UT center unveils AI tool for rapid brain lesion counting
%2Favatars%2FaJImjL87n6vb.png&w=96&q=75)
%2F2023%2F07%2F16%2Fimage%2Fjpeg%2F1yGICFRvj5haCawkBCnHmokfTnAzmBY5KgrsokGu.jpg&w=3840&q=75)
Researchers at UT Health Science Center San Antonio have unveiled a groundbreaking tool that can count brain lesions in seconds. This innovative technology utilizes artificial intelligence (AI) to accurately quantify and map these lesions, providing valuable insights into conditions such as cerebral small-vessel disease, which can lead to stroke and dementia.
Until now, quantifying certain types of brain lesions has been a time-consuming task for medical professionals. Dr. Mohamad Habes, a researcher at UT Health Science Center's Glenn Biggs Institute for Alzheimer's and Neurodegenerative Diseases, explained, "Certain kinds of brain lesions are tremendously difficult to quantify without AI." As the assistant professor of radiology and director of the Biggs Institute neuroimaging core, Dr. Habes played a pivotal role in this research.
The study, published in JAMA Network Open, showcased the utility of the AI tool in identifying and counting enlarged perivascular spaces (ePVSs). These spaces, filled with cerebrospinal fluid, surround arteries and veins and serve as markers for cerebral small-vessel disease. The research involved a follow-up analysis of 1,026 participants from the Multi-Ethnic Study of Atherosclerosis (MESA), collaborating with researchers from eight institutions.
The significance of the AI tool
Dr. Habes emphasized the significance of their deep-learning tool, stating, "We have developed an innovative deep-learning tool to precisely quantify every single enlarged perivascular space in the brain and provide us a map of the patient's small-vessel disease." Previously, the difficulty of counting ePVSs on MRI scans led to their neglect.
On average, an MRI scan of a middle-aged person may reveal around 500 or 600 of these small spaces. The laborious task of manually counting them would take hours, making it impractical in a busy clinic setting.
The team's automated deep-learning method for ePVS detection, described in Neuroimage: Reports, showcases the power of the algorithm. Dr. Habes explained, "This tool recognizes them, tells us their exact locations, counts them, and tells us their volumes. It tells us a ton of information about them, far more than what a human can do." This technology opens up new possibilities for studying and understanding brain lesions.
During their investigation, the researchers discovered that enlarged perivascular spaces in the brain's basal ganglia and thalamus regions hold particular significance. These regions have shown associations with stroke and markers of small-vessel disease.
The basal ganglia, an essential deep-brain region linked to neurodegenerative disorders, plays a role in movement and decision-making. The thalamus, located near the basal ganglia, is involved in sensory functions such as taste and touch.
Dr. Habes expressed hope that the AI tool for enumerating brain lesions will undergo further study at Alzheimer's Disease Research Centers (ADRCs). The technology represents a significant stride forward in medical imaging and paves the way for more efficient and accurate diagnoses in the future.
SHOW COMMENT (1)
/2023/07/26/image/jpeg/9Dkowuh7yI1YIB0hFtRiZ5DWxel88daCnm1Eld3Y.jpg "Can AI accurately identify patients with respiratory symptoms?")
/2023/08/07/image/jpeg/Ud2zDGb2iGOiBAo4pvLO543XFvNGkPlUEZCF7qSY.jpg "Why do matter and the universe exist at all? Scientists get closer to the answer")
/2023/09/22/image/jpeg/ezxP0CaCL9js7IHPU0dL2DKNgCnpXB2eKl21dunq.jpg "Canadian telecom uses AI cameras to fight wildfires")
/2023/08/30/image/jpeg/Llkj2YI4zCWyQWM06dnC9PZHBRzZLT4na9uWmRXZ.jpg "Maybe you can hear sounds in space after all")
/2023/08/23/image/jpeg/ivMD3RG1VXLwimcDFkTj4viol8hAbysi9HLwfOik.jpg "Is medical research entering a new era of fertility treatments?")
/2023/09/22/image/jpeg/9SLaB2Df46jpPiVQeF11ZmUbCIhULAGJlUeBx7OP.jpg "How a student invented an affordable fire-fighting robot")
/2023/09/22/image/jpeg/QdiwYUSgm1SXYVNR6hYJTGg57873RFdy9P7IZvzo.jpg "Solar cars can reduce global charging needs by half")
/2023/09/22/image/jpeg/P7SdZBzocsfspOZPW3sqPoEMP3rzACvEMBZrtiNE.jpg "Gold nanoclusters could be the key to hydrogen energy")
/2023/08/26/image/jpeg/dx4nDIYOH40PorY0ptnpC1JymO0nUKbTPQy7XNly.jpg "9 examples of when AI went haywire")
/2023/09/22/image/jpeg/nsmar7gjdLlrBOi4PzKAxGav2HZeyKXWXa9TmEya.jpg "Honda releases its first-ever series production V8 engine")