On the benefits of self-taught learning for brain decoding

Context: We study the benefits of using a large public neuroimaging database composed of functional magnetic resonance imaging (fMRI) statistic maps, in a self-taught learning framework, for improving brain decoding on new tasks. First, we leverage the NeuroVault database to train, on a selection of relevant statistic maps, a convolutional autoencoder to reconstruct these maps. Then, we use this trained encoder to initialize a supervised convolutional neural network to classify tasks or cognitive processes of unseen statistic maps from large collections of the NeuroVault database. Results: We show that such a self-taught learning process always improves the performance of the classifiers, but the magnitude of the benefits strongly depends on the number of samples available both for pretraining and fine-tuning the models and on the complexity of the targeted downstream task. Conclusion: The pretrained model improves the classification performance and displays more generalizable features, less sensitive to individual differences.

Automated summary

This study examines the advantages of using a large public neuroimaging database in a self-taught learning framework to enhance brain decoding for new tasks. The researchers show that training a convolutional autoencoder and using a pretrained model to classify unknown tasks improves the performance of the classifiers.