一个统一的大脑连接组翻译和融合工具Krakencoder，这一成果由放射科Amy Kuceyeski研究小组经过不懈努力而取得。这一研究成果于2025年6月5日发表在国际顶尖学术期刊《自然—方法学》上。

该课题组提出了Krakencoder，这是一个联合连接体映射工具，可以同时在结构和功能连接之间，以及通过共同的潜在表示在不同的地图集和处理选择之间进行双向转换。这些映射显示出卓越的准确性和个人层面的可识别性；与现有模型相比，结构连接和功能连接映射的可识别性提高了42-54%。Krakencoder通过共享的低维潜在空间结合了所有的连接体风格。这种概念表征更好地反映了家庭关系，保留了与年龄和性别相关的信息，增强了与认知相关的信息。Krakencoder可以在不需要再训练的情况下应用于新的分布外数据，同时仍然保留连接组预测中的个体间差异和潜在表征中的家族关系。Krakencoder在以个性化、行为和人口统计学相关的方式捕捉多模态脑连接体之间的关系方面是一个显著的飞跃。

研究人员表示，大脑连接可以通过多种方式进行评估，这取决于模式和处理策略。

附：英文原文

Title: Krakencoder: a unified brain connectome translation and fusion tool

Author: Jamison, Keith W., Gu, Zijin, Wang, Qinxin, Tozlu, Ceren, Sabuncu, Mert R., Kuceyeski, Amy

Issue&Volume: 2025-06-05

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

Source: https://www.nature.com/articles/s41592-025-02706-2