Peaks2Image: Reconstructing fMRI Statistical Maps from Peaks

Raphaël Meudec, Jérôme Dockès, Demian Wassermann, Bertrand Thirion

TL;DR: Peaks2Image allows the reconstruction of statistical maps from coordinates in neuroscientific studies, and leverage them to decode any concept from the studies vocabulary.

Abstract: Neuroscience is striving to overcome the lack of power due to the small sample size of standard studies. An important step forward has been the creation of large-scale public image repositories, such as NeuroVault. Such repositories enable comparing images across studies and automatically associating them with cognitive terms. Yet, this type of meta-analysis faces a major roadblock: the scarcity and inconsistency of image annotations and metadata. Another resource containing rich annotations is the neuroscientific literature. However it only yields a handful of brain-space coordinates per publication, those of the main activity peaks reported in each study. In this work, we propose Peaks2Image, a neuralnetwork approach to reconstructing continuous spatial representations of brain activity from peak activation tables. Using reconstructions of studies published in the neuroscientific literature, we train a decoder using tf-idf features as labels, leading to a much broader set of decoded terms than current image-based studies. We validate the decoder on 43,000 NeuroVault images, successfully decoding 58 out of 81 concepts in a zero-shot setting.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics

Submission Guidelines: Yes

Please Choose The Closest Area That Your Submission Falls Into: Neuroscience and Cognitive Science (e.g., neural coding, brain-computer interfaces)