Brain Age Prediction Using 2D Projections Based on Higher-Order Statistical Moments and Eigenslices from 3D Magnetic Resonance Imaging Volumes

Johan Jönemo, Anders Eklund, Ebrahim Karami · 2023

Read Brain Age Prediction Using 2D Projections Based on Higher-Order Statistical Moments and Eigenslices from 3D Magnetic Resonance Imaging Volumes by Johan Jönemo, Anders Eklund, Ebrahim Karami (2023) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-10743800.txt.

Description

Johan Jönemo and Anders Eklund predict brain age from MRI scans on the cheap, in a 2023 paper. Brain age, guessed from a scan, flags brains ageing faster than the calendar. Deep networks read full 3D scans well but train slowly on huge collections like the UK Biobank. Earlier work showed a few flat projections of each scan train far faster, at some cost in accuracy.

This follow-up tries richer summaries: higher-order statistical moments, which capture skew and spread, and eigenslices, slices drawn from the scan's own structure. The moments added nothing, but eigenslices nudged accuracy upward. Stacking several such models into an ensemble helped further. Fast brain-age screening stays feasible without supercomputer budgets.

Catalog record

CREATORJohan Jönemo, Anders Eklund, Ebrahim Karami
YEAR2023
COLLECTIONPAPERS
FORMATTXT
FILE SIZE30 KB
VERSION1.0
LICENSECC BY 4.0
RIGHTSCC BY
SOURCEEurope PMC

Source: https://europepmc.org/articles/PMC10743800

Browse the full library · About the Tower of Babel