MSGID: 1:317/3 6476cdbd   
   PID: hpt/lnx 1.9.0-cur 2019-01-08   
   TID: hpt/lnx 1.9.0-cur 2019-01-08   
    New tool may help spot 'invisible' brain damage in college athletes   
      
      
     Date:   
         May 30, 2023   
     Source:   
         NYU Langone Health / NYU Grossman School of Medicine   
     Summary:   
         An artificial intelligence computer program that processes magnetic   
         resonance imaging (MRI) can accurately identify changes in brain   
         structure that result from repeated head injury, a new study in   
         student athletes shows. These variations have not been captured by   
         other traditional medical images such as computerized tomography   
         (CT) scans.   
      
         The new technology, researchers say, may help design new diagnostic   
         tools to better understand subtle brain injuries that accumulate   
         over time.   
      
      
         Facebook Twitter Pinterest LinkedIN Email   
      
   ==========================================================================   
   FULL STORY   
   ==========================================================================   
   An artificial intelligence computer program that processes magnetic   
   resonance imaging (MRI) can accurately identify changes in brain structure   
   that result from repeated head injury, a new study in student athletes   
   shows. These variations have not been captured by other traditional   
   medical images such as computerized tomography (CT) scans. The new   
   technology, researchers say, may help design new diagnostic tools to   
   better understand subtle brain injuries that accumulate over time.   
      
   Experts have long known about potential risks of concussion among young   
   athletes, particularly for those who play high-contact sports such as   
   football, hockey, and soccer. Evidence is now mounting that repeated head   
   impacts, even if they at first appear mild, may add up over many years   
   and lead to cognitive loss. While advanced MRI identifies microscopic   
   changes in brain structure that result from head trauma, researchers   
   say the scans produce vast amounts of data that is difficult to navigate.   
      
   Led by researchers in the Department of Radiology at NYU Grossman   
   School of Medicine, the new study showed for the first time that the new   
   tool, using an AI technique called machine learning, could accurately   
   distinguish between the brains of male athletes who played contact sports   
   like football versus noncontact sports like track and field. The results   
   linked repeated head impacts with tiny, structural changes in the brains   
   of contact-sport athletes who had not been diagnosed with a concussion.   
      
   "Our findings uncover meaningful differences between the brains of   
   athletes who play contact sports compared to those who compete in   
   noncontact sports," said study senior author and neuroradiologist Yvonne   
   Lui, MD. "Since we expect these groups to have similar brain structure,   
   these results suggest that there may be a risk in choosing one sport   
   over another," adds Lui, a professor and vice chair for research in the   
   Department of Radiology at NYU Langone Health.   
      
   Lui adds that beyond spotting potential damage, the machine-learning   
   technique used in their investigation may also help experts to better   
   understand the underlying mechanisms behind brain injury.   
      
   The new study, which published online May 22 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 meant   
   to clearly link changes detected by the AI tool in the brain scans of   
   football players to head impacts.   
      
   It builds on a previous study that had identified brain-structure   
   differences in football players, comparing those with and without   
   concussions to athletes who competed in noncontact sports.   
      
   For the investigation, the researchers analyzed MRI scans from 81 male   
   athletes taken between 2016 through 2018, none of whom had a known   
   diagnosis of concussion within that time period. Contact-sport athletes   
   played football, lacrosse, and soccer, while noncontact-sport athletes   
   participated in baseball, basketball, track and field, and cross-country.   
      
   As part of their analysis, the research team designed statistical   
   techniques that gave their computer program the ability to "learn"   
   how to predict exposure to repeated head impacts using mathematical   
   models. These were based on data examples fed into them, with the program   
   getting "smarter" as the amount of training data grew.   
      
   The study team trained the program to identify unusual features in   
   brain tissue and distinguish between athletes with and without repeated   
   exposure to head injuries based on these factors. They also ranked how   
   useful each feature was for detecting damage to help uncover which of   
   the many MRI metrics might contribute most to diagnoses.   
      
   Two metrics most accurately flagged structural changes that resulted   
   from head injury, say the authors. The first, mean diffusivity, measures   
   how easily water can move through brain tissue and is often used to spot   
   strokes on MRI scans.   
      
   The second, mean kurtosis, examines the complexity of brain-tissue   
   structure and can indicate changes in the parts of the brain involved   
   in learning, memory, and emotions.   
      
   "Our results highlight the power of artificial intelligence to help   
   us see things that we could not see before, particularly 'invisible   
   injuries' that do not show up on conventional MRI scans," said study   
   lead author Junbo Chen, MS, a doctoral candidate at NYU Tandon School   
   of Engineering. "This method may provide an important diagnostic tool   
   not only for concussion, but also for detecting the damage that stems   
   from subtler and more frequent head impacts."  Chen adds that the study   
   team next plans to explore the use of their machine- learning technique   
   for examining head injury in female athletes.   
      
   Funding for the study was provided by National Institute of Health   
   grants P41EB017183 and C63000NYUPG118117. Further funding was provided   
   by Department of Defense grant W81XWH2010699.   
      
   In addition to Lui and Chen, other NYU researchers involved in the study   
   were Sohae Chung, PhD; Tianhao Li, MS; Els Fieremans, PhD; Dmitry Novikov,   
   PhD; and Yao Wang, PhD.   
      
       * RELATED_TOPICS   
             o Mind_&_Brain   
                   # Brain_Injury # Intelligence # Brain-Computer_Interfaces   
                   # Disorders_and_Syndromes   
             o Computers_&_Math   
                   # Neural_Interfaces # Computer_Modeling # Communications   
                   # Hacking   
       * RELATED_TERMS   
             o Magnetic_resonance_imaging o Functional_neuroimaging   
             o Headache o Traumatic_brain_injury o Brain_damage o   
             Computer_vision o Head_injury o Neuropsychology   
      
   ==========================================================================   
   Story Source: Materials provided by   
   NYU_Langone_Health_/_NYU_Grossman_School_of_Medicine.   
      
   Note: Content may be edited for style and length.   
      
      
   ==========================================================================   
   Journal Reference:   
      1. Junbo Chen, Sohae Chung, Tianhao Li, Els Fieremans, Dmitry   
      S. Novikov,   
         Yao Wang, Yvonne W. Lui. Identifying relevant diffusion MRI   
         microstructure biomarkers relating to exposure to repeated head   
         impacts in contact sport athletes. The Neuroradiology Journal,   
         2023; 197140092311773 DOI: 10.1177/19714009231177396   
   ==========================================================================   
      
   Link to news story:   
   https://www.sciencedaily.com/releases/2023/05/230530125434.htm   
      
   --- up 1 year, 13 weeks, 1 day, 10 hours, 50 minutes   
    * Origin: -=> Castle Rock BBS <=- Now Husky HPT Powered! (1:317/3)   
   SEEN-BY: 15/0 106/201 114/705 123/120 153/7715 218/700 226/30 227/114   
   SEEN-BY: 229/110 112 113 307 317 400 426 428 470 664 700 291/111 292/854   
   SEEN-BY: 298/25 305/3 317/3 320/219 396/45   
   PATH: 317/3 229/426