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 Experiment Video

Updated: Jul 12, 2026

Synchronous Triplanar Reconstruction Integrated with Color Doppler Mapping for Precise and Rapid Localization of Thyroid Lesions
05:41

Synchronous Triplanar Reconstruction Integrated with Color Doppler Mapping for Precise and Rapid Localization of Thyroid Lesions

Published on: February 9, 2024

Spatial-temporal and physical constrained deep learning model for simultaneous T1 and T2 reconstruction and mapping

Runyu Yang1, Haozhong Sun1, Xiaoqi Lin1

  • 1Center for Biomedical Imaging Research, Department of Biomedical Engineering, Tsinghua University, Beijing, China.

Quantitative Imaging in Medicine and Surgery
|July 11, 2026
PubMed
Summary

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

Dietary stearic acid aggravates acute graft-versus-host disease by promoting oxidative stress and pro-inflammatory macrophage polarization.

International immunopharmacology·2026
Same author

K38 Succinylation of CsrA Regulates Biofilm Formation in <i>Pseudomonas fluorescens</i> PF08 by Modulating c-di-GMP Levels.

Journal of agricultural and food chemistry·2026
Same author

Triple synergy by one-step reductive smelting separation for full utilization of vanadium extraction tailings: Detoxification, Fe-Cr-V wear-resistant alloy preparation and co-production of Ti-rich residue.

Journal of hazardous materials·2026
Same author

Triboelectric effect on the adhesive coating of particles in a high shear mixer.

International journal of pharmaceutics·2026
Same author

A multimodal deep learning model predicting hyperprogressive disease for PD-1 blockade in advanced hepatocellular carcinoma.

NPJ digital medicine·2026
Same author

Truncated enhanced constraint for low-rank plus sparse in cardiac dynamic MRI reconstruction.

Magnetic resonance letters·2026

This study introduces a novel deep learning method for faster and more accurate T1 and T2 magnetic resonance imaging (MRI) parametric mapping. The approach significantly accelerates quantitative mapping, improving diagnostic capabilities.

Area of Science:

  • Medical Imaging
  • Quantitative MRI
  • Deep Learning in Medical Applications

Background:

  • Magnetic resonance (MR) parametric maps offer quantitative tissue characteristics crucial for medical diagnosis.
  • Current T1 and T2 mapping techniques face limitations including long reconstruction times and the need for multi-sequence image registration, hindering clinical use.
  • Existing deep learning methods for MR reconstruction accelerate the process but often neglect inherent data constraints and require extensive training data.

Purpose of the Study:

  • To address the limitations of existing MR quantitative mapping techniques.
  • To develop a novel method for simultaneous T1 and T2 reconstruction and mapping that is faster and more accurate.
  • To integrate deep learning with physical constraints for improved quantitative parameter mapping.
Keywords:
Deep learninglow rankmagnetic resonance parametric maps (MR parametric maps)physical modelsparsity

Related Experiment Videos

Last Updated: Jul 12, 2026

Synchronous Triplanar Reconstruction Integrated with Color Doppler Mapping for Precise and Rapid Localization of Thyroid Lesions
05:41

Synchronous Triplanar Reconstruction Integrated with Color Doppler Mapping for Precise and Rapid Localization of Thyroid Lesions

Published on: February 9, 2024

Main Methods:

  • Proposes the spatial-temporal and physical constrained deep learning model for simultaneous T1 and T2 reconstruction and mapping (STEP) method.
  • Utilizes physical models for deep learning feature backpropagation, incorporating spatiotemporal correlations.
  • Integrates low-rank/sparse constraints with deep learning priors for mutual enhancement.

Main Results:

  • The STEP method achieved higher accuracy in T1 and T2 maps compared to traditional and conventional deep learning methods.
  • Simultaneous quantitative T1 and T2 maps were generated using only 2-4% of full k-space data, with SSIM > 0.7 and nRMSE < 0.1.
  • The entire process was accelerated approximately 150 times, with excellent T1 (R²=0.99) and T2 (R²=0.94) quantification.

Conclusions:

  • The proposed method synergistically combines deep learning with low-rank sparse iterative processing.
  • It effectively extracts feature information using low-rank sparse priors and optimizes backpropagation via physical models.
  • Achieves concurrent T1 and T2 quantification with significant improvements in speed and accuracy.