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: Oct 4, 2025

Concurrent EEG and Functional MRI Recording and Integration Analysis for Dynamic Cortical Activity Imaging

Concurrent EEG and Functional MRI Recording and Integration Analysis for Dynamic Cortical Activity Imaging

Published on: June 30, 2018

TR-GAN: Multi-Session Future MRI Prediction With Temporal Recurrent Generative Adversarial Network.

Chen-Chen Fan, Liang Peng, Tian Wang

IEEE Transactions on Medical Imaging

|February 11, 2022

Summary

This summary is machine-generated.

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

A Muscle-Mimetic Core-Sheath Composite Yarn Scaffold for In-Body Tissue Induction and Regeneration of Small-Diameter Vascular Grafts.

Advanced healthcare materials·2026

Same author

Plant-derived extracellular vesicles for drug delivery: current and future.

Regenerative biomaterials·2026

Same author

Zhi-Zi-Chi Decoction Alleviates Depressive-like Behaviors by Regulating Gut Microbiota and Targeting the AMPK/PI3K-TOR Pathway via Its Metabolite Protocatechuic Acid.

Pharmaceuticals (Basel, Switzerland)·2026

Same author

Active Constituents and Mechanisms of Xinshubao Tablets in Coronary Vasorelaxation.

Pharmaceuticals (Basel, Switzerland)·2026

Same author

Application and Molecular Modification of Enzyme in Textile Degumming.

Applied biochemistry and biotechnology·2026

Same author

The Role of Neutrophils and NETosis in Diseases: The Implications for Therapy.

MedComm·2026

Same journal

UniOCTSeg++: Refined Hierarchical Prompt Strategy and Bi-directional Progressive Consistency Learning for Universal Retinal Layer Segmentation in OCT.

IEEE transactions on medical imaging·2026

Same journal

Volumetric Functional Ultrasound Imaging in Macaques.

IEEE transactions on medical imaging·2026

Same journal

MUST: Multi-style virtual staining with incomplete pairs.

IEEE transactions on medical imaging·2026

Same journal

BrainCL: Transformer-Based Brain Network Contrastive Learning with Multi-Order Topology and Salience Masking.

IEEE transactions on medical imaging·2026

Same journal

LLM-enhanced Neuron Segmentation and Reconstruction in Complex Mouse Brain Images.

IEEE transactions on medical imaging·2026

Same journal

Matrixed-Spectrum Decomposition Accelerated Linear Boltzmann Transport Equation Solver for Fast Scatter Correction in Multi-Spectral CT.

IEEE transactions on medical imaging·2026

See all related articles

This study introduces a new Temporal Recurrent Generative Adversarial Network (TR-GAN) to fill gaps in Alzheimer's disease (AD) MRI datasets. TR-GAN effectively generates missing MRI sessions, improving diagnostic accuracy for AD and MCI classification.

Area of Science:

Neuroimaging
Artificial Intelligence
Medical Diagnostics

Background:

Magnetic Resonance Imaging (MRI) is crucial for Alzheimer's disease (AD) diagnosis.
Deep learning, particularly Convolutional Neural Networks (CNNs), has advanced MRI analysis.
Fragmented MRI datasets due to participant dropout pose a significant challenge for longitudinal studies.

Purpose of the Study:

To propose a novel Temporal Recurrent Generative Adversarial Network (TR-GAN) for completing missing MRI sessions in longitudinal datasets.
To address the limitations of existing methods in generating future or variable-length MRI data.
To enhance the quality and completeness of MRI datasets for improved AD diagnosis.

Main Methods:

Development of TR-GAN, a generative adversarial network with recurrent connections to handle variable input sequence lengths.

More Related Videos

Reliable Acquisition of Electroencephalography Data during Simultaneous Electroencephalography and Functional MRI

Reliable Acquisition of Electroencephalography Data during Simultaneous Electroencephalography and Functional MRI

Published on: March 19, 2021

Related Experiment Videos

Last Updated: Oct 4, 2025

Concurrent EEG and Functional MRI Recording and Integration Analysis for Dynamic Cortical Activity Imaging

Concurrent EEG and Functional MRI Recording and Integration Analysis for Dynamic Cortical Activity Imaging

Published on: June 30, 2018

Reliable Acquisition of Electroencephalography Data during Simultaneous Electroencephalography and Functional MRI

Reliable Acquisition of Electroencephalography Data during Simultaneous Electroencephalography and Functional MRI

Published on: March 19, 2021

Implementation of a multiple scale & location (MSL) module and a SWAP module to enhance focus on detailed MRI data.

Training and evaluation of TR-GAN on longitudinal MRI datasets, comparing its performance against other GAN architectures.

Main Results:

TR-GAN demonstrated superior performance across all evaluation metrics on two datasets compared to existing GAN methods.
The model successfully generated future MRI sessions with variable lengths, overcoming limitations of prior approaches.
Expansion of the Whole MRI dataset using TR-GAN led to a 3.61% increase in AD/CN/MCI classification accuracy and a 4.00% increase in stable MCI vs. progressive MCI classification accuracy.

Conclusions:

TR-GAN offers an effective solution for completing fragmented longitudinal MRI datasets.
The proposed method significantly improves the accuracy of classifying Alzheimer's disease and its subtypes.
TR-GAN has the potential to enhance the utility of MRI data in clinical diagnosis and research for neurodegenerative diseases.