% IMPORTANT: The following is UTF-8 encoded. This means that in the presence
% of non-ASCII characters, it will not work with BibTeX 0.99 or older.
% Instead, you should use an up-to-date BibTeX implementation like “bibtex8” or
% “biber”.
@INPROCEEDINGS{Antonopoulos:1034876,
author = {Antonopoulos, Georgios and More, Shammi and Raimondo,
Federico and Eickhoff, Simon and Patil, Kaustubh},
title = {{P}arcel-wise stacking ensemble provides improved age
prediction and brain-aging insights},
reportid = {FZJ-2024-07622},
year = {2024},
abstract = {Introduction:Predicting chronological age using structural
magnetic resonance imaging (MRI) has shown great potential
for studying aging in health and disease. A model trained on
MRI scans from healthy individuals can provide biological
insights into healthy brain aging and it can also
potentially assist in detection of abnormal aging in
psychiatric, and neurodegenerative disorders [1, 2]. Such a
model may lead to novel monitoring and treatment options.
However, both accuracy and explainability of age prediction
models need to be improved before they can be applied in the
real-world. To this end, we propose parcel-wise stacking
ensemble models (SEM) [3]. In SEM the voxels in each region
are not weighted equally, as in the standard approaches.
Regional models evaluate the contribution of each voxel in
the process making this way, better use of voxels'
information. Moreover, combining predictions in sequential
models leads to reduced overall bias and variance, of the
final prediction.Methods:We used T1w MRI scans of healthy
subjects from 4 open datasets (IXI, eNKI, CamCAN and
1000Gehirne. N>500 each, total N=3103, age range 18-90
years). Voxel based morphometry using CAT12.8 [4] was
employed to estimate gray matter volume (GMV) for each
subject. Performance was estimated in terms of mean absolute
error (MAE) assessed in leave-one-dataset-out (LODO) set
up.Proposed SEM consists of two levels, denoted as L0 and L1
(Figure 1). GLMnet [5] was used for both L0 and L1 models.
The L0 uses an 873-parcel atlas and trains a model for each
parcel using corresponding voxels-wise GMV. The features for
the L1 model are obtained as out-of-sample (OOS) predictions
from a 3-fold cross-validation scheme on L0 models. Two
types of L0 models were obtained; either by pooling data
from different sites (L0p) or by making predictions for each
training site separately (L0s). Similarly, in L1 models were
obtained by either pooling L0 predictions (L1p) or by
training the L1 model for each site separately and averaging
the per-site predictions (L1s).Additionally, to examine the
case where enough data is available at an application site,
we estimate L0 OOS predictions from that site (L0oos). These
are then used to obtain predictions using the L1 models. As
a baseline we also trained models using the average GMV in
each parcel -by averaging predictions of the site-specific
models or training models on pooled data across sites-,
while ensuring use of consistent training samples across the
set ups.Results:The highest test performances were observed
for the L0oos setups where L0 predictions came from the test
site. The best predictions were for the L0oos-L1p (average
MAE=4.8), closely followed by the L0oos-L1s (MAE=4.9).
Setups using pooled L0 predictions to train L1,
independently of how L0 was trained, L0p-L1p and L0s-L1p,
had both MAE=5.1. Models using mean parcel-wise GMV had
MAE=5.7 when the model was trained using the train sets
together with the 2 folds of the test set. Performance was
worse for the other two mean parcel-wise GMV models trained
in three datasets, with the L1p setup up being slightly
better compared to L1s (MAE=6.2 and MAE=6.7 respectively).L0
models provided robust interpretation of regional aging
effects, i.e. the Pearson correlation of real age with OOS
predicted-age was higher than with GMV (averaged across all
datasets used for training, Figure 2). While there is a
considerable overlap in the identified regions between the
two methodologies, SEM distinctly emphasizes certain areas,
notably the subcortex and cerebellum.Conclusions:SEM
provides improved age prediction performance compared to
using parcel-wise average of GMV as well as novel biological
insights regarding healthy aging. Further improvements in
the SEM design could be achieved by selecting suitable
learning algorithms with appropriate hyperparameter tuning
for L0 and L1 models.},
month = {Jun},
date = {2024-06-23},
organization = {OHBM 2024, Seoul (South Korea), 23 Jun
2024 - 27 Jun 2024},
subtyp = {After Call},
cin = {INM-7},
cid = {I:(DE-Juel1)INM-7-20090406},
pnm = {5253 - Neuroimaging (POF4-525)},
pid = {G:(DE-HGF)POF4-5253},
typ = {PUB:(DE-HGF)24},
doi = {10.34734/FZJ-2024-07622},
url = {https://juser.fz-juelich.de/record/1034876},
}