Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by

Same author

Using deep learning to identify inherited retinal diseases based on wide-field retinal imaging data.

PloS one·2026

Same author

Functional brain-to-brain transformation without shared stimuli.

NeuroImage·2026

Same author

Correction: A blood test-based machine learning model for predicting lung cancer risk.

Frontiers in medicine·2025

Same author

XVertNet: Unsupervised Contrast Enhancement of Vertebral Structures with Dynamic Self-Tuning Guidance and Multi-Stage Analysis.

Journal of imaging informatics in medicine·2025

Same author

A blood test-based machine learning model for predicting lung cancer risk.

Frontiers in medicine·2025

Same author

Effects of Walking on Anticipatory Brain Processing During a Concurrent Cognitive Task.

Psychophysiology·2025

Same journal

Investigating the Neural Origins of Ear-EEG: A Correlation Study Using Scalp EEG Source Reconstruction.

NeuroImage·2026

Same journal

Hysteresis effects in visual and auditory perception and the comparison of underlying neural mechanisms - an EEG study.

NeuroImage·2026

Same journal

Short-term audio-tactile training affects cortical auditory speech-envelope tracking for incongruent but not congruent stimuli.

NeuroImage·2026

Same journal

Dissociable Neurocognitive Mechanisms of State and Trait Anxiety in Working Memory: Threat-Induced Alterations in Decision Dynamics and Attenuation of Large-Scale Network Reconfiguration.

NeuroImage·2026

Same journal

Neuro-Ocular Amyloid Characterization in Alzheimer's Disease via Cross-Site PET-MRI and Hierarchical Cross-Attention Driven Multimodal Representation Learning.

NeuroImage·2026

Same journal

Whole-brain network dynamics underlying intolerance of uncertainty.

NeuroImage·2026

See all related articles

Search research articles

Related Experiment Video

Updated: Sep 28, 2025

Large-scale Reconstructions and Independent, Unbiased Clustering Based on Morphological Metrics to Classify Neurons in Selective Populations

Large-scale Reconstructions and Independent, Unbiased Clustering Based on Morphological Metrics to Classify Neurons in Selective Populations

Published on: February 15, 2017

Self-supervised Natural Image Reconstruction and Large-scale Semantic Classification from Brain Activity.

Guy Gaziv¹, Roman Beliy¹, Niv Granot¹

¹Dept. of Computer Science and Applied Math, Weizmann Institute of Science, Rehovot, Israel.

|March 28, 2022

Summary

This summary is machine-generated.

This study introduces a self-supervised method for reconstructing images from fMRI data and classifying semantic categories. The approach enables accurate image reconstruction and large-scale semantic classification, even for novel categories, without explicit supervision.

Keywords:

Self-Supervised learning, Decoding, Encoding, fMRI, Image reconstruction, Classification vision

More Related Videos

Author Spotlight: Advancing 3D Cytoarchitecture Analysis - Rapid Volumetric Reconstruction of the Human Brain

Author Spotlight: Advancing 3D Cytoarchitecture Analysis - Rapid Volumetric Reconstruction of the Human Brain

Published on: January 26, 2024

Author Spotlight: Bridging Gaps in Anatomy and Establishing a Foundation for Algorithmic Studies

Author Spotlight: Bridging Gaps in Anatomy and Establishing a Foundation for Algorithmic Studies

Published on: December 15, 2023

Related Experiment Videos

Last Updated: Sep 28, 2025

Large-scale Reconstructions and Independent, Unbiased Clustering Based on Morphological Metrics to Classify Neurons in Selective Populations

Large-scale Reconstructions and Independent, Unbiased Clustering Based on Morphological Metrics to Classify Neurons in Selective Populations

Published on: February 15, 2017

Author Spotlight: Advancing 3D Cytoarchitecture Analysis - Rapid Volumetric Reconstruction of the Human Brain

Author Spotlight: Advancing 3D Cytoarchitecture Analysis - Rapid Volumetric Reconstruction of the Human Brain

Published on: January 26, 2024

Author Spotlight: Bridging Gaps in Anatomy and Establishing a Foundation for Algorithmic Studies

Author Spotlight: Bridging Gaps in Anatomy and Establishing a Foundation for Algorithmic Studies

Published on: December 15, 2023

Area of Science:

Neuroscience
Computer Vision
Machine Learning

Background:

Reconstructing natural images from fMRI data is difficult due to limited paired image-fMRI data.
Decoding semantic categories from brain activity (fMRI) is a significant challenge.

Purpose of the Study:

To develop a novel self-supervised approach for fMRI-to-image reconstruction and semantic classification.
To overcome the limitations of scarce paired data in brain imaging research.

Main Methods:

Utilized a cycle consistency approach between image-to-fMRI and fMRI-to-image deep neural networks.
Trained the reconstruction network on unpaired natural images across diverse semantic categories.
Integrated high-level perceptual losses with self-supervised training.

Main Results:

Achieved state-of-the-art fMRI-to-image reconstruction.
Demonstrated the first large-scale semantic classification from fMRI responses.
Enabled classification of never-before-seen semantic classes without prior labels.
Showcased unprecedented image reconstruction from fMRI for novel images.

Conclusions:

The self-supervised method significantly advances fMRI-based image reconstruction and semantic understanding.
The approach demonstrates biological consistency, offering a powerful tool for brain decoding.
This work opens new avenues for large-scale semantic analysis of brain activity.