Summary: Researchers have used artificial intelligence (AI) to track and visualize changes in synapse strength in live animals. Synapses are the communication points of the brain, crucial for the processes of learning, memory and aging.
Using machine learning, the scientists improved image quality, allowing for the detection and tracking of individual synapses over time. This advance may offer critical insights into how the brain is affected by aging, disease or injury.
Main aspects:
- The technique uses artificial intelligence to track changes in the strength of synapses, the point at which nerve cells communicate, in live animals.
- The study implemented machine learning to improve the quality of images made up of thousands of synapses, allowing for individual detection and tracking over time.
- This innovative technique will help understand how synapse connections in the human brain change with learning, ageing, injury and disease.
Source: Johns Hopkins medicine
Johns Hopkins scientists have developed a method involving artificial intelligence to visualize and track changes in the strength of synapses, the connection points through which nerve cells in the brain communicate in live animals.
The technique, described inMethods of natureit should lead, the scientists say, to a better understanding of how those connections in the human brain change with learning, aging, injury and disease.
If you want to learn more about how an orchestra plays, you have to observe individual musicians over time, and this new method does that for synapses in the brains of living animals, say Dwight Bergles, Ph.D., Diana Sylvestre and Charles Homcy Professor in the Solomon H. Snyder Department of Neuroscience at the Johns Hopkins University (JHU) School of Medicine.
Bergles co-authored the study with colleagues Adam Charles, Ph.D., ME and Jeremias Sulam, Ph.D., both assistant professors in the department of biomedical engineering, and Richard Huganir, Ph.D., Bloomberg Distinguished Professor at JHU and Director of the Solomon H. Snyder Department of Neuroscience. All four researchers are members of the Johns Hopkins Kavli Neuroscience Discovery Institute.
Nerve cells transfer information from one cell to another by exchanging chemical messages at synapses (junctions). In the brain, the authors explain, different life experiences, such as exposure to new environments and learning skills, are thought to induce changes in the synapses, strengthening or weakening these connections to enable learning and memory.
Understanding how these tiny changes occur across the trillions of synapses in our brains is a daunting challenge, but it’s crucial to discovering how the brain works when it’s healthy and how it’s altered by disease.
To determine which synapses change during a particular life event, scientists have long searched for better ways to visualize the changing chemistry of synaptic messaging, necessitated by the high density of synapses in the brain and their small tract sizes that make them extremely difficult to visualize even with new state-of-the-art microscopes.
We had to go through challenging, blurry and noisy imaging data to extract the portions of the signal we need to see, says Charles.
To do so, Bergles, Sulam, Charles, Huganir and their colleagues turned to machine learning, a computational framework that allows for the flexible development of automatic data processing tools.
Machine learning has been successfully applied to many domains of biomedical imaging and, in this case, scientists have exploited the approach to improve the quality of images composed of thousands of synapses.
While it can be a powerful tool for automatic detection, far exceeding human speed, the system must first be trained, teaching the algorithm what high-quality images of synapses should look like.
In these experiments, the researchers worked with genetically engineered mice in which glutamate receptors, the chemical sensors in synapses, glowed green (fluorescent) when exposed to light.
Since each receptor emits the same amount of light, the amount of fluorescence generated by a synapse in these mice is an indication of the number of synapses and thus their strength.
As expected, imaging in the intact brain produced low-quality images in which individual clusters of glutamate receptors at synapses were difficult to see clearly, let alone detect individually and track over time.
To convert them into higher quality images, the scientists trained a machine learning algorithm with images taken of (ex vivo) brain slices derived from the same type of genetically engineered mice.
Since these images were not from live animals, much higher quality images could be produced using a different microscopy technique, as well as low quality images similar to those taken with live animals of the same views.
This multimodal data collection framework enabled the team to develop an enhancement algorithm that can produce higher resolution images from low-quality images, similar to images collected from live mice.
In this way, the data collected from the intact brain can be significantly enhanced and able to detect and track single synapses (by the thousands) during multi-day experiments.
To follow changes in the receptors over time in live mice, the researchers then used microscopy to take repeated images of the same synapses in the mice over several weeks. After acquiring baseline images, the team placed the animals in a chamber with new sights, smells and tactile stimulation for a single five-minute period.
They then imaged the same area of the brain every other day to see if and how the new stimuli had affected the number of glutamate receptors in the synapses.
Although the goal of the work was to develop a variety of methods to analyze changes in synapse level in many different contexts, the researchers found that this simple change in environment caused a spectrum of changes in fluorescence across synapses in the cortex cerebral, indicating connections in which the force increased and others in which it decreased, with a propensity towards strengthening in animals exposed to the new environment.
The studies were made possible through close collaboration between scientists with distinct expertise, ranging from molecular biology to artificial intelligence, who do not normally work closely together. But such collaboration is encouraged at the interdisciplinary Kavli Neuroscience Discovery Institute, says Bergles.
The researchers are now using this machine learning approach to study synaptic changes in animal models of Alzheimer’s disease and believe the method could shed new light on synaptic changes that occur in other disease and injury settings.
We’re really excited to see how and where the rest of the scientific community takes this, Sulam says.
Financing: The experiments in this study were conducted by Yu Kang Xu (a doctoral student and member of the Kavli Neuroscience Discovery Institute at JHU), Austin Graves, Ph.D. (research assistant professor of biomedical engineering at JHU), and Gabrielle Coste ( PhD candidate in neuroscience at JHU). This research was funded by the National Institutes of Health (RO1 RF1MH121539).
Learn about this news about AI and neuroscience research
Author: Vanessa Wasta
Source: Johns Hopkins medicine
Contact: Vanessa Wasta – Johns Hopkins Medicine
Image: The image is credited to Neuroscience News
Original research: Free access.
“Cross-Mode Supervised Image Restoration Enables Nanoscale Monitoring of Synaptic Plasticity in Living Mice” by Dwight Bergles et al. Methods of nature
Abstract
Cross-mode supervised imaging restoration enables nanoscale monitoring of synaptic plasticity in live mice
Learning is thought to involve changes in glutamate receptors at synapses, submicron structures that mediate communication between neurons in the central nervous system.
Due to their small size and high density, synapses are difficult to resolve in vivo, limiting our ability to directly relate receptor dynamics to animal behavior. Here we have developed a combination of computational and biological methods to overcome these challenges.
First, we trained a deep learning image restoration algorithm that combines the benefits of ex vivo super resolution and in vivo imaging modalities to overcome the specific limitations of each optical system.
When applied to in vivo images of transgenic mice expressing fluorescently labeled glutamate receptors, this recovery algorithm super-resolved synapses, enabling behavior-associated synaptic plasticity to be monitored with high spatial resolution.
This method demonstrates the capabilities of image enhancement to learn from ex vivo data and imaging techniques to enhance the resolution of in vivo imaging.
#Visualizing #Strength #Brain #Synapses #Artificial #Intelligence #Neuroscience #News
