First-of-its-kind AI Model Uses Brain Scans to Reveal Link Between Aging and Cognitive Decline

Researchers at the University of Southern California (USC) have developed a new artificial intelligence (AI) model that analyzes brain scans to measure the rate of brain aging. This first-of-its-kind tool non-invasively monitors the rate of brain changes by analyzing magnetic resonance imaging (MRI) scans. In return, researchers have found that accelerated brain aging strongly correlates with an increased risk of cognitive impairment.

3D-CNN Utilized MRI Scans to Accurately Track Brain Aging and Neuroanatomic Changes

Biological age differs from chronological age, as it reflects how well the body functions at a cellular level. While blood-based measures assess epigenetic aging, they do not accurately reflect brain aging due to the blood-brain barrier, and direct brain tissue sampling is too invasive. Previous research demonstrated that MRI scans could non-invasively estimate brain age using AI analysis of brain anatomy compared to large datasets. However, earlier models had limitations, as they could estimate whether a brain appeared older than expected but could not determine when aging acceleration occurred or whether it was progressing over time.

This newly developed three-dimensional convolutional neural network (3D-CNN) provides a more precise way to measure brain aging over time. Researchers trained and validated the model using more than 3,000 MRI scans from cognitively normal adults. Unlike traditional cross-sectional methods that estimate brain age from a single scan, this approach compares baseline and follow-up MRI scans from the same individual, allowing for a more accurate assessment of neuroanatomic changes linked to accelerated or decelerated aging. 

The 3D-CNN also produces interpretable “saliency maps”, highlighting the specific brain regions most critical for determining the pace of aging. When applied to a group of 104 cognitively healthy adults and 140 Alzheimer’s disease patients, the new model’s measurements of brain aging speed closely aligned with changes in cognitive function test results taken at both time points.

Andrei Irimia, associate professor of gerontology, biomedical engineering, quantitative & computational biology and neuroscience at the USC Leonard Davis School of Gerontology, said, “Rates of brain aging are correlated significantly with changes in cognitive function. So, if you have a high rate of brain aging, you’re more likely to have a high rate of degradation in cognitive function.”

Model Offers Potential to Detect Accelerated Brain Aging Before Symptoms of Cognitive Impairment Appear

The study found that the new model can distinguish different rates of aging across various brain regions. Investigating these differences, including how they vary based on genetics, environment, and lifestyle factors, could provide insights into the development of various brain pathologies. The study also revealed that brain aging occurred at different rates in certain regions between the sexes, which may help explain why men and women face distinct risks for neurodegenerative disorders, such as Alzheimer’s.

Additionally, the model has the potential to identify individuals with accelerated brain aging before they show symptoms of cognitive impairment. While new Alzheimer’s drugs have been introduced, their efficacy has been limited, possibly because patients may begin treatment after significant Alzheimer’s pathology has already developed in the brain.

“One thing that my lab is very interested in is estimating risk for Alzheimer’s; we’d like to one day be able to say, ‘Right now, it looks like this person has a 30% risk for Alzheimer’s.’ We’re not there yet, but we’re working on it,” said Andrei Irimia. “I think this kind of measure will be very helpful to produce variables that are prognostic and can help to forecast Alzheimer’s risk. That would be really powerful, especially as we start developing potential drugs for prevention.”

Related posts:

Billion-Dollar AI Deals Powering Antibody Design, Biologics, and Next-Gen Therapies Pioneers of AI Win Nobel Prize in Physics for Training Neural Networks with Physics Building a Virtual Cell with AI: Key Priorities and Opportunities Grok3: The Smartest AI According to Elon Musk—Can It Overcome the Challenges?

Author

Denisse Sandoval