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 Videos

Deep-learning-based Optimization of the Under-sampling Pattern in MRI.

Cagla D Bahadir1, Alan Q Wang2, Adrian V Dalca3

  • 1Meinig School of Biomedical Engineering, Cornell University.

IEEE Transactions on Computational Imaging
|July 8, 2026
PubMed
Summary
This summary is machine-generated.

Related Concept Videos

Magnetic Resonance Imaging01:24

Magnetic Resonance Imaging

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...
Imaging Studies IV: Magnetic Resonance Imaging01:27

Imaging Studies IV: Magnetic Resonance Imaging

Introduction:Magnetic Resonance Imaging, or MRI, can include a specialized imaging technique of the urinary system known as Magnetic Resonance Urography (MRU). This radiation-free technique uses strong magnetic fields and radio waves to produce detailed images with the help of a computer. MRU is particularly effective for visualizing fluid-filled structures like the kidneys, ureters, and bladder.Applications of MRI in the Genitourinary SystemKidneys and Ureters: MRI detects tumors, cysts,...

You might also read

Related Articles

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

Sort by
Same author

Learning-based non-linear registration robust to MRI-sequence contrast.

Proceedings of the International Society for Magnetic Resonance in Medicine ... Scientific Meeting and Exhibition. International Society for Magnetic Resonance in Medicine. Scientific Meeting and Exhibition·2026
Same author

A view-engage-predict framework for enhancing brain-behavior mapping with naturalistic movie-watching fMRI.

Communications biology·2026
Same author

Structural connectome analysis using a graph-based deep model for prediction of non-imaging variables.

Frontiers in neuroscience·2026
Same author

Weak supervision of H&E slides reveals systems-level biology and functional states that govern therapeutic resistance.

bioRxiv : the preprint server for biology·2026
Same author

Motion-Aware Neural Networks Improve Rigid Motion Correction of Accelerated Segmented Multislice MRI.

Proceedings of the International Society for Magnetic Resonance in Medicine ... Scientific Meeting and Exhibition. International Society for Magnetic Resonance in Medicine. Scientific Meeting and Exhibition·2026
Same author

Joint Neural Network for Fast Retrospective Rigid Motion Correction of Accelerated Segmented Multislice MRI.

Proceedings of the International Society for Magnetic Resonance in Medicine ... Scientific Meeting and Exhibition. International Society for Magnetic Resonance in Medicine. Scientific Meeting and Exhibition·2026

This study introduces LOUPE, a novel framework for compressed sensing MRI (CS-MRI) that optimizes k-space sampling patterns and reconstruction simultaneously. LOUPE achieves superior image quality and anatomical detail preservation, even at high acceleration rates.

Area of Science:

  • Medical Imaging
  • Artificial Intelligence
  • Biomedical Engineering

Background:

  • Compressed sensing MRI (CS-MRI) accelerates scans by under-sampling k-space data.
  • Key challenges in CS-MRI involve optimizing sampling locations and reconstruction methods.
  • Current methods often address sampling and reconstruction separately.

Purpose of the Study:

  • To develop a unified, data-driven framework for optimizing both under-sampling patterns and reconstruction in CS-MRI.
  • To simultaneously address the 'where to sample' and 'how to reconstruct' problems in 2D Cartesian CS-MRI.
  • To improve image reconstruction quality and preserve anatomical detail at accelerated scan times.

Main Methods:

  • Introduced LOUPE (Learning-based Optimization of the Under-sampling PattErn), an end-to-end neural network framework.
Keywords:
Compressed SensingDeep LearningMagnetic Resonance Imaging

Related Experiment Videos

  • Trained the model on full-resolution MRI scans, retrospectively under-sampled using a 2D Cartesian grid.
  • Integrated an anti-aliasing (reconstruction) model to compare reconstructions with original scans, enabling data-driven optimization of under-sampling masks.

    • Main Results:

    • LOUPE-optimized under-sampling masks are data-dependent, varying with anatomy (e.g., brain vs. knee).
    • Demonstrated superior reconstruction quality compared to alternative methods on a large-scale knee MRI dataset.
    • Achieved high-fidelity reconstructions with significant anatomical detail preservation even at an 8-fold acceleration rate.

    Conclusions:

    • LOUPE provides an effective, unified approach to optimize CS-MRI acquisition and reconstruction.
    • The data-driven, anatomy-specific sampling patterns generated by LOUPE enhance reconstruction performance.
    • This framework holds significant potential for accelerating MRI scans without compromising diagnostic image quality.