Sex-based Network-Specific Differences in Connectomes: A Krakencoder-Based Analysis

2026-06-15

AI Summary

This study investigates the impact of missing functional brain networks on cross-modal prediction between structural and functional connectomes, as well as the preservation of sex differences under such perturbations. Leveraging the Krakencoder framework, the authors systematically simulated the removal of individual subnetworks within the Yeo-7 functional parcellation and evaluated the resulting disruptions using multiple metrics—KL divergence, Frobenius norm, Wasserstein distance—and a sex classifier. Findings reveal that the default mode network exerts the strongest influence on cross-modal prediction accuracy, whereas the somatomotor network has the weakest effect. Sex classification accuracy dropped significantly from 84.76% with the intact connectome to 66.09% under perturbed conditions. This work represents the first integration of Krakencoder with multidimensional perturbation analysis, elucidating the distinct roles of key functional networks in both cross-modal mapping and sex-related information encoding.

Abstract

This study examines how deficiencies in one brain connectome modality propagate to the other, using the Krakencoder as a simulation framework. Structural and functional connectomes from 702 healthy participants in the Human Connectome Project were analyzed, with the impact of each of the Yeo-7 functional networks assessed separately. Seven scenarios were considered, each involving the removal of a single network while the remaining networks were preserved. The resulting perturbations in cross-modal predictions were quantified using three complementary metrics: KL divergence on eigenvalue spectra, Frobenius norm, and Wasserstein distance. In addition, the persistence of sex-specific information within the predicted connectomes was evaluated. Across all metrics and both prediction directions, the Default Mode Network produced the largest perturbations, whereas the Somatomotor network yielded the smallest. Sex differences in network-level perturbation signatures were subtle, with the best result being an accuracy of 66.09% from connectomes predicted under network-removal conditions. In contrast, connectomes predicted from intact inputs achieved substantially higher sex classification accuracy, reaching up to 84.76%. These findings confirm that full predicted connectomes retain considerably more sex-discriminative information than perturbation-derived signatures alone.

Problem

• connectome
• sex differences
• network perturbation
• cross-modal prediction
• functional networks

Innovation

• Krakencoder
• cross-modal prediction
• network perturbation
• sex differences
• connectome