A brand-new study involving student-athletes exposes that an artificial intelligence computer system program, adept at processing magnetic resonance imaging (MRI), can effectively detect structural modifications in the brain due to reoccurring head injuries. According to researchers, this groundbreaking innovation might aid in the development of brand-new diagnostic tools to much better comprehend subtle brain injuries that accumulate over time.
While advanced MRI identifies microscopic modifications in brain structure that result from head trauma, scientists say the scans produce huge quantities of data that is hard to navigate.
The new study, which was recently published in The Neuroradiology Journal, involved hundreds of brain images from 36 contact-sport college athletes (mostly football players) and 45 noncontact-sport college professional athletes (mostly runners and baseball gamers). The work was suggested to plainly link changes discovered by the AI tool in the brain scans of football players to head impacts.
” Our findings reveal meaningful differences in between the brains of athletes who play contact sports compared to those who complete in noncontact sports,” said research study senior author and neuroradiologist Yvonne Lui, MD. “Since we expect these groups to have similar brain structure, these outcomes suggest that there might be a threat in selecting one sport over another,” adds Lui, a professor and vice chair for research study in the Department of Radiology at NYU Langone Health.
Lui includes that beyond spotting possible damage, the machine-learning technique utilized in their examination might also help experts to much better comprehend the underlying systems behind brain injury.
The brand-new study, which was just recently released in The Neuroradiology Journal, involved hundreds of brain images from 36 contact-sport college athletes (mostly football players) and 45 noncontact-sport college athletes (mostly runners and baseball players). The work was implied to clearly link changes found by the AI tool in the brain scans of football players to head impacts. It develops on a previous research study that had actually recognized brain-structure differences in football gamers, comparing those with and without concussions to athletes who competed in noncontact sports.
For the investigation, the scientists examined MRI scans from 81 male professional athletes taken between 2016 through 2018, none of whom had a recognized diagnosis of concussion within that time duration. Contact-sport athletes played football, lacrosse, and soccer, while noncontact-sport professional athletes participated in baseball, basketball, track and field, and cross-country.
As part of their analysis, the research study team developed statistical methods that provided their computer system program the capability to “learn” how to predict direct exposure to duplicated head impacts utilizing mathematical models. These were based upon information examples fed into them, with the program getting “smarter” as the quantity of training data grew.
The study group trained the program to recognize unusual features in brain tissue and compare athletes with and without duplicated direct exposure to head injuries based on these factors. They also ranked how beneficial each feature was for finding damage to help uncover which of the numerous MRI metrics may contribute most to diagnoses.
2 metrics most accurately flagged structural changes that resulted from a head injury, state the authors. The very first, suggest diffusivity, determines how easily water can move through brain tissue and is typically used to identify strokes on MRI scans. The second, mean kurtosis, analyzes the intricacy of brain-tissue structure and can show modifications in the parts of the brain included in learning, memory, and emotions.
” Our results highlight the power of synthetic intelligence to help us see things that we could not see in the past, especially invisible injuries that do not reveal up on traditional MRI scans,” stated study lead author Junbo Chen, MS, a doctoral prospect at NYU Tandon School of Engineering. “This technique might offer an important diagnostic tool not just for concussion but also for identifying the damage that comes from subtler and more regular head effects.”
Chen adds that the study team next strategies to check out making use of their machine-learning method for examining head injuries in female athletes.
Reference: “Identifying relevant diffusion MRI microstructure biomarkers associating with exposure to repeated head effects in contact sport athletes” by Junbo Chen, Sohae Chung, Tianhao Li, Els Fieremans, Dmitry S. Novikov, Yao Wang and Yvonne W. Lui, 22 May 2023, The Neuroradiology Journal.DOI: 10.1177/ 19714009231177396.
The study was funded by the National Institutes of Health and the U.S. Department of Defense.
An AI tool successfully finds subtle brain structure modifications triggered by repetitive head injuries in professional athletes, potentially enhancing diagnosis and understanding of such injuries in time.
A brand-new research study including student-athletes reveals that an expert system computer system program, adept at processing magnetic resonance imaging (MRI), can successfully spot structural modifications in the brain due to reoccurring head injuries. Such modifications were previously unnoticed by traditional medical imaging techniques like digital tomography (CT) scans. According to scientists, this revolutionary innovation might assist in the development of brand-new diagnostic tools to better understand subtle brain injuries that accumulate with time.
Specialists have long understood about the possible risks of concussion amongst young athletes, particularly for those who play high-contact sports such as football, hockey, and soccer. Evidence is now mounting that duplicated head impacts, even if they in the beginning appear moderate, may include up over numerous years and lead to cognitive loss. While advanced MRI determines microscopic changes in brain structure that arise from head trauma, scientists say the scans produce large amounts of information that is difficult to browse.
Led by researchers in the Department of Radiology at NYU Grossman School of Medicine, the brand-new study revealed for the very first time that the brand-new tool, using an AI technique called artificial intelligence, might properly distinguish between the brains of male athletes who played contact sports like football versus noncontact sports like track and field. The outcomes connected repetitive head impacts with small, structural modifications in the brains of contact-sport professional athletes who had not been diagnosed with a concussion.
