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

Synthetic Biology

Synthetic Biology

Synthetic biology is an interdisciplinary science that involves using principles from disciplines such as engineering, molecular biology, cell biology, and systems biology. It involves remodeling existing organisms from nature or constructing completely new synthetic organisms for applications such as protein or enzyme production, bioremediation, value-added macromolecule production, and the addition of desirable traits to crops, to name a few.
Golden rice
Golden rice is a genetically modified...

Search research articles

Home
Synthetic Scientific Image Generation With Vae, Gan, And Diffusion Model Architectures

Home
Synthetic Scientific Image Generation With Vae, Gan, And Diffusion Model Architectures

Related Experiment Video

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

Synthetic Scientific Image Generation with VAE, GAN, and Diffusion Model Architectures

Zineb Sordo¹, Eric Chagnon¹, Zixi Hu¹

¹Applied Math and Computational Research Division, Lawrence Berkeley National Laboratory, Berkeley, CA 94720, USA.

Journal of Imaging

|August 27, 2025

View abstract on PubMed

Summary

This summary is machine-generated.

Generative AI models like GANs excel at creating realistic scientific images, but validating their accuracy requires expert input. Further research is needed to address challenges in interpretability and computational cost for broader scientific applications.

Keywords:

Generative Adversarial Networks diffusion generative AI image generation synthetic data

More Related Videos

Author Spotlight: Development of an Automated Camera-Based System for Real-Time Blast Overpressure Monitoring and TBI Risk Assessment in Military Training

Author Spotlight: Development of an Automated Camera-Based System for Real-Time Blast Overpressure Monitoring and TBI Risk Assessment in Military Training

Published on: December 6, 2024

Generation of Shear Adhesion Map Using SynVivo Synthetic Microvascular Networks

Generation of Shear Adhesion Map Using SynVivo Synthetic Microvascular Networks

Published on: May 25, 2014

Related Experiment Videos

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

Author Spotlight: Development of an Automated Camera-Based System for Real-Time Blast Overpressure Monitoring and TBI Risk Assessment in Military Training

Author Spotlight: Development of an Automated Camera-Based System for Real-Time Blast Overpressure Monitoring and TBI Risk Assessment in Military Training

Published on: December 6, 2024

Generation of Shear Adhesion Map Using SynVivo Synthetic Microvascular Networks

Generation of Shear Adhesion Map Using SynVivo Synthetic Microvascular Networks

Published on: May 25, 2014

Area of Science:

Scientific Imaging
Artificial Intelligence
Data Synthesis

Background:

Generative AI (genAI) offers powerful capabilities for synthesizing complex image data.
Scientific imaging applications can benefit from novel image generation techniques.

Purpose of the Study:

To conduct a comparative analysis of leading generative AI architectures for scientific image synthesis.
To evaluate Variational Autoencoders (VAEs), Generative Adversarial Networks (GANs), and Diffusion Models.

Main Methods:

Evaluation on domain-specific datasets (microCT scans, plant roots).
Integration of quantitative metrics (SSIM, LPIPS, FID, CLIPScore) and qualitative expert assessments.
Analysis of foundational principles, architectural advancements, and practical trade-offs.

Main Results:

Generative Adversarial Networks (GANs), especially StyleGAN, demonstrated high perceptual quality and structural coherence.
Diffusion models showed high realism and semantic alignment but faced challenges in balancing visual fidelity with scientific accuracy.
Limitations of standard quantitative metrics in assessing scientific relevance were identified, highlighting the need for expert validation.

Conclusions:

Generative AI holds significant potential for scientific data augmentation, simulation, and hypothesis generation.
Key challenges include model interpretability, computational expense, and robust verification protocols.
Domain-expert validation is crucial for ensuring the scientific relevance of generated images.