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

Dehydroepiandrosterone Sulfate/Cortisol Ratio as a Biomarker of Depressive Symptoms in Late-Onset Hypogonadism: An Analysis of 3,005 Males.

The world journal of men's health·2026
Same author

Utility of High-Resolution Semiconductor Positron Emission Tomography/Computed Tomography in the Assessment of Breast Cancer Extent: Comparison with Magnetic Resonance Imaging.

The British journal of radiology·2026
Same author

Neurologic Complications of Varicella-Zoster Virus Reactivation: Clinical and Imaging Features.

Radiographics : a review publication of the Radiological Society of North America, Inc·2026
Same author

Usefulness of Superselective Arterial Spin Labeling for Evaluating Feeding Arteries and Brain Invasion in Meningiomas.

AJNR. American journal of neuroradiology·2026
Same author

Response to letter to the editor by Liu and colleagues.

Journal of clinical lipidology·2026
Same author

In Older Men With Persistent Nocturia Due to Nocturnal Polyuria, Desmopressin Is Effective for Those With Higher Muscle Mass.

Lower urinary tract symptoms·2026

Related Experiment Video

Updated: Jun 9, 2025

Author Spotlight: Enhancing PSC-to-Functional Cell Differentiation Using ML Models Based on Live-Cell Bright-Field Imaging
11:38

Author Spotlight: Enhancing PSC-to-Functional Cell Differentiation Using ML Models Based on Live-Cell Bright-Field Imaging

Published on: October 4, 2024

492

[Effect of Training Data Differences on Accuracy in MR Image Generation Using Pix2pix].

Masaru Tsukano1, Yasushi Yamamoto2, Masato Shirai3

  • 1Department of Radiology, Shimane University Hospital.

Nihon Hoshasen Gijutsu Gakkai Zasshi
|October 30, 2024
PubMed
Summary
This summary is machine-generated.

Deep learning magnetic resonance (MR) image generation accuracy depends on training data patterns. More data from a single MR system improved image quality compared to limited data or data from multiple systems.

Keywords:
brain magnetic resonance imagingdata augmentationdeep learningimage generationpix2pix

More Related Videos

Author Spotlight: An Efficient and Robust Software for Automated Fusion of Multiple Preclinical Imaging Modalities
07:13

Author Spotlight: An Efficient and Robust Software for Automated Fusion of Multiple Preclinical Imaging Modalities

Published on: October 27, 2023

1.1K
Simultaneous PET/MRI Imaging During Mouse Cerebral Hypoxia-ischemia
10:35

Simultaneous PET/MRI Imaging During Mouse Cerebral Hypoxia-ischemia

Published on: September 20, 2015

12.2K

Related Experiment Videos

Last Updated: Jun 9, 2025

Author Spotlight: Enhancing PSC-to-Functional Cell Differentiation Using ML Models Based on Live-Cell Bright-Field Imaging
11:38

Author Spotlight: Enhancing PSC-to-Functional Cell Differentiation Using ML Models Based on Live-Cell Bright-Field Imaging

Published on: October 4, 2024

492
Author Spotlight: An Efficient and Robust Software for Automated Fusion of Multiple Preclinical Imaging Modalities
07:13

Author Spotlight: An Efficient and Robust Software for Automated Fusion of Multiple Preclinical Imaging Modalities

Published on: October 27, 2023

1.1K
Simultaneous PET/MRI Imaging During Mouse Cerebral Hypoxia-ischemia
10:35

Simultaneous PET/MRI Imaging During Mouse Cerebral Hypoxia-ischemia

Published on: September 20, 2015

12.2K

Area of Science:

  • Medical Imaging
  • Artificial Intelligence
  • Deep Learning

Context:

  • Magnetic resonance (MR) imaging is crucial for medical diagnostics.
  • Deep learning models like pix2pix are increasingly used for image generation.
  • Optimizing training data is essential for accurate AI-driven image synthesis.

Purpose:

  • To investigate how different training data patterns impact the accuracy of deep learning-based MR image generation.
  • To evaluate the effect of dataset size and source diversity on image synthesis quality.

Summary:

  • The study utilized the pix2pix model to generate T1-weighted MR images from T2-weighted or FLAIR images.
  • Four training data patterns were tested: varying case numbers (150 vs. 300) and MR system sources (one vs. two).
  • Image generation accuracy was assessed using peak signal-to-noise ratio (PSNR) and structural similarity (SSIM).

Impact:

  • Findings indicate that training dataset size and homogeneity significantly influence MR image generation accuracy.
  • A dataset of 300 cases from a single MR system yielded superior results compared to smaller datasets or multi-system datasets.
  • This research provides insights for optimizing deep learning strategies in medical image synthesis.