Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

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

In Situ Electroactive Bacteria-Activated Nanozyme for Amplifying Chemodynamic Therapy of Solid Tumors.

Nano letters·2026
Same author

Adaptive optical correction for in vivo two-photon fluorescence microscopy with neural fields.

Nature methods·2026
Same author

Continuity fields enhance visual perception through positive serial dependence.

Nature reviews psychology·2026
Same author

Antigen-Enriched Tumor-Dendritic Cell Fusion Membrane-Coated Metal-Phenolic Nanovaccine Enables Dual T-Cell Activation for Robust Cancer Immunotherapy.

Advanced healthcare materials·2026
Same author

Integration of affective cues in context-rich and dynamic scenes varies across individuals.

Nature communications·2025
Same author

Slow change blindness from serial dependence.

bioRxiv : the preprint server for biology·2025

Related Experiment Video

Updated: Aug 11, 2025

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
04:48

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

2.9K

Controllable Medical Image Generation via Generative Adversarial Networks.

Zhihang Ren1, Stella X Yu1, David Whitney1

  • 1UC Berkeley / ICSI; Berkeley, California, USA.

IS&T International Symposium on Electronic Imaging
|February 6, 2023
PubMed
Summary

Generative Adversarial Networks (GAN) create realistic medical image stimuli for studying perceptual biases in tumor detection. This technology enables controlled experiments to improve diagnostic accuracy for radiologists and pathologists.

More Related Videos

Generating Strictly Controlled Stimuli for Figure Recognition Experiments
05:39

Generating Strictly Controlled Stimuli for Figure Recognition Experiments

Published on: March 18, 2019

5.3K
Image-guided, Laser-based Fabrication of Vascular-derived Microfluidic Networks
10:53

Image-guided, Laser-based Fabrication of Vascular-derived Microfluidic Networks

Published on: January 3, 2017

10.0K

Related Experiment Videos

Last Updated: Aug 11, 2025

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
04:48

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

2.9K
Generating Strictly Controlled Stimuli for Figure Recognition Experiments
05:39

Generating Strictly Controlled Stimuli for Figure Recognition Experiments

Published on: March 18, 2019

5.3K
Image-guided, Laser-based Fabrication of Vascular-derived Microfluidic Networks
10:53

Image-guided, Laser-based Fabrication of Vascular-derived Microfluidic Networks

Published on: January 3, 2017

10.0K

Area of Science:

  • Medical Imaging
  • Computer Vision
  • Psychophysics

Background:

  • Radiologists and pathologists face high-stakes perceptual decisions in diagnosing conditions like cancer.
  • Human perceptual biases can significantly impact patient outcomes, necessitating bias mitigation strategies.
  • Previous studies on perceptual biases used artificial stimuli, limiting their real-world applicability.

Purpose of the Study:

  • To develop a method for generating realistic medical image stimuli for psychophysical and computer vision research.
  • To create controllable, tumor-like image datasets with specified shapes and textures.
  • To enable more authentic studies on perceptual biases in medical image interpretation.

Main Methods:

  • Utilized Generative Adversarial Networks (GAN) to synthesize medical image data.
  • Developed a model capable of generating tumor-like stimuli with controlled shapes and realistic textures.
  • Validated the authenticity and controllability of the generated stimuli through experiments.

Main Results:

  • Successfully generated vivid and realistic medical image stimuli.
  • Demonstrated precise control over the shape and texture of generated tumor-like images.
  • Experimental validation confirmed the authenticity of the GAN-generated stimuli.

Conclusions:

  • Generative Adversarial Networks (GAN) offer a powerful tool for creating realistic medical image stimuli.
  • This approach overcomes limitations of artificial stimuli in perceptual bias research.
  • The developed model facilitates controlled psychophysical and computer vision studies, potentially improving diagnostic accuracy.