Boosting hyperalignment performance with age-specific templates
Hyperalignment aligns individual brain activity and functional connectivity patterns to a common, high-dimensional model space, resolving idiosyncrasies in functional–anatomical correspondence and revealing shared information encoded in fine-grained spatial patterns. Given that the brain undergoes significant developmental and functional changes over the lifespan, certain features in brain…
In a recent study, researchers investigated the potential benefits of using age-specific functional templates in hyperalignment, a technique that aligns individual brain activity patterns to a common model space. The researchers utilized the Cambridge Centre for Ageing and Neuroscience (Cam-CAN) dataset, which consists of participants aged 18 to 87 years, and the Dallas Lifespan Brain Study dataset, which includes individuals aged 20 to 90 years.
They built age-specific templates based on the data and tested their performance in both young and old brains within these datasets.
The study revealed that the congruent age-specific template consistently outperformed the incongruent template in various analyses. These analyses included inter-subject correlation of hyperaligned connectivity profiles, predictions of individualized connectomes, and predictions of brain responses to movies. The findings remained consistent across both datasets, providing a clearer understanding of age-related differences in brain function.
This research highlights the advantages of employing age-specific templates to refine hyperalignment model performance.
Moreover, the results of this study could potentially contribute to the development of age-sensitive diagnostic tools and interventions for neurological disorders. By understanding the unique brain function patterns associated with different age groups, healthcare professionals may be better equipped to diagnose and treat conditions that affect specific age demographics.
Written by urgent.news from eLife's reporting — not their text. Machine-written — it may contain errors, so check the original before relying on it.
