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

Performance benchmarking of deep learning models for real-time median nerve segmentation and cross-sectional area measurement in ultrasound imaging.

Medical physics·2026
Same author

Rolling convolution filters for lightweight neural networks in medical image analysis.

Journal of medical imaging (Bellingham, Wash.)·2026
Same author

ISDU-QSMNet: Iteration Specific Denoising With Unshared Weights for Improved QSM Reconstruction.

NMR in biomedicine·2025
Same author

DF-QSM: Data Fidelity based Hybrid Approach for Improved Quantitative Susceptibility Mapping of the Brain.

NMR in biomedicine·2024
Same author

Transformer-Based Automated Segmentation of the Median Nerve in Ultrasound Videos of Wrist-to-Elbow Region.

IEEE transactions on ultrasonics, ferroelectrics, and frequency control·2023
Same author

Model resolution-based deconvolution for improved quantitative susceptibility mapping.

NMR in biomedicine·2023

Related Experiment Video

Updated: Jun 28, 2025

Identification of Disease-related Spatial Covariance Patterns using Neuroimaging Data
14:27

Identification of Disease-related Spatial Covariance Patterns using Neuroimaging Data

Published on: June 26, 2013

15.6K

Spinet-QSM: model-based deep learning with schatten p-norm regularization for improved quantitative susceptibility

Vaddadi Venkatesh1, Raji Susan Mathew2, Phaneendra K Yalavarthy3

  • 1Department of Computational and Data Sciences, Indian Institute of Science, Bangalore, Karnataka, 560012, India.

Magma (New York, N.Y.)
|April 10, 2024
PubMed
Summary
This summary is machine-generated.

A novel deep learning framework, SpiNet-QSM, enhances quantitative susceptibility mapping (QSM) by utilizing a flexible Schatten norm. This advanced method improves magnetic susceptibility estimation in MRI, outperforming existing techniques.

Keywords:
Dipole inversionModel-based deep learningSchatten p-normSusceptibility reconstruction

More Related Videos

Author Spotlight: Bridging Gaps in Anatomy and Establishing a Foundation for Algorithmic Studies
04:25

Author Spotlight: Bridging Gaps in Anatomy and Establishing a Foundation for Algorithmic Studies

Published on: December 15, 2023

2.4K
Lesion Explorer: A Video-guided, Standardized Protocol for Accurate and Reliable MRI-derived Volumetrics in Alzheimer's Disease and Normal Elderly
12:50

Lesion Explorer: A Video-guided, Standardized Protocol for Accurate and Reliable MRI-derived Volumetrics in Alzheimer's Disease and Normal Elderly

Published on: April 14, 2014

40.3K

Related Experiment Videos

Last Updated: Jun 28, 2025

Identification of Disease-related Spatial Covariance Patterns using Neuroimaging Data
14:27

Identification of Disease-related Spatial Covariance Patterns using Neuroimaging Data

Published on: June 26, 2013

15.6K
Author Spotlight: Bridging Gaps in Anatomy and Establishing a Foundation for Algorithmic Studies
04:25

Author Spotlight: Bridging Gaps in Anatomy and Establishing a Foundation for Algorithmic Studies

Published on: December 15, 2023

2.4K
Lesion Explorer: A Video-guided, Standardized Protocol for Accurate and Reliable MRI-derived Volumetrics in Alzheimer's Disease and Normal Elderly
12:50

Lesion Explorer: A Video-guided, Standardized Protocol for Accurate and Reliable MRI-derived Volumetrics in Alzheimer's Disease and Normal Elderly

Published on: April 14, 2014

40.3K

Area of Science:

  • Medical Imaging
  • Computational Neuroscience
  • Biophysics

Background:

  • Quantitative susceptibility mapping (QSM) estimates tissue magnetic susceptibility from MRI phase data.
  • Solving the inverse source-effect problem is crucial for accurate QSM reconstruction.
  • Existing methods often rely on fixed norms, limiting adaptability.

Purpose of the Study:

  • To develop an effective model-based deep learning framework for solving the QSM inverse problem.
  • Introduce a novel deep learning approach for improved QSM accuracy.
  • Enhance the adaptability of QSM reconstruction models.

Main Methods:

  • Proposed a Schatten -norm-driven model-based deep learning framework for QSM.
  • Incorporated a learnable norm parameter for data adaptation.
  • Enforced any -norm on a trainable regularizer, unlike fixed l1/l2 norms.

Main Results:

  • The proposed SpiNet-QSM method was compared against QSMnet and LPCNN.
  • Reconstructions were performed on 77 imaging volumes across diverse acquisition protocols and clinical conditions (e.g., hemorrhage, multiple sclerosis).
  • The approach demonstrated significant outperformance over state-of-the-art methods in quantitative metrics.

Conclusions:

  • SpiNet-QSM consistently improved high-frequency error norm (HFEN) and normalized root mean squared error (NRMSE) by at least 5%.
  • Achieved superior QSM reconstruction with limited training data compared to other methods.
  • The flexible norm-driven approach offers a robust solution for QSM.