Johns Hopkins University researchers have developed a technique that uses artificial intelligence to visualize and track changes in the strength of synapses, the connections that allow nerve cells in the brain to communicate with each other in living animals. The method, help researchers better understand how learning, aging, injury and disease affect these connections in human brains.
“If you want to learn more about how an orchestra plays, you have to track individual players over time, and this new method does that for synapses in the brains of living animals,” says Dwight Bergles, Ph.D., Diana Sylvestre. and Charles Homcy Professor in the Solomon H. Snyder Institute of Neuroscience at the Johns Hopkins University (JHU) School of Medicine.
Nerve cells transmit information from one cell to another by exchanging chemical messages at synapses (“connections”). In the brain, the authors explain, various life experiences, such as exposure to new environments and learning skills, are thought to induce changes in synapses, strengthening or weakening these connections to enable learning and memory.
Understanding how these tiny changes occur in the trillions of synapses in our brain is a daunting challenge, but it is crucial to uncovering how the brain works when it is healthy and how it is altered by disease.
The high density of synapses in the brain
To determine which synapses change during a particular life event, scientists have long sought better ways to visualize the changing chemistry of synaptic messages, which is required by the high density of synapses in the brain and their small size properties that make them extremely difficult to visualize. with new state-of-the-art microscopes.
“We needed to move from difficult, blurry, noisy image data to extracting the parts of the signal we need to see,” says Charles.
To that end, Bergles, Sulam, Charles, Huganir and their colleagues turned to machine learning, a computational framework that enables the flexible development of tools for automatic data processing. Machine learning has been successfully applied to many domains across biomedical imaging, researchers used the approach to enhance the quality of images composed of thousands of synapses. Although this can be a powerful tool for automated detection that greatly exceeds human speeds.
Researchers worked with genetically engineered mice
In these experiments, the researchers worked with genetically engineered mice in which glutamate receptors chemical sensors at synapses glow green (fluoresce) when exposed to light. Because each receptor emits the same amount of light, the amount of fluorescence generated by a synapse in these mice is an indicator of the number of synapses and thus their strength.
As expected, imaging in the intact brain produced low-quality images in which it was difficult to clearly see individual clusters of glutamate receptors at synapses, let alone detect them individually and track them over time. To convert them into higher quality images, the researchers trained a machine learning algorithm with images taken from brain slices (ex vivo) from the same type of genetically altered mice.
Because these images were not from live animals, it was possible to create much higher-quality images using a different microscopic technique, as well as low-quality images similar to those taken from live animals with the same views.
This cross-modality data collection framework allowed the team to develop an enhancement algorithm that can create higher-resolution images from low-quality ones, similar to images collected from live mice. In this way, data collected from the intact brain can be greatly enhanced and able to detect and track individual synapses (in the thousands) over the course of multi-day experiments.
Read Now:BBC has to file revised IT returns for understating income by ₹40 crore
