Krakencoder: a unified brain connectome translation and fusion tool.
Publication Type | Academic Article |
Authors | Jamison K, Gu Z, Wang Q, Tozlu C, Sabuncu M, Kuceyeski A |
Journal | Nat Methods |
Date Published | 06/05/2025 |
ISSN | 1548-7105 |
Abstract | Brain connectivity can be estimated in many ways, depending on modality and processing strategy. Here, we present the Krakencoder, a joint connectome mapping tool that simultaneously bidirectionally translates between structural and functional connectivity, and between different atlases and processing choices via a common latent representation. These mappings demonstrate exceptional accuracy and individual-level identifiability; the mapping between structural and functional connectivity has identifiability 42-54% higher than existing models. The Krakencoder combines all connectome flavors via a shared low-dimensional latent space. This fusion representation better reflects familial relatedness, preserves age- and sex-relevant information, and enhances cognition-relevant information. The Krakencoder can be applied, without retraining, to new out-of-distribution data while still preserving inter-individual differences in the connectome predictions and familial relationships in the latent representations. The Krakencoder is a notable leap forward in capturing the relationship between multimodal brain connectomes in an individualized, behaviorally and demographically relevant way. |
DOI | 10.1038/s41592-025-02706-2 |
PubMed ID | 40473984 |