Data harmonizing via interpolation applied to brain age prediction

Nieto, Nicolás; Patil, Kaustubh R.; Asati, Aditi; Jadhav, Kshitij

doi:10.1007/s44248-026-00100-7

Typ	Amount	VAT	Currency	Share	Status	Cost centre
APC	878.00	0.00	EUR	100.00 %	(Zahlung erfolgt)	ZB
Sum	878.00	0.00	EUR
Total	878.00

Journal Article

FZJ-2026-02602

Data harmonizing via interpolation applied to brain age prediction

Nieto, N. (Corresponding author)FZJ* ; Asati, A. ; Jadhav, K. ; Patil, K. R.FZJ*

2026
Springer Nature Cham

Discover data 4(1), 3 (2026) [10.1007/s44248-026-00100-7]

This record in other databases:

Please use a persistent id in citations: doi:10.1007/s44248-026-00100-7 doi:10.34734/FZJ-2026-02602

Abstract: Brain age estimation using magnetic resonance imaging is a promising biomarker for detecting accelerated aging and neurodegenerative disorders. However, the development of robust clinical models is severely hampered by the “Effects of Site”, where scanner-specific biases obscure biological signals in multi-center datasets. In this study, we propose a novel harmonization strategy, Inter-Site SMOTE, which generates synthetic training data by interpolating between age- and gender-matched participants from different sites. We hypothesize that these synthetic samples populate the sparse regions between site distributions, effectively bridging domain gaps while preserving biological integrity. We systematically evaluated this approach using four large neuroimaging datasets () in a leave-one-site-out regression task. Our results demonstrate that Inter-Site SMOTE significantly improves generalization to unseen scanners compared to standard data pooling. Crucially, we show that standard statistical harmonization (ComBat) fails to improve predictive performance in this setting due to inference-time assumptions, whereas our data-centric approach enhances robustness. Furthermore, we provide empirical evidence that the improvement is driven by the specific geometry of cross-site interpolation, as intra-site augmentation failed to yield comparable gains. This work presents a simple, effective solution for multi-site harmonization that circumvents the limitations of statistical adjustment methods, paving the way for more generalizable prediction models.

Classification: