FreeSurfer version-shuffling can boost brain age predictions
Korbmacher, M.; Westlye, L. T.; Maximov, I. I.
Show abstract
Abstract / Key pointsO_LIThe influence of FreeSurfer version-dependent variability in reconstructed cortical features on brain age predictions is average small when varying training and test splits from the same data. C_LIO_LIFreeSurfer version differences can lead to some variability in brain age dependent on the choice of algorithm and individual differences in brain morphometry, highlighting the advantage of repeated random train-test splitting. C_LIO_LIShuffling of differently processed FreeSurfer data dependent on the FreeSurfer version increases performance and generalizability of the brain age prediction model. C_LI
Matching journals
The top 2 journals account for 50% of the predicted probability mass.
Similar papers in this journal
- Brain-age prediction: a systematic comparison of machine learning workflows 96%
- The effect of head motion on brain age prediction using deep convolutional neural networks 96%
- Towards the Interpretability of Deep Learning Models for Multi-modal Neuroimaging: Finding Structural Changes of the Ageing Brain 96%
Similar papers in this journal
- Individual variations in Brain age relate to early life factors more than to longitudinal brain change 95%
- Nomograms of Human Hippocampal Volume Shifted by Polygenic Scores 94%
- Brain aging comprises many modes of structural and functional change with distinct genetic and biophysical associations 94%
Similar papers in this journal
- Diffusion Deep Learning for Brain Age Prediction and Longitudinal Tracking in Children Through Adulthood 97%
- Brain-wide functional connectome analysis of 40,000 individuals reveals brain networks that show aging effects in older adults 94%
- Translating phenotypic prediction models from big to small anatomical MRI data using meta-matching 94%
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.