Self-Supervised Transformers for fMRI representation

Itzik Malkiel, Gony Rosenman, Lior Wolf, Talma Hendler

Research output: Contribution to journalConference articlepeer-review

2 Scopus citations

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.

Original languageEnglish
Pages (from-to)895-913
Number of pages19
JournalProceedings of Machine Learning Research
Volume172
StatePublished - 2022
Event5th International Conference on Medical Imaging with Deep Learning, MIDL 2022 - Zurich, Switzerland
Duration: 6 Jul 20228 Jul 2022

Funding

FundersFunder number
Horizon 2020 Framework ProgrammeERC CoG 725974
European Research Council
Israel Science Foundation2923/20

    Keywords

    • Self-supervision
    • Transformers
    • fMRI

    Fingerprint

    Dive into the research topics of 'Self-Supervised Transformers for fMRI representation'. Together they form a unique fingerprint.

    Cite this