Few-shot Decoding of Brain Activation Maps
This work addresses the challenge of analyzing neuroimaging data with scarce samples, which could benefit clinical and cognitive neuroscience applications like biomarker identification.
The authors tackled the problem of decoding brain activation maps with limited training data by adapting few-shot learning methods to neuroimaging, creating a benchmark dataset and showing that these methods can efficiently decode brain signals using few examples.
Few-shot learning addresses problems for which a limited number of training examples are available. So far, the field has been mostly driven by applications in computer vision. Here, we are interested in adapting recently introduced few-shot methods to solve problems dealing with neuroimaging data, a promising application field. To this end, we create a neuroimaging benchmark dataset for few-shot learning and compare multiple learning paradigms, including meta-learning, as well as various backbone networks. Our experiments show that few-shot methods are able to efficiently decode brain signals using few examples, which paves the way for a number of applications in clinical and cognitive neuroscience, such as identifying biomarkers from brain scans or understanding the generalization of brain representations across a wide range of cognitive tasks.