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

Search research articles

Related Experiment Video

Updated: May 28, 2026

Generating the Transcriptional Regulation View of Transcriptomic Features for Prediction Task and Dark Biomarker Detection on Small Datasets

Generating the Transcriptional Regulation View of Transcriptomic Features for Prediction Task and Dark Biomarker Detection on Small Datasets

Published on: March 1, 2024

TADM-CGAN: a resting-state to task activation map prediction framework using temporal attention-driven diffusion

Sasideep Pasumarthi¹, Nitya Tiwari¹, Himanshu Padole²

¹School of Electrical and Computer Sciences, IIT Bhubaneswar, Khordha, Odisha, 752050, India.

Scientific Reports

|May 26, 2026

Summary

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

Cognitive and personality trait prediction using activation maps and temporal dynamics derived from resting-state fMRI.

Scientific reports·2026

Same author

Functional relevance of piRNA-PIWI axis in cancers: diagnostic and therapeutic avenues.

Cell cycle (Georgetown, Tex.)·2026

Same author

GEMReg: a spatio-temporal grayordinate ensemble modelling framework for predicting task activation maps from resting-state fMRI.

Frontiers in neuroscience·2025

See all related articles

Predicting brain activity from resting-state fMRI is challenging. Our new TADM-CGAN model uses temporal and spatial data to accurately predict task activation maps from resting-state scans.

Area of Science:

Computational neuroimaging
Neuroscience
Machine learning

Background:

Predicting task-induced brain activation from resting-state fMRI (rs-fMRI) is difficult due to challenges in modeling temporal and spatial neural activity.
Existing methods often use parcel-based modeling, overlooking long-range temporal interactions and nonlinear rs-fMRI signal dynamics.

Purpose of the Study:

To introduce TADM-CGAN, a novel two-stage, grayordinate-level cascaded architecture for inferring task activation maps directly from rs-fMRI time series.
To fully leverage both temporal and spatial characteristics of rs-fMRI data for improved prediction accuracy.

Main Methods:

A multi-head temporal attention-driven diffusion model (TADM) generates temporal embeddings for each grayordinate, capturing rs-fMRI time series dependencies.

Related Experiment Videos

Last Updated: May 28, 2026

Generating the Transcriptional Regulation View of Transcriptomic Features for Prediction Task and Dark Biomarker Detection on Small Datasets

Generating the Transcriptional Regulation View of Transcriptomic Features for Prediction Task and Dark Biomarker Detection on Small Datasets

Published on: March 1, 2024

Grayordinate-specific regression models predict preliminary activation values using these temporal features.

A principal component analysis (PCA)-conditioned conditional generative adversarial network (PCA-CGAN) refines predictions, constrained to a low-rank subspace and enhanced with an activation fidelity loss (AFL).

Main Results:

The TADM-CGAN framework demonstrates superior performance compared to existing task activation map prediction methods.
Consistent outperformance was observed across diverse task contrasts and datasets, indicating robustness and generalizability.

Conclusions:

The proposed cascaded TADM-CGAN architecture effectively predicts task activation maps from rs-fMRI.
This method offers a robust and generalizable approach for computational neuroimaging applications.