Anatomically-Informed Data Augmentation for functional MRI with Applications to Deep Learning
This work addresses the challenge of small datasets for researchers using fMRI in medical AI applications, though it is incremental as it adapts augmentation techniques from natural images to a specific domain.
The paper tackles the problem of limited dataset sizes in deep learning for functional neuroimaging by proposing an anatomically-informed data augmentation method for fMRI, which results in a 26% improvement in predicting antidepressant treatment response compared to using unaugmented data.
The application of deep learning to build accurate predictive models from functional neuroimaging data is often hindered by limited dataset sizes. Though data augmentation can help mitigate such training obstacles, most data augmentation methods have been developed for natural images as in computer vision tasks such as CIFAR, not for medical images. This work helps to fills in this gap by proposing a method for generating new functional Magnetic Resonance Images (fMRI) with realistic brain morphology. This method is tested on a challenging task of predicting antidepressant treatment response from pre-treatment task-based fMRI and demonstrates a 26% improvement in performance in predicting response using augmented images. This improvement compares favorably to state-of-the-art augmentation methods for natural images. Through an ablative test, augmentation is also shown to substantively improve performance when applied before hyperparameter optimization. These results suggest the optimal order of operations and support the role of data augmentation method for improving predictive performance in tasks using fMRI.