EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Optimized AI-based neural decoding from BOLD fMRI signal for analyzing visual and semantic ROIs in the human visual system

Lorenzo Veronese iD, Andrea Moglia iD, Nicolò Pecco iD, Pasquale Anthony Della Rosa iD, Paola Scifo iD, Luca Mainardi iD, Pietro Cerveri iD

Journal of Neural Engineering · 2025

DOI: 10.1088/1741-2552/adfbc2 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Neural Engineering, 2025. Verfasst von Lorenzo Veronese und 6 weiteren Autor:innen. Beteiligte Einrichtung: Department of Electronics, Information and Bioengineering, Politecnico di Milano, Milan, Italy. Hauptthemen laut MEDLINE: Magnetic Resonance Imaging, Semantics, Visual Perception, Brain Mapping. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 45 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: P.E. FUTURE ARTIFICIAL INTELLIGENCE RESEARCH (FAIR), Italian Ministry of Research and University.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Objective . AI-based neural decoding reconstructs visual perception by leveraging generative models to map brain activity measured through functional magnetic resonance imaging (fMRI) into the observed visual stimulus. Approach . Traditionally, ridge linear models transform fMRI into a latent space, which is then decoded using variational autoencoders (VAE) or LDMs. Owing to the complexity and noisiness of fMRI data, newer approaches split the reconstruction into two sequential stages, the first one providing a rough visual approximation using a VAE, the second one incorporating semantic information through the adoption of LDM guided by contrastive language-image pre-training (CLIP) embeddings. This work addressed some key scientific and technical gaps of the two-stage neural decoding by: (1) implementing a gated recurrent unit-based architecture to establish a non-linear mapping between the fMRI signal and the VAE latent space, (2) optimizing the dimensionality of the VAE latent space, (3) systematically evaluating the contribution of the first reconstruction stage, and (4) analyzing the impact of different brain regions of interest (ROIs) on reconstruction quality. Main results . Experiments on the NSD, containing 73 000 unique natural images, along with fMRI of eight subjects, demonstrated that the proposed architecture maintained competitive performance while reducing the complexity of its first stage by 85%. The sensitivity analysis showcased that the first reconstruction stage is essential for preserving high structural similarity in the final reconstructions. Restricting analysis to semantic ROIs, while excluding early visual areas, diminished visual coherence, preserving semantics though. The inter-subject repeatability across ROIs was about 92% and 98% for visual and sematic metrics, respectively. Significance . This study represents a key step toward optimized neural decoding architectures leveraging non-linear models for stimulus prediction. Sensitivity analysis highlighted the interplay between the two reconstruction stages, while ROI-based analysis provided strong evidence that the two-stage AI model reflects the brain’s hierarchical processing of visual information.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Magnetic Resonance ImagingSemanticsVisual PerceptionBrain MappingArtificial IntelligenceVisual CortexHumansPhotic StimulationMaleAdultFemaleYoung AdultBrain

Stichwörter der Autor:innen

fMRI imagerygenerative artificial intelligenceneural decodingvisual stimuls

Autor:innen und Institutionen

  • Department of Electronics, Information and Bioengineering, Politecnico di Milano, Milan, Italy.
  • Department of Neuroradiology, Istituto di Ricovero e Cura a Carattere Scientifico (IRCCS), Ospedale San Raffaele, Milan, Italy.
  • Department of Nuclear Medicine, Istituto di Ricovero e Cura a Carattere Scientifico (IRCCS), Ospedale San Raffaele, Milan, Italy.
  • Department of Industrial and Information Engineering, Universitá di Pavia, Pave, Italy.

ORCID-Profile: Lorenzo Veronese, Andrea Moglia, Nicolò Pecco, Pasquale Anthony Della Rosa, Paola Scifo, Luca Mainardi, Pietro Cerveri

Förderung

  • P.E. FUTURE ARTIFICIAL INTELLIGENCE RESEARCH (FAIR), Italian Ministry of Research and University

Zitieren

APA

Veronese, L., Moglia, A., Pecco, N., Anthony Della Rosa, P., Scifo, P., Mainardi, L., & Cerveri, P. (2025). Optimized AI-based neural decoding from BOLD fMRI signal for analyzing visual and semantic ROIs in the human visual system. Journal of Neural Engineering. https://doi.org/10.1088/1741-2552/adfbc2

Vancouver

Veronese L, Moglia A, Pecco N, Anthony Della Rosa P, Scifo P, Mainardi L, et al. Optimized AI-based neural decoding from BOLD fMRI signal for analyzing visual and semantic ROIs in the human visual system. Journal of Neural Engineering. 2025. doi:10.1088/1741-2552/adfbc2

BibTeX
@article{Veronese2025,
  author = {Veronese, Lorenzo and Moglia, Andrea and Pecco, Nicolò and Anthony Della Rosa, Pasquale and Scifo, Paola and Mainardi, Luca and Cerveri, Pietro},
  title = {Optimized AI-based neural decoding from BOLD fMRI signal for analyzing visual and semantic ROIs in the human visual system},
  journal = {Journal of Neural Engineering},
  year = {2025},
  doi = {10.1088/1741-2552/adfbc2}
}
Kostenlos starten →