ABFR-KAN: Kolmogorov-Arnold Networks for Functional Brain Analysis

TL;DR

This paper introduces ABFR-KAN, a transformer-based brain network model that improves functional connectivity analysis for autism diagnosis by reducing bias and increasing reliability, outperforming existing methods.

Contribution

The paper presents a novel transformer-based network incorporating Kolmogorov-Arnold Networks to address bias and enhance FC estimation in brain disorder classification.

Findings

ABFR-KAN outperforms state-of-the-art baselines on ABIDE I dataset.

The model shows robustness across different model backbones and configurations.

Cross-site evaluation confirms improved generalization.

Abstract

Functional connectivity (FC) analysis, a valuable tool for computer-aided brain disorder diagnosis, traditionally relies on atlas-based parcellation. However, issues relating to selection bias and a lack of regard for subject specificity can arise as a result of such parcellations. Addressing this, we propose ABFR-KAN, a transformer-based classification network that incorporates novel advanced brain function representation components with the power of Kolmogorov-Arnold Networks (KANs) to mitigate structural bias, improve anatomical conformity, and enhance the reliability of FC estimation. Extensive experiments on the ABIDE I dataset, including cross-site evaluation and ablation studies across varying model backbones and KAN configurations, demonstrate that ABFR-KAN consistently outperforms state-of-the-art baselines for autism spectrum distorder (ASD) classification. Our code is available at https://github.com/tbwa233/ABFR-KAN.