Diseases and injuries can change the human body all the way down to the level of individual cells, and researchers have tapped AI to help them get a look at what those changes are.
Specifically, a multi-institute team has developed an imaging tool, dubbed TDAExplore, that uses topology and AI to study how cells alter during illness and where in the cell changes are happening, said Eric Vitriol, PhD, cell biologist and neuroscientist at the Medical College of Georgia, in a statement.
“We think this is exciting progress into using computers to give us new information about how image sets are different from each other,” Vitriol explained. “What are the actual biological changes that are happening, including ones that I might not be able to see, because they are too minute, or because I have some kind of bias about where I should be looking.”
AI, of course, can process much more data much more quickly than humans, and computer vision, which allows computers to pull information from digital images, is a type of machine learning that has been around for decades.
According to Vitriol, topology is “perfect” for image analysis because images consist of patterns, of objects arranged in space, and topological data analysis (the TDA in TDAExplore) helps the computer also recognize the lay of the land, in this case where actin — a protein and essential building block of the fibers, or filaments, that help give cells shape and movement — has moved or changed density.
Before they could proceed too far, however, the researchers needed to first gain insights into what is normal and what happens in disease states. The challenge there, noted Vitriol, is while patterns emerged to indicate where actin is and how it’s organized, manually analyzing images is time-consuming and scientists could carry their own bias.
“How do I know that when I decide what’s different that it’s the most different thing or is that just what I wanted to see?” Vitriol asked. “We want to bring computer objectivity to it and we want to bring a higher degree of pattern recognition into the analysis of images. A lot of my job is trying to find patterns in images that are hard to see. Because I need to identify those patterns so I can find some way to get numbers out of those images.”
Some machine learning models require hundreds of images to train and classify images, the team noted. Their new system needs only a few high-resolution images to operate. The ability to get more data from images leads to higher accuracy, including recognizing changes in diseases and, ideally, improving patient outcomes.
For AI to produce the best results, researchers coupled the technology with topology, providing image statistics through data analysis.
Photo by wildpixel/Getty Images