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: Apr 25, 2026

Creating Objects and Object Categories for Studying Perception and Perceptual Learning

Creating Objects and Object Categories for Studying Perception and Perceptual Learning

Published on: November 2, 2012

Cycle Diffusion Model for Counterfactual Image Generation.

Fangrui Huang¹, Alan Wang¹, Binxu Li¹

¹Stanford University, Stanford CA 94305, USA.

Predictive Intelligence in Medicine. PRIME (Workshop)

|April 24, 2026

Summary

This summary is machine-generated.

Related Concept Videos

Carrier Generation and Recombination

Carrier Generation and Recombination

Carrier generation is the process by which electron-hole pairs (EHPs) are created within the semiconductor. In direct-bandgap semiconductors, such as gallium arsenide (GaAs), this occurs efficiently when energy absorption prompts valence electrons to leap into the conduction band, leaving behind holes.
This process is given by the generation rate G and is efficient due to the conservation of momentum between the valence band maximum and conduction band minimum.
Indirect generation involves an...

You might also read

Related Articles

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

Sort by

Same author

Deep Learning for Brain MRI Artifact Correction: Current Challenges and Future Directions.

Bioengineering (Basel, Switzerland)·2026

Same author

A Rare Case Reveals Important Consideration of the Diagnosis of Giant Cell Arteritis in Patients with Bilateral Painful Optic Perineuritis.

Reports (MDPI)·2026

Same author

A framework of digital biomarkers for neurodegenerative diseases.

Nature reviews bioengineering·2026

Same author

SocialGen: Modeling Multi-Human Social Interaction with Language Models.

Proceedings. International Conference on 3D Vision·2026

Same author

Achieving high-quality and safe compost: a study on multi-optimization of a non-linear system using machine learning.

Bioresource technology·2026

Same author

The Language of Motion: Unifying Verbal and Non-verbal Language of 3D Human Motion.

Proceedings. IEEE Computer Society Conference on Computer Vision and Pattern Recognition·2026

Same journal

Neurocognitive Latent Space Regularization for Multi-Label Diagnosis from MRI.

Predictive Intelligence in Medicine. PRIME (Workshop)·2025

Same journal

Spectral Graph Sample Weighting for Interpretable Sub-cohort Analysis in Predictive Models for Neuroimaging.

Predictive Intelligence in Medicine. PRIME (Workshop)·2024

Same journal

SynthA1c: Towards Clinically Interpretable Patient Representations for Diabetes Risk Stratification.

Predictive Intelligence in Medicine. PRIME (Workshop)·2024

Same journal

Imputing Brain Measurements Across Data Sets via Graph Neural Networks.

Predictive Intelligence in Medicine. PRIME (Workshop)·2023

Same journal

Bridging the Gap between Deep Learning and Hypothesis-Driven Analysis via Permutation Testing.

Predictive Intelligence in Medicine. PRIME (Workshop)·2022

Same journal

Multiple Instance Neuroimage Transformer.

Predictive Intelligence in Medicine. PRIME (Workshop)·2022

See all related articles

Cycle Diffusion Models (CDM) improve medical image synthesis by ensuring generated images match original data. This enhances realism and accuracy for applications like data augmentation and disease modeling.

Area of Science:

Medical Imaging
Artificial Intelligence
Computer Vision

Background:

Deep generative models excel at medical image synthesis but struggle with conditioning faithfulness and realism.
Direct and counterfactual generation of high-quality synthetic medical images remains a significant challenge.

Purpose of the Study:

To introduce a novel cycle training framework to fine-tune diffusion models for enhanced medical image generation.
To improve conditioning adherence and synthetic image realism in diffusion models.

Main Methods:

Developed the Cycle Diffusion Model (CDM), a framework incorporating cycle constraints to enforce consistency between generated and original images.
Fine-tuned diffusion models using the CDM approach on a combined 3D brain MRI dataset (ABCD, HCP, ADNI, PPMI).

Keywords:

Counterfactual Generation Generative Model Neuroimaging

Related Experiment Videos

Last Updated: Apr 25, 2026

Creating Objects and Object Categories for Studying Perception and Perceptual Learning

Creating Objects and Object Categories for Studying Perception and Perceptual Learning

Published on: November 2, 2012

Main Results:

CDM significantly improved conditioning accuracy compared to baseline diffusion models.
Enhanced synthetic image realism and quality, as evidenced by improved FID and SSIM scores.
Demonstrated reliable direct and counterfactual generation capabilities.

Conclusions:

The cycle strategy in CDM is an effective method for refining diffusion-based medical image generation.
CDM shows promise for applications in medical data augmentation, counterfactual analysis, and disease progression modeling.