Researchers should be better able to comprehend how learning, ageing, injury, and disease influence these connections in human brains thanks to the technology described in Nature Methods.

According to Dwight Bergles, Ph.D., the Diana Sylvestre and Charles Homcy Professor in the Solomon H. Snyder Department of Neuroscience at the Johns Hopkins University (JHU) School of Medicine, “if you want to learn more about how an orchestra plays, you have to watch individual players over time.

The study’s co-authors included Richard Huganir, Ph.D., a Bloomberg Distinguished Professor at Johns Hopkins University and the head of the Solomon H. Snyder Department of Neuroscience, as well as Adam Charles, Ph.D., M.E., and Jeremias Sulam, Ph.D., all assistant professors in the department of biomedical engineering. The Kavli Neuroscience Discovery Institute at Johns Hopkins University houses all four of the researchers.

Synaptic junctions (also known as “junctions”) are where nerve cells exchange chemical messengers to transmit information. According to the authors, learning new abilities and being exposed to new settings are only two examples of how varied life events may alter synapses in the brain, either increasing or weakening the connections that allow for learning and memory. Although it is a difficult task, understanding how these little changes take place across the trillions of synapses in our brains is essential to understanding how the brain functions normally and how sickness affects it.

The high density of synapses in the brain and their small size—characteristics that make them extremely difficult to visualise even with new state-of-the-art microscopes—have forced scientists to search for better ways to visualise the shifting chemistry of synaptic messaging.

According to Charles, we had to start with difficult, hazy, and noisy imaging data in order to recover the signal sections we needed to observe.

Bergles, Sulam, Charles, Huganir, and their coworkers utilised machine learning, a foundation for computing that enables flexible development of automatic data processing tools, to achieve this. The scientists used machine learning to improve the quality of images made up of thousands of synapses because it has been successfully used in numerous fields spanning biomedical imaging. The system must first be “trained,” showing the algorithm what high-quality photos of synapses should look like, in order for it to be a powerful tool for automated detection that can outperform human speeds.

In these studies, the researchers used genetically modified mice whose synapses’ chemical sensors, glutamate receptors, fluoresced green when exposed to light. Since each receptor in these mice produces the same amount of light, the quantity of fluorescence produced by a synapse is a measure of the strength and number of synapses present.

As was to be predicted, imaging in the intact brain provided poor-quality images that made it difficult to discern individual clusters of glutamate receptors at synapses, let alone to individually detect and track them over time. The researchers used photos of brain slices (ex vivo) from the same kind of genetically altered animals to train a machine learning algorithm to transform these into higher-quality images. Because these photos weren’t taken from living animals, it was possible to create both low-quality photographs that were comparable to those acquired from live animals and considerably higher-quality images using a different microscopy approach.

The team was able to create an enhancement algorithm that can generate higher resolution photos from lower quality ones, much like the images they collected from living mice, thanks to their cross-modality data gathering system. By doing this, data obtained from the intact brain can be much improved, allowing for the detection and tracking of individual synapses (numbering in the thousands) over the course of multiday trials.

The researchers next employed microscopy to repeatedly capture photos of the same synapses in mice over a period of weeks in order to track changes in receptors over time in living animals. The animals spent a single five-minute session in a chamber with novel sights, odours, and tactile stimulation after baseline photos were taken. The amount of glutamate receptors at synapses was then measured by imaging the same region of the brain every other day to determine whether and how the new stimuli had changed it.

Although the primary goal of the research was to create a set of techniques for analysing synapse level changes in a variety of contexts, the team discovered that this minor environmental change led to a spectrum of fluorescence changes in synapses in the cerebral cortex, indicating connections where the strength increased and others where it decreased, with a bias towards strengthening in animals exposed to the novel environment.

The investigations were made possible by close cooperation among scientists who ordinarily don’t work closely together but have specialised in fields ranging from molecular biology to artificial intelligence. However, according to Bergles, such cooperation is encouraged at the multidisciplinary Kavli Neuroscience Discovery Institute. The technology could potentially provide fresh insight into synaptic alterations that take place in different illness and injury scenarios, according to the researchers, who are already employing it to study synaptic changes in animal models of Alzheimer’s disease.