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

Magnetic Resonance Imaging01:24

Magnetic Resonance Imaging

5.4K
Magnetic resonance imaging (MRI) is a noninvasive medical imaging technique based on a phenomenon of nuclear physics discovered in the 1930s, in which matter exposed to magnetic fields and radio waves was found to emit radio signals. In 1970, a physician and researcher named Raymond Damadian noticed that malignant (cancerous) tissue gave off different signals than normal body tissue. He applied for a patent for the first MRI scanning device in clinical use by the early 1980s. The early MRI...
5.4K
Electron Microscope Tomography and Single-particle Reconstruction01:07

Electron Microscope Tomography and Single-particle Reconstruction

2.5K
Transmission electron microscopy (TEM) can be used to determine the 3D structure of biological samples with the help of techniques such as electron microscope tomography and single-particle reconstruction. While single-particle reconstruction can examine macromolecules and macromolecular complexes in vitro conditions only, tomography permits the study of cell components or small cells in vivo.
Electron Tomography
Electron tomography can be performed either in TEM or STEM (scanning transmission...
2.5K

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Underlying Semantic Diffusion for Effective and Efficient In-Context Learning.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2026
Same author

SD<sup>2</sup>-SNN: Self-distillation and structural decomposition framework for SNNs in continual learning.

Neural networks : the official journal of the International Neural Network Society·2026
Same author

Porcine epidemic diarrhea virus suppresses DHX9-mediated antiviral transcription through its nucleocapsid protein.

Communications biology·2026
Same author

Antigen spreading mediates heterogeneous solid tumor eradication by DNA demethylating agent-programmed CAR T cells.

Science advances·2026
Same author

Chain length distribution and its effects on the pasting and thermal properties of lotus root starch.

Food chemistry·2026
Same author

Demethylation-primed tandem CD19/CD20 CAR T cells in relapsed/refractory B-cell lymphoma: a phase I/II trial.

Nature communications·2026

Related Experiment Video

Updated: Aug 12, 2025

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

445

DSMENet: Detail and Structure Mutually Enhancing Network for under-sampled MRI reconstruction.

Yueze Wang1, Yanwei Pang1, Chuan Tong1

  • 1TJK-BIIT Lab, School of Electrical and Information Engineering, Tianjin University, Tianjin, 300072, China.

Computers in Biology and Medicine
|January 30, 2023
PubMed
Summary

This study introduces a new AI model, the Detail and Structure Mutually Enhancing Network (DSMENet), to improve MRI scan speed. DSMENet effectively reconstructs detailed MR images from incomplete data, enhancing diagnostic accuracy.

Keywords:
Convolutional neural networkDeep learningImage reconstructionMagnetic resonance imaging

More Related Videos

Co-analysis of Brain Structure and Function using fMRI and Diffusion-weighted Imaging
17:06

Co-analysis of Brain Structure and Function using fMRI and Diffusion-weighted Imaging

Published on: November 8, 2012

26.3K
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

22.6K

Related Experiment Videos

Last Updated: Aug 12, 2025

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

445
Co-analysis of Brain Structure and Function using fMRI and Diffusion-weighted Imaging
17:06

Co-analysis of Brain Structure and Function using fMRI and Diffusion-weighted Imaging

Published on: November 8, 2012

26.3K
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

22.6K

Area of Science:

  • Medical Imaging
  • Artificial Intelligence
  • Computer Vision

Background:

  • Magnetic Resonance Imaging (MRI) acceleration is crucial for reducing scan times.
  • Reconstructing zero-filled (ZF) MR images from partial k-space data using convolutional neural networks (CNNs) is a key technique.
  • Existing methods struggle to effectively learn the mapping from ZF to target images due to insufficient attention to different image components.

Purpose of the Study:

  • To propose a novel deep learning model, the Detail and Structure Mutually Enhancing Network (DSMENet), for improved MRI reconstruction.
  • To enhance the reconstruction of zero-filled MR images by effectively utilizing both structural and detailed information.
  • To accelerate MRI acquisition while maintaining high image quality and diagnostic utility.

Main Methods:

  • Developed DSMENet, integrating a Structure Reconstruction UNet (SRUN) for multi-scale structure learning and a Detail Feature Refinement Module (DFRM) for fine-grained detail enrichment.
  • Implemented bidirectional alternate connections for information exchange between SRUN and DFRFM.
  • Introduced Detail Representation Construction Module (DRCM) and Detail Guided Fusion Module (DGFM) for enhanced detail extraction and fusion.
  • Incorporated Deep Enhanced Restoration (DER) strategy for performance optimization.

Main Results:

  • DSMENet demonstrated robust performance across various body parts, undersampling rates, and k-space masks on fastMRI and CC-359 datasets.
  • Achieved competitive quantitative results, including a Normalized Mean Square Error (NMSE) of 0.0268, Peak Signal-to-Noise Ratio (PSNR) of 33.7, and Structural Similarity Index Measure (SSIM) of 0.7808 on the fastMRI 4x single-coil knee leaderboard.
  • Showcased significant improvements in both qualitative and quantitative image reconstruction compared to existing methods.

Conclusions:

  • DSMENet effectively addresses the limitations of current MRI reconstruction techniques by mutually enhancing structural and detailed information.
  • The proposed model offers a robust and efficient solution for accelerating MRI scans without compromising image quality.
  • DSMENet holds significant potential for advancing clinical MRI applications through faster and more accurate image reconstruction.