Researchers have developed an AI-based approach to generate detailed maps highlighting differences in how distinct parts of the brain age.The new model, described in a study published in the journal Proceedings of the National Academy of Sciences, also shows how patterns of brain changes correlate with changes in cognitive function across one's lifespan, researchers said."Not all brain regions age at the same rate. Some areas appear to be more resilient, while others are more vulnerable to ageing and disease. By measuring local brain ageing, we can identify where the brain is ageing faster than expected and how those changes relate to cognitive function," lead researcher Andrei Irimia, associate professor at the University of Southern California's school of gerontology, said.Studies have put forth methodologies to estimate 'brain age', an emerging neuroimaging biomarker that compares a person's brain structure to patterns seen in healthy people across the lifespan.Traditional methods typically reduce the brain to a single age estimate, which can obscure important regional differences, the researchers said.The team's model provides a much richer picture of typical ageing and neurodegeneration.Rather than assigning a single brain age to an individual, the approach generates a detailed map showing how old different parts of the brain appear relative to what is typical for someone of the same chronological age, they said."Our approach consistently reveals spatial patterns of ageing, including relatively advanced ageing in frontal and temporal regions, across both typical ageing and Alzheimer's disease," the authors wrote."By providing spatially resolved measures of brain ageing, this work enables more precise investigation of how neuroanatomic alterations and cognitive impairment affect brain anatomy, above and beyond global brain age measures," they said.The researchers trained a deep-learning neural network using MRI scans from 14,748 cognitively normal adults aged 19 to 100 drawn from six large public datasets, including the UK Biobank and Human Connectome Project.The model was tested using over 1,900 additional MRI scans from the Alzheimer's Disease Neuroimaging Initiative -- another public dataset. It included cognitively normal adults, people with mild cognitive impairment and people with Alzheimer's disease.The frontal and temporal lobes -- regions involved in decision-making, memory and other higher cognitive functions -- were seen to appear biologically older than the parietal and occipital regions, which are involved in spatial awareness and sensory processing functions.The brain's right hemisphere tended to show slightly more advanced ageing than the left, a pattern that persisted regardless of whether participants were right- or left-handed.Differences in local brain ageing were found to become even more pronounced as cognitive impairment progressed.Compared with cognitively normal adults, participants with mild cognitive impairment or Alzheimer's disease showed significantly older local brain ages in structures among the first affected by Alzheimer's pathology, including the hippocampus, amygdala and several deep brain regions involved in memory and cognitive processing.Further, an older local brain age was associated with a poorer performance on cognitive assessments, strengthening the link between structural brain changes and real-world function.The strongest relationships appeared in people with Alzheimer's disease, suggesting that regional brain ageing may become increasingly informative as neurodegeneration advances, the researchers said.