Contributed Talk Sessions | Poster Sessions | All Posters | Search Papers

Poster Session C: Friday, August 15, 2:00 – 5:00 pm, de Brug & E‑Hall

Boosting Hyperalignment Performance with Age-specific Templates

Yuqi Zhang¹, Maria Gobbini², James Haxby¹, Ma Feilong¹; ¹Dartmouth College, ²University of Bologna

Presenter: Yuqi Zhang

The brain undergoes significant developmental and functional changes over the lifespan, and certain features in brain functional organization may be more prominent in certain age groups than others. Due to individual differences in functional–anatomical correspondence, features encoded in fine-grained spatial patterns need to be functionally aligned using hyperalignment. In this work, we examine whether age-specific functional templates improve hyperalignment. We built age-specific templates using the Cambridge Centre for Ageing and Neuroscience (Cam-CAN) dataset (18–87 yo) and evaluated their performance. We found that congruent age-specific templates improve the performance of (a) predicting individualized connectomes, (b) predicting individualized brain responses during movie watching, and (c) inter-subject correlation of connectivity profiles. This work enhances our understanding of age-related differences in brain function, highlights the benefits of creating age-specific templates to refine hyperalignment model performance, and may contribute to the development of age-sensitive diagnostic tools and interventions for neurological disorders.

Topic Area: Methods & Computational Tools

Extended Abstract: Full Text PDF