Spectral filtering improves brain data models for personalized prediction
Flattening the Connectome Spectrum: A Spectral Filter for FC Induces a Pretraining Target for fMRI Encoders
Artificial IntelligenceMachine Learning
Summary
Functional MRI scans show how different parts of the brain connect, but predicting individual traits from this data can be tricky. The authors found that adjusting the mathematical properties of brain connectivity data helps models detect personal differences better. They used this adjustment to train a smaller brain data model that works as well as bigger models and does better with shorter scans and smaller groups. They also shared their model and code so others can use this improved approach.
What this means in practice
- •For medical imaging analysts: Use recalibrated brain connectivity data to improve personalized trait prediction from fMRI scans, especially with limited scan duration or small patient groups.
- •For neurotechnology developers: Incorporate the pretrained fMRI encoder to build more efficient brain data analysis tools with fewer parameters but competitive accuracy.
Authors
Giovanni Marraffini, Victoria Shevchenko, Carlo Alberto Barbano, Demian Wassermann
Abstract
Self-supervised pretraining reshaped prediction in language and vision, and brain foundation models (BFMs) inherited its promise. Representations learned from large unlabelled corpora should capture individual functional dynamics and generalise across cohorts. However, kernel ridge regression (KRR) fitted on functional connectivity (FC) matrices still predicts individual phenotypes more accurately than any BFM we tested. In this paper, we show that KRR is weighted by the eigenvalues of the FC which are miscalibrated for phenotype prediction. We apply an efficient spectral filter to recalibrate the eigenvalues of each subject's FC matrix, enabling the model to exploit more inter-individual variance. Across the 5 datasets, 11 parcellations and 6 prediction targets we tested, we match or exceed the KRR baseline. Based on this finding, we then pretrain a small encoder model on about 4,000 hours of fMRI from 162 open datasets, whereby we align the pairwise similarities between the embeddings of recording snippets with those between the recalibrated connectomes. Our model performs on par with the best of the 6 published BFMs we tested while having an order of magnitude fewer parameters. Our encoder performs better than FC on short scans and in smaller cohorts, especially in fingerprinting. We release the pretrained model weights, the code and the pretraining data, preprocessed and parcellated.