Self-Supervised Transformers for fMRI representation (2021-12-10T00:00:00.000000Z)

TL;DR

TFF, which is a Transformer framework for the analysis of functional Magnetic Resonance Imaging (fMRI) data, employs a two-phase training approach, which shows state-of-the-art performance on a variety of fMRI tasks, including age and gender prediction, as well as schizophrenia recognition.

Abstract

We present TFF, which is a Transformer framework for the analysis of functional Magnetic Resonance Imaging (fMRI) data. TFF employs a two-phase training approach. First, self-supervised training is applied to a collection of fMRI scans, where the model is trained to reconstruct 3D volume data. Second, the pre-trained model is fine-tuned on specific tasks, utilizing ground truth labels. Our results show state-of-the-art performance on a variety of fMRI tasks, including age and gender prediction, as well as schizophrenia recognition. Our code for the training, network architecture, and results is attached as supplementary material.

Authors

Lior Wolf

7 papers

Itzik Malkiel

2 papers

Gony Rosenman

1 papers

TL;DR

Abstract

Authors

References36 items

Functional connectome fingerprinting: Identifying individuals and predicting cognitive functions via autoencoder

An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale

BrainGNN: Interpretable Brain Graph Neural Network for fMRI Analysis

Spatio-Temporal Graph Convolution for Resting-State fMRI Analysis

DeepFMRI: End-to-end deep learning for functional connectivity and classification of ADHD using fMRI

Effects of Age and Sex on Subcortical Volumes

VisualBERT: A Simple and Performant Baseline for Vision and Language

Enhancing the Locality and Breaking the Memory Bottleneck of Transformer on Time Series Forecasting

Functional MRI of brain physiology in aging and neurodegenerative diseases

Sex differences in somatomotor representations of others’ pain: a permutation-based analysis

3D MRI brain tumor segmentation using autoencoder regularization

Classification and Prediction of Brain Disorders Using Functional Connectivity: Promising but Challenging

Learning Neural Markers of Schizophrenia Disorder Using Recurrent Neural Networks

Decoupled Weight Decay Regularization

3D CNN Based Automatic Diagnosis of Attention Deficit Hyperactivity Disorder Using Functional and Structural MRI

Linked dimensions of psychopathology and connectivity in functional brain networks

Spatio-temporal Graph Convolutional Neural Network: A Deep Learning Framework for Traffic Forecasting

FCNet: A Convolutional Neural Network for Calculating Functional Connectivity from Functional MRI

Preprocessed Consortium for Neuropsychiatric Phenomics dataset

Attention is All you Need

Local-Global Parcellation of the Human Cerebral Cortex From Intrinsic Functional Connectivity MRI

Human brain mapping: A systematic comparison of parcellation methods for the human cerebral cortex

BrainNetCNN: Convolutional neural networks for brain networks; towards predicting neurodevelopment

A Window into the Brain: Advances in Psychiatric fMRI

Resting-State Functional Connectivity in Psychiatric Disorders.

Very Deep Convolutional Networks for Large-Scale Image Recognition

Sex differences in the structural connectome of the human brain

The WU-Minn Human Connectome Project: An overview

Exploring the brain network: A review on resting-state fMRI functional connectivity

Decoding the visual and subjective contents of the human brain

Automated Anatomical Labeling of Activations in SPM Using a Macroscopic Anatomical Parcellation of the MNI MRI Single-Subject Brain

BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding

R’), along with its six most correlated regions. research for explaining gender and aging on the brain activity, conducted mostly, but not only, through MRI imaging studies

Dropout: a simple way to prevent neural networks from overfitting

We combined the parcellation

Developmental Cognitive Neuroscience Age-related Changes in Insula Cortical Thickness and Impulsivity: Significance for Emotional Development and Decision-making

Field of Study

Venue Information

Name

Type

URL

Alternate Names