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

A WEEV 6K viroporin activates MLKL-dependent necroptosis to drive inflammatory injury.

Cell death discovery·2026
Same author

Orthogonal nanopores cross-validation for multiplex single-molecule profiling.

Chemical science·2026
Same author

Fatal abdominal compartment syndrome following mannitol bowel preparation in a patient with refractory Crohn's disease.

Journal of Crohn's & colitis·2026
Same author

VMP1 forms a Ca<sup>2+</sup> release channel essential for postnatal heartbeat.

Science advances·2026
Same author

RNF26 bridges ER stress and autophagy in the clearance of MERS envelope protein.

Virologica Sinica·2026
Same author

Structural basis for a central permeation pathway in the P2X1 receptor.

Cell discovery·2026

Related Experiment Video

Updated: Dec 15, 2025

Tracking the Mammary Architectural Features and Detecting Breast Cancer with Magnetic Resonance Diffusion Tensor Imaging
15:48

Tracking the Mammary Architectural Features and Detecting Breast Cancer with Magnetic Resonance Diffusion Tensor Imaging

Published on: December 15, 2014

22.9K

High-Resolution Breast MRI Reconstruction Using a Deep Convolutional Generative Adversarial Network.

Kun Sun1,2, Liangqiong Qu2, Chunfeng Lian2

  • 1Department of Radiology, Ruijin Hospital, Shanghai Jiaotong University School of Medicine, Shanghai, China.

Journal of Magnetic Resonance Imaging : JMRI
|July 14, 2020
PubMed
Summary
This summary is machine-generated.

Deep convolutional generative adversarial networks (DCGAN) can synthesize high-resolution breast MRI images from low-resolution scans, improving image quality and lesion detection. This AI approach offers potential for faster, high-quality medical imaging.

Keywords:
MRIbreastgenerative adversarial network

More Related Videos

Three-Dimensional Phase Resolved Functional Lung Magnetic Resonance Imaging
10:44

Three-Dimensional Phase Resolved Functional Lung Magnetic Resonance Imaging

Published on: June 21, 2024

952
Author Spotlight: Optimized Lung MRI Protocol with Computationally Efficient Reconstruction Methods
05:07

Author Spotlight: Optimized Lung MRI Protocol with Computationally Efficient Reconstruction Methods

Published on: September 6, 2024

614

Related Experiment Videos

Last Updated: Dec 15, 2025

Tracking the Mammary Architectural Features and Detecting Breast Cancer with Magnetic Resonance Diffusion Tensor Imaging
15:48

Tracking the Mammary Architectural Features and Detecting Breast Cancer with Magnetic Resonance Diffusion Tensor Imaging

Published on: December 15, 2014

22.9K
Three-Dimensional Phase Resolved Functional Lung Magnetic Resonance Imaging
10:44

Three-Dimensional Phase Resolved Functional Lung Magnetic Resonance Imaging

Published on: June 21, 2024

952
Author Spotlight: Optimized Lung MRI Protocol with Computationally Efficient Reconstruction Methods
05:07

Author Spotlight: Optimized Lung MRI Protocol with Computationally Efficient Reconstruction Methods

Published on: September 6, 2024

614

Area of Science:

  • Artificial Intelligence in Medical Imaging
  • Deep Learning for Image Synthesis
  • Radiology and Medical Diagnostics

Background:

  • Generative adversarial networks (GANs) show promise for creating high-resolution (HR) medical images, potentially reducing scan times.
  • Deep convolutional generative adversarial networks (DCGANs) are explored for their capability in medical image synthesis.

Purpose of the Study:

  • To evaluate the efficacy of DCGAN in generating HR pre- and postcontrast breast MRI images (HRpre and HRpost) from low-resolution (LR) counterparts (LRpre and LRpost).

Main Methods:

  • Retrospective analysis of prospectively acquired dynamic contrast-enhanced (DCE) MRI data from 224 subjects (200 training, 24 testing) using a 1.5T scanner.
  • Three radiologists independently assessed image quality, lesion conspicuity, and BI-RADS categories of original LR and generated HR images, using DCE MRI as ground truth.
  • Inter/intracorrelation coefficients (ICCs) and Wilcoxon signed-rank tests were used for statistical analysis.

Main Results:

  • Generated HR images demonstrated significantly higher mean image quality scores compared to original LR images (4.77±0.41 vs. 3.27±0.43 for precontrast, 4.72±0.44 vs. 3.23±0.43 for postcontrast; P<0.0001).
  • Mean lesion conspicuity scores were also significantly higher for generated HR images (4.18±0.70 vs. 3.49±0.58 for precontrast, 4.35±0.59 vs. 3.48±0.61 for postcontrast; P<0.001).
  • Good interreader agreement was observed for image quality, lesion conspicuity, and BI-RADS categories (ICCs >0.75).

Conclusions:

  • DCGAN effectively generates high-resolution breast MRI images from fast pre- and postcontrast low-resolution scans.
  • The generated HR images exhibit superior quantitative and qualitative performance, as validated in a multireader study.
  • This AI-driven approach holds potential for improving diagnostic accuracy and efficiency in breast MRI.