Self-Supervised Transformers for fMRI representation
This work addresses fMRI analysis for medical and neuroscience applications, but it appears incremental as it adapts existing Transformer and self-supervised methods to a specific domain.
The paper tackles the problem of analyzing fMRI data by introducing TFF, a Transformer framework that uses self-supervised pre-training and fine-tuning, achieving state-of-the-art performance on tasks like age and gender prediction and schizophrenia recognition.
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.