In a groundbreaking development, scientists have introduced a cutting-edge non-invasive movement tracking method known as GlowTrack. This innovative technique utilizes fluorescent dye markers to train artificial intelligence (AI) systems for capturing the intricacies of movement, ranging from the digit of a single mouse to the complexity of the human hand. The implications of GlowTrack extend across diverse fields, including biology, robotics, medicine, and beyond. Movement serves as a window into understanding how the brain functions and controls the body, making this breakthrough technology invaluable.
The evolution of movement tracking
The journey of tracking human and animal movement has evolved significantly, progressing from manual clipboard-and-pen observations to modern AI-based methods. The current state-of-the-art techniques leverage artificial intelligence to automatically monitor the movement of various body parts. However, these methods still entail time-intensive processes, requiring researchers to manually mark each body part hundreds to thousands of times.
Associate Professor Eiman Azim and his team have developed GlowTrack, a non-invasive movement tracking method that leverages fluorescent dye markers to train AI systems. What sets GlowTrack apart is its robustness, efficiency, and high-definition capabilities. It can track a single digit on a mouse’s paw with precision or monitor hundreds of landmarks on a human hand. This groundbreaking technique, detailed in a recent publication in Nature Communications (September 26, 2023), holds the potential to revolutionize multiple fields, from biology and robotics to medicine and more.
Eiman Azim, the senior author of the study and holder of the William Scandling Developmental Chair, remarked, “Over the last several years, there has been a revolution in tracking behavior as powerful artificial intelligence tools have been brought into the laboratory. Our approach makes these tools more versatile, improving the ways we capture diverse movements in the laboratory. Better quantification of movement gives us better insight into how the brain controls behavior and could aid in the study of movement disorders like amyotrophic lateral sclerosis (ALS) and Parkinson’s disease.”
Overcoming limitations: The power of fluorescent dye markers
Conventional methods for tracking animal movement involve manual and repetitive marking of body parts on a computer screen, a time-consuming process prone to human error and limited by time constraints. Human annotation restricts these methods to narrow testing environments, as AI models specialize based on the limited training data they receive. Any change in factors such as lighting, body orientation, camera angle, or other variables renders the model incapable of recognizing the tracked body part.
To address these limitations, the researchers turned to fluorescent dye markers to label parts of animals or human bodies. These “invisible” markers, when employed, generate visually diverse data rapidly, eliminating the need for human annotation. Once fed this robust data, AI models can track movements across a broader range of environments and achieve a level of resolution that would be exceedingly difficult to attain through manual human labeling.
Fostering collaboration and reproducibility
GlowTrack’s introduction paves the way for simplified comparisons of movement data across various studies, as different laboratories can employ the same models to track body movement in diverse situations. Eiman Azim emphasized the significance of comparison and reproducibility in scientific discovery. “Fluorescent dye markers were the perfect solution,” stated Daniel Butler, the first author of the study and a Salk bioinformatics analyst. He likened these markers to “invisible ink on a dollar bill that lights up only when you want it to, allowing us to generate a massive amount of training data.”
Future possibilities and collaborations
In the future, the research team envisions supporting a wide array of applications for GlowTrack. They aim to combine its capabilities with other tracking tools that can reconstruct movements in three dimensions. Additionally, they plan to explore analytical approaches for uncovering patterns within the extensive movement datasets generated by this revolutionary method.
Eiman Azim expressed enthusiasm about the potential impact of their approach, stating, “Our approach can benefit a host of fields that need more sensitive, reliable, and comprehensive tools to capture and quantify movement. I am eager to see how other scientists and non-scientists adopt these methods, and what unique, unforeseen applications might arise.”
Acknowledgments and support
The research was made possible through the support of various entities, including the UC San Diego CMG Training Program, a Jesse and Caryl Philips Foundation Award, the National Institutes of Health (R00NS088193, DP2NS105555, R01NS111479, RF1NS128898, and U19NS112959), the Searle Scholars Program, the Pew Charitable Trusts, and the McKnight Foundation.
With GlowTrack’s emergence, the scientific community and beyond eagerly anticipate the transformative potential this technology holds for understanding and harnessing the power of movement in various fields.
