Preview

LogOn BRAIN MACHINE LEARNING -- {USAGM}

Please log in to download this media. Not registered? Register now!
Metadata
  • LogOn BRAIN MACHINE LEARNING -- {USAGM}
  • May 16, 2023
  • [[Researchers at the University of Southern California are using machine learning to analyze brain scans to better predict diseases associated with aging. For VOA, Genia Dulot has the story from Los Angeles.]]
  • Content Type Package
  • Language English
  • Transcript/Script LogOn BRAIN MACHINE LEARNING HEADLINE: LogOn: Researchers Analyzing Brain Scans to Predict Alzheimer’s Disease TEASER: Scientists at the University of Southern California are using machine learning to analyze medical imaging PUBLISHED AT: 05/16/2023 at 10:15AM BYLINE: Genia Dulot CONTRIBUTOR: DATELINE: Los Angeles, California VIDEOGRAPHER: Genia Dulot PRODUCER: SCRIPT EDITORS: Stearns, Reifenrath VIDEO SOURCE (S): VOA, Skype PLATFORMS (mark with X): WEB __ TV _X_ RADIO _X_ TRT: 1:59 VID APPROVED BY: mia TYPE: TVPKG EDITOR NOTES: ((INTRO:)) [[Researchers at the University of Southern California are using machine learning to analyze brain scans to better predict diseases associated with aging. For VOA, Genia Dulot has the story from Los Angeles.]] ((NARRATOR)) University of Southern California researchers are using magnetic resonance imaging, or MRI, scans to determine the biological age of a human brain, which may not always match a person’s chronological age, says Andrei Irimia, an assistant professor at USC Leonard Davis School of Gerontology. ((Andrei Irimia, USC Leonard Davis School of Gerontology)) “If a 45-year-old has the brain of a 55-year-old due to poor lifestyle choices, then that can also increase risk for disease because brains that are biologically older are typically a lot likelier to become ill and have higher risk for neurodegenerative disease, including Alzheimer’s disease.” ((NARRATOR)) The USC team used machine learning to develop a program trained on 4,800 MRI scans of healthy brains, which was then tested on 300 patients with neurogenerative diseases. Software author Paul Bogdan integrated magnifiers that zoom in on different brain regions into the program's deep-learning architecture. ((Paul Bogdan, USC Viterbi School of Engineering)) “The role of deep learning architecture is to look at each region in a three-dimensional space, see if that particular region contributes to predicting the age, and, if it does, it also quantifies how much it can help to predict the age of the brain.” ((NARRATOR)) Bogdan says that magnification allows for richer analysis of brain aging between men and women because each gender has different changes happening in different areas of the brain. Researchers say other medical uses for machine learning may be screening circulating blood cells to identify cancers. ((Genia Dulot, for VOA News, Los Angeles)
  • NewsML Media Topics Arts, Culture, Entertainment and Media
  • Network VOA
  • Location (dateline) Los Angeles
  • Embargo Date May 16, 2023 00:16 EDT
  • Byline Genia Dulot, for VOA News
  • Brand / Language Service Voice of America - English
Frames
Related records