Normal cohorts in automated brain atrophy estimation: how many healthy subjects to include?

Christian RubbertLuisa WolfMarius VachVivien L IvanDennis M HedderichChristian GaserRobert DahnkeJulian Caspersnull null

Published in: European radiology (2024)

• Software-based brain atrophy estimation often relies on normal cohorts for comparisons. • At least 15 subjects must be included in an age- and sex-specific normal cohort. • Using different normal cohorts does not influence regional atrophy estimation.

Keyphrases

resting state
white matter
machine learning
functional connectivity
high throughput
deep learning
brain injury
single cell