Learning Sequential Information in Task-based fMRI for Synthetic Data Augmentation
This work addresses data scarcity in medical imaging for researchers and clinicians, but it is incremental as it adapts existing models to a specific domain.
The paper tackled the problem of insufficient training data in medical image analysis by proposing a method to generate synthetic task-based fMRI sequences for data augmentation, showing that these synthetic images effectively improved autism spectrum disorder classification.
Insufficiency of training data is a persistent issue in medical image analysis, especially for task-based functional magnetic resonance images (fMRI) with spatio-temporal imaging data acquired using specific cognitive tasks. In this paper, we propose an approach for generating synthetic fMRI sequences that can then be used to create augmented training datasets in downstream learning tasks. To synthesize high-resolution task-specific fMRI, we adapt the $α$-GAN structure, leveraging advantages of both GAN and variational autoencoder models, and propose different alternatives in aggregating temporal information. The synthetic images are evaluated from multiple perspectives including visualizations and an autism spectrum disorder (ASD) classification task. The results show that the synthetic task-based fMRI can provide effective data augmentation in learning the ASD classification task.