Amortization Transformer for Brain Effective Connectivity Estimation from fMRI Data

Abstract

Using machine learning methods to estimate brain effective connectivity networks from functional magnetic resonance imaging (fMRI) data has garnered significant attention in the fields of neuroinformatics and bioinformatics. However, existing methods usually require retraining the model for each subject, which ignores the knowledge shared across subjects. In this paper, we propose a novel framework for estimating effective connectivity based on an amortization transformer, named AT-EC. In detail, AT-EC first employs an amortization transformer to model the dynamics of fMRI time series and infer brain effective connectivity across different subjects, which can train an amortized model that leverages the shared knowledge from different subjects. Then, an assisted learning mechanism based on functional connectivity is designed to assist the estimation of the brain effective connectivity network. Experimental results on both simulated and real-world data demonstrate the efficacy of our method.

Learning Causal Biological Networks with Parallel Ant Colony Optimization Algorithm

“…2021 [27] Large-scale Dynamic Causal Mode (PEB) 2020 [28] Latent Factor Causal Models (LFCMs) 2022 [29] Recurrent Generative Adversarial Network (RGAN) 2021 [21] Truncated Matrix Power Iteration (TMPI) 2022 [16] Deep Reinforcement Learning (DRL) 2022 [19] BN with Pruning Strategies (CO-CDG) 2022 [15] Amortization Transformer (AT-EC) 2023 [30] Deconfounded Functional Structure Estimation (DeFuSE) 2023 [31] 2.1.1. Causal Brain Networks Causal brain networks consist of multiple brain nodes and causal interactions between different nodes, and accurate learning of causal brain networks is valuable for understanding the functioning of brain cognition and gaining insight into the pathogenesis of brain diseases [32,33].…”

“…In recent years, many studies have emerged to learn causal brain networks from fMRI signal data, Friston et al [ 22 ] first proposed a spectral dynamic causal modeling for learning causal brain networks from fMRI signal data. Zhang et al [ 30 ] first proposed a amortization transformer model for learning causal brain networks from fMRI signal data. Li et al [ 28 ] and Razi et al [ 34 ] extended the model to learn the causal brain networks on large-scale brain regions from fMRI signal data.…”

NeurostimML: a machine learning model for predicting neurostimulation-induced tissue damage

“…Subsequently the trained algorithm may be used for prediction on new, untested stimulation parameters (testing instances) [29]. The machine learning approach has been widely used in areas of neuroscience and neural engineering research including brain imaging analysis [30][31][32], neuroinformatics [33][34][35], and behavioral analysis [36][37][38]. Herein, we extend the application of machine learning models to predict electrical stimulation-induced neural tissue damage.…”