EUVIMEDEUVIMED entdecken
MetaanalyseOpen Access · CC BY 4.0

Peaks2Image: Reconstructing fMRI maps from stereotactic coordinates to enhance cognitive meta-analysis

Raphaël Meudec iD, Jérôme Dockès, Fateme Ghayem, Demian Wassermann, Bertrand Thirion iD

Imaging Neuroscience · 2026

DOI: 10.1162/imag.a.1367 ↗

Kurz gefasst

Metaanalyse in der Zeitschrift Imaging Neuroscience, 2026. Verfasst von Raphaël Meudec und 4 weiteren Autor:innen. Beteiligte Einrichtung: Université Paris-Saclay, Inria, CEA, Palaiseau, France. Hauptthemen laut MEDLINE: Magnetic Resonance Imaging, Brain Mapping, Brain, Image Processing, Computer-Assisted. Die Arbeit nennt 46 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

To integrate novel findings and reach a consensus on the neural correlates of cognitive functions, human neuroscientists have relied heavily on the literature to formulate, validate, or refine hypotheses. Since thousands of publications have reported the coordinates of regions identified in brain mapping, the community has largely performed meta-analyses based on these coordinates. A known problem with coordinate-based meta-analyses is that they rely on limited information from each publication, so terms appearing in few publications are not reliably mapped. Recently, the use of public images has stimulated meta-analysis, which has become possible due to the creation of large image repositories. NeuroVault is a prominent example of such a repository. These repositories allow researchers to compare images across publications, leading to image-based meta-analyses. However, image-based meta-analysis faces a major obstacle: the scarcity and inconsistency of image annotation and metadata. In this paper, we propose Peaks2Image, a neural network approach that reconstructs continuous spatial representations of brain activity from peak activation tables. Peaks2Image provides dense brain reconstructions that can be combined with extensive annotations from the neuroscience literature. We use these annotations to train a decoder with textual features as labels. This results in a much broader set of decoded terms than current image-based studies. We validated the decoder using 47,000 annotated images and successfully identified 91 out of 108 terms, with a model that was uniquely trained using the neuroscience literature.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Magnetic Resonance ImagingBrain MappingBrainImage Processing, Computer-AssistedCognitionMeta-Analysis as TopicHumansNeural Networks, ComputerStereotaxic Techniques

Stichwörter der Autor:innen

DiFuMocoordinate-based meta-analysisdecodingfMRIimage reconstructionset transformer

Autor:innen und Institutionen

  • Université Paris-Saclay, Inria, CEA, Palaiseau, France.

ORCID-Profile: Raphaël Meudec, Bertrand Thirion

Zitieren

APA

Meudec, R., Dockès, J., Ghayem, F., Wassermann, D., & Thirion, B. (2026). Peaks2Image: Reconstructing fMRI maps from stereotactic coordinates to enhance cognitive meta-analysis. Imaging Neuroscience. https://doi.org/10.1162/imag.a.1367

Vancouver

Meudec R, Dockès J, Ghayem F, Wassermann D, Thirion B. Peaks2Image: Reconstructing fMRI maps from stereotactic coordinates to enhance cognitive meta-analysis. Imaging Neuroscience. 2026. doi:10.1162/imag.a.1367

BibTeX
@article{Meudec2026,
  author = {Meudec, Raphaël and Dockès, Jérôme and Ghayem, Fateme and Wassermann, Demian and Thirion, Bertrand},
  title = {Peaks2Image: Reconstructing fMRI maps from stereotactic coordinates to enhance cognitive meta-analysis},
  journal = {Imaging Neuroscience},
  year = {2026},
  doi = {10.1162/imag.a.1367}
}
Kostenlos starten →