SwiFT: Swin 4D fMRI Transformer

• URL: http://arxiv.org/abs/2307.05916v2
• Date: Tue, 31 Oct 2023 04:54:00 GMT
• Title: SwiFT: Swin 4D fMRI Transformer
• Authors: Peter Yongho Kim, Junbeom Kwon, Sunghwan Joo, Sangyoon Bae, Donggyu Lee, Yoonho Jung, Shinjae Yoo, Jiook Cha, Taesup Moon
• Abstract summary: We present SwiFTS (win 4D fMRI Transformer), a Swin Transformer architecture that can learn brain dynamics directly from volumes fMRI. We evaluate SwiFT using multiple large-scale resting-state fMRI datasets to predict sex age and cognitive intelligence.
• Score: 17.95502427633986
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Modeling spatiotemporal brain dynamics from high-dimensional data, such as functional Magnetic Resonance Imaging (fMRI), is a formidable task in neuroscience. Existing approaches for fMRI analysis utilize hand-crafted features, but the process of feature extraction risks losing essential information in fMRI scans. To address this challenge, we present SwiFT (Swin 4D fMRI Transformer), a Swin Transformer architecture that can learn brain dynamics directly from fMRI volumes in a memory and computation-efficient manner. SwiFT achieves this by implementing a 4D window multi-head self-attention mechanism and absolute positional embeddings. We evaluate SwiFT using multiple large-scale resting-state fMRI datasets, including the Human Connectome Project (HCP), Adolescent Brain Cognitive Development (ABCD), and UK Biobank (UKB) datasets, to predict sex, age, and cognitive intelligence. Our experimental outcomes reveal that SwiFT consistently outperforms recent state-of-the-art models. Furthermore, by leveraging its end-to-end learning capability, we show that contrastive loss-based self-supervised pre-training of SwiFT can enhance performance on downstream tasks. Additionally, we employ an explainable AI method to identify the brain regions associated with sex classification. To our knowledge, SwiFT is the first Swin Transformer architecture to process dimensional spatiotemporal brain functional data in an end-to-end fashion. Our work holds substantial potential in facilitating scalable learning of functional brain imaging in neuroscience research by reducing the hurdles associated with applying Transformer models to high-dimensional fMRI.

Related papers

• MindAligner: Explicit Brain Functional Alignment for Cross-Subject Visual Decoding from Limited fMRI Data [64.92867794764247]
  MindAligner is a framework for cross-subject brain decoding from limited fMRI data. Brain Transfer Matrix (BTM) projects the brain signals of an arbitrary new subject to one of the known subjects. Brain Functional Alignment module is proposed to perform soft cross-subject brain alignment under different visual stimuli.
  arXiv  Detail & Related papers  (2025-02-07T16:01:59Z)
• Classification of Mild Cognitive Impairment Based on Dynamic Functional Connectivity Using Spatio-Temporal Transformer [30.044545011553172]
  We propose a novel framework that jointly learns the embedding of both spatial and temporal information within dFC. Experimental results on 345 subjects with 570 scans from the Alzheimers Disease Neuroimaging Initiative (ADNI) demonstrate the superiority of our proposed method.
  arXiv  Detail & Related papers  (2025-01-27T18:20:33Z)
• Predicting Human Brain States with Transformer [45.25907962341717]
  We show that a self-attention-based model can accurately predict the brain states up to 5.04s with the previous 21.6s. These promising initial results demonstrate the possibility of developing gen-erative models for fMRI data.
  arXiv  Detail & Related papers  (2024-12-11T00:18:39Z)
• Brain3D: Generating 3D Objects from fMRI [76.41771117405973]
  We design a novel 3D object representation learning method, Brain3D, that takes as input the fMRI data of a subject. We show that our model captures the distinct functionalities of each region of human vision system. Preliminary evaluations indicate that Brain3D can successfully identify the disordered brain regions in simulated scenarios.
  arXiv  Detail & Related papers  (2024-05-24T06:06:11Z)
• Interpretable Spatio-Temporal Embedding for Brain Structural-Effective Network with Ordinary Differential Equation [56.34634121544929]
  In this study, we first construct the brain-effective network via the dynamic causal model. We then introduce an interpretable graph learning framework termed Spatio-Temporal Embedding ODE (STE-ODE) This framework incorporates specifically designed directed node embedding layers, aiming at capturing the dynamic interplay between structural and effective networks.
  arXiv  Detail & Related papers  (2024-05-21T20:37:07Z)
• ACTION: Augmentation and Computation Toolbox for Brain Network Analysis with Functional MRI [28.639321546348654]
  Action is a Python-based and cross-platform toolbox for fMRI analysis. It enables automatic fMRI augmentation, covering blood-oxygen-level-dependent (BOLD) signal augmentation and brain network augmentation. It supports constructing deep learning models, which leverage large-scale auxiliary unlabeled data.
  arXiv  Detail & Related papers  (2024-05-10T01:45:09Z)
• MindBridge: A Cross-Subject Brain Decoding Framework [60.58552697067837]
  Brain decoding aims to reconstruct stimuli from acquired brain signals. Currently, brain decoding is confined to a per-subject-per-model paradigm. We present MindBridge, that achieves cross-subject brain decoding by employing only one model.
  arXiv  Detail & Related papers  (2024-04-11T15:46:42Z)
• Brainformer: Mimic Human Visual Brain Functions to Machine Vision Models via fMRI [12.203617776046169]
  We introduce a novel framework named Brainformer to analyze fMRI patterns in the human perception system. This work introduces a prospective approach to transferring knowledge from human perception to neural networks.
  arXiv  Detail & Related papers  (2023-11-30T22:39:23Z)
• fMRI-PTE: A Large-scale fMRI Pretrained Transformer Encoder for Multi-Subject Brain Activity Decoding [54.17776744076334]
  We propose fMRI-PTE, an innovative auto-encoder approach for fMRI pre-training. Our approach involves transforming fMRI signals into unified 2D representations, ensuring consistency in dimensions and preserving brain activity patterns. Our contributions encompass introducing fMRI-PTE, innovative data transformation, efficient training, a novel learning strategy, and the universal applicability of our approach.
  arXiv  Detail & Related papers  (2023-11-01T07:24:22Z)
• BrainCLIP: Bridging Brain and Visual-Linguistic Representation Via CLIP for Generic Natural Visual Stimulus Decoding [51.911473457195555]
  BrainCLIP is a task-agnostic fMRI-based brain decoding model. It bridges the modality gap between brain activity, image, and text. BrainCLIP can reconstruct visual stimuli with high semantic fidelity.
  arXiv  Detail & Related papers  (2023-02-25T03:28:54Z)
• EEG to fMRI Synthesis: Is Deep Learning a candidate? [0.913755431537592]
  This work provides the first comprehensive on how to use state-of-the-art principles from Neural Processing to synthesize fMRI data from electroencephalographic (EEG) view data. A comparison of state-of-the-art synthesis approaches, including Autoencoders, Generative Adrial Networks and Pairwise Learning, is undertaken. Results highlight the feasibility of EEG to fMRI brain image mappings, pinpointing the role of current advances in Machine Learning and showing the relevance of upcoming contributions to further improve performance.
  arXiv  Detail & Related papers  (2020-09-29T16:29:20Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.