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

Abscopal responses following stereotactic ablative radiotherapy during immune checkpoint inhibitor therapy in metastatic renal cell carcinoma: protocol for the prospective multicentre observational AURICRE study in Japan.

BMJ open·2026
Same author

Utility of serum Krebs von den Lungen-6 and surfactant protein D levels for differential diagnosis of immune checkpoint inhibitor-related pneumonitis.

Immunotherapy·2026
Same author

Diagnostic performance of commercial AI systems versus participating radiologists for pulmonary nodule detection in routine clinical practice.

Japanese journal of radiology·2026
Same author

Real-world outcomes of definitive chemoradiotherapy for bladder cancer: a multi-institutional retrospective study in Japan.

Japanese journal of clinical oncology·2026
Same author

Identification of the SCN9A Variant c.647T>C (p. Phe216Ser) in a Patient With Primary Erythromelalgia.

The Journal of dermatology·2026
Same author

Operando ATR-FTIR elucidation of surface-mediated photocatalytic pathways on metal-free nanomaterials.

Spectrochimica acta. Part A, Molecular and biomolecular spectroscopy·2026

Related Experiment Video

Updated: Aug 22, 2025

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

586

Model-based Deep Learning Reconstruction Using a Folded Image Training Strategy for Abdominal 3D T1-weighted Imaging.

Satoshi Funayama1, Utaroh Motosugi2, Shintaro Ichikawa3

  • 1Department of Radiology, University of Yamanashi.

Magnetic Resonance in Medical Sciences : MRMS : an Official Journal of Japan Society of Magnetic Resonance in Medicine
|November 9, 2022
PubMed
Summary

The folded image training strategy (FITS) with an improved model-based deep learning (iMoDL) network significantly enhances abdominal MRI quality. This method improves image quality metrics and diagnostic performance compared to conventional techniques.

Keywords:
deep learningimage reconstructionliver imagingnetwork training

More Related Videos

Reconstruction of 3-Dimensional Histology Volume and its Application to Study Mouse Mammary Glands
10:59

Reconstruction of 3-Dimensional Histology Volume and its Application to Study Mouse Mammary Glands

Published on: July 26, 2014

14.5K
Creation of a High-Fidelity, Low-Cost, Intraosseous Line Placement Task Trainer via 3D Printing
11:45

Creation of a High-Fidelity, Low-Cost, Intraosseous Line Placement Task Trainer via 3D Printing

Published on: August 17, 2022

2.2K

Related Experiment Videos

Last Updated: Aug 22, 2025

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

586
Reconstruction of 3-Dimensional Histology Volume and its Application to Study Mouse Mammary Glands
10:59

Reconstruction of 3-Dimensional Histology Volume and its Application to Study Mouse Mammary Glands

Published on: July 26, 2014

14.5K
Creation of a High-Fidelity, Low-Cost, Intraosseous Line Placement Task Trainer via 3D Printing
11:45

Creation of a High-Fidelity, Low-Cost, Intraosseous Line Placement Task Trainer via 3D Printing

Published on: August 17, 2022

2.2K

Area of Science:

  • Medical Imaging
  • Artificial Intelligence in Medicine
  • Magnetic Resonance Imaging

Background:

  • Deep learning models are increasingly used for Magnetic Resonance Imaging (MRI) reconstruction.
  • Model-based deep learning (MoDL) offers a framework for image reconstruction.
  • Optimizing MoDL training strategies is crucial for improving image quality.

Purpose of the Study:

  • To evaluate the feasibility of the folded image training strategy (FITS).
  • To assess the image quality of abdominal MR images reconstructed using the improved MoDL (iMoDL) network trained with FITS (FITS-iMoDL).

Main Methods:

  • Retrospective analysis of 122 patients' abdominal 3D T1-weighted MR images.
  • Comparison of FITS-iMoDL with conventional MoDL (conv-MoDL), FITS-MoDL, compressed sensing (CS), and parallel imaging (CG-SENSE) using peak SNR (PSNR) and structure similarity index (SSIM).
  • Clinical evaluation of SNR, contrast, and image quality using mean opinion scores (MOS) by three radiologists.

Main Results:

  • FITS-iMoDL demonstrated significantly higher PSNR and SSIM compared to conv-MoDL, CS, and CG-SENSE.
  • Clinical analysis showed significantly higher SNR for FITS-iMoDL compared to reference and CS images.
  • Radiologists reported significantly improved image quality, including conspicuity of anatomical structures and lesions, with FITS-iMoDL.

Conclusions:

  • FITS-iMoDL enables deeper MoDL networks without increased memory usage.
  • The FITS-iMoDL method significantly improves image quality in abdominal 3D T1-weighted MRI.
  • This approach offers superior performance compared to conventional compressed sensing techniques.