ACTION: Augmentation and Computation Toolbox for Brain Network Analysis with Functional MRI

TL;DR

The paper tackles the limited data and tool support in fMRI analysis by introducing ACTION, a Python-based toolbox that integrates automatic fMRI data augmentation, diverse brain network construction, feature extraction, and AI model construction. ACTION provides pretrained deep learning backbones trained on 3,806 resting-state scans and supports federated learning to enable multi-site studies without centralizing data. The framework offers ten deep learning architectures, seven network-construction methods, graph augmentation strategies, and conventional ML options, all designed to improve robustness and generalization for fMRI tasks such as ASD diagnosis. Empirical results on ABIDE-derived multi-site data demonstrate improved diagnostic performance and practical utility, highlighting ACTION’s potential to accelerate reproducible, scalable brain network analysis with fMRI.

Abstract

Functional magnetic resonance imaging (fMRI) has been increasingly employed to investigate functional brain activity. Many fMRI-related software/toolboxes have been developed, providing specialized algorithms for fMRI analysis. However, existing toolboxes seldom consider fMRI data augmentation, which is quite useful, especially in studies with limited or imbalanced data. Moreover, current studies usually focus on analyzing fMRI using conventional machine learning models that rely on human-engineered fMRI features, without investigating deep learning models that can automatically learn data-driven fMRI representations. In this work, we develop an open-source toolbox, called Augmentation and Computation Toolbox for braIn netwOrk aNalysis (ACTION), offering comprehensive functions to streamline fMRI analysis. The ACTION is a Python-based and cross-platform toolbox with graphical user-friendly interfaces. It enables automatic fMRI augmentation, covering blood-oxygen-level-dependent (BOLD) signal augmentation and brain network augmentation. Many popular methods for brain network construction and network feature extraction are included. In particular, it supports constructing deep learning models, which leverage large-scale auxiliary unlabeled data (3,800+ resting-state fMRI scans) for model pretraining to enhance model performance for downstream tasks. To facilitate multi-site fMRI studies, it is also equipped with several popular federated learning strategies. Furthermore, it enables users to design and test custom algorithms through scripting, greatly improving its utility and extensibility. We demonstrate the effectiveness and user-friendliness of ACTION on real fMRI data and present the experimental results. The software, along with its source code and manual, can be accessed online.

Figures (7)

• Figure 1: Major functions included in the proposed ACTION software, including fMRI data augmentation, brain network construction, brain network feature extraction, and artificial intelligence (AI) model construction.
• Figure 2: Illustration of four methods for fMRI blood-oxygen-level-dependent (BOLD) signal augmentation.
• Figure 3: Illustration of six graph augmentation methods based on fMRI-derived brain networks/graphs.
• Figure 4: Visualization of the constructed brain network.
• Figure 5: Illustration of conventional machine learning framework for fMRI-based prediction.