Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

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

Ultrasonographic punctate echogenic foci in metastatic lymph nodes and their presence in primary thyroid cancer.

Medicine·2026

Same author

AutoMedic: An Automated Evaluation Framework for Clinical Conversational Agents with Medical Dataset Grounding.

IEEE journal of biomedical and health informatics·2026

Same author

ROS-Responsive Nanobubbles for Dual-Enhanced Ultrasound and Magnetic Resonance Imaging of Tumor Oxidative Stress.

Advanced science (Weinheim, Baden-Wurttemberg, Germany)·2026

Same author

Physics-Guided Neural Network for Quantitative Parameter Mapping Using Balanced Steady State Free Precession MRI.

Magnetic resonance in medicine·2026

Same author

Pontine Microtubular Signal Intensity in Hemifacial Spasm: Association with Outcome After Microvascular Decompression Surgery.

Life (Basel, Switzerland)·2026

Same author

Image quality improvement of liver ultrasound using unsupervised deep learning.

PloS one·2026

Same journal

Embracing intra-class heterogeneity for semi-supervised medical image segmentation: From diversity to precision.

Medical image analysis·2026

Same journal

Real-time patient-specific microwave ablation zone prediction via a unified bioheat solver and MRI-informed perturbation learning.

Medical image analysis·2026

Same journal

Generative morphodynamic forecasting enables robust zero-shot volumetric medical segmentation.

Medical image analysis·2026

Same journal

ContiMorph: An unsupervised learning framework for cardiac motion tracking with time-continuous diffeomorphism.

Medical image analysis·2026

Same journal

MedP-CLIP: Medical CLIP with region-aware prompt integration.

Medical image analysis·2026

Same journal

Multi-organ guided diagnosis of mild cognitive impairment via hierarchical alignment and knowledge distillation.

Medical image analysis·2026

See all related articles

Search research articles

Related Experiment Video

Updated: Sep 22, 2025

Basics of Multivariate Analysis in Neuroimaging Data

Basics of Multivariate Analysis in Neuroimaging Data

Published on: July 24, 2010

Unsupervised resolution-agnostic quantitative susceptibility mapping using adaptive instance normalization.

Gyutaek Oh¹, Hyokyoung Bae¹, Hyun-Seo Ahn¹

¹Department of Bio and Brain Engineering, Korea Advanced Institute of Science and Technology (KAIST), Daejeon 34141, Republic of Korea.

Medical Image Analysis

|May 23, 2022

Summary

This summary is machine-generated.

This study introduces an unsupervised deep learning method for quantitative susceptibility mapping (QSM) using magnetic resonance imaging (MRI). The novel approach achieves accurate QSM reconstruction across various resolutions without needing ground-truth data.

Keywords:

Adaptive instance normalization Quantitative susceptibility mapping Resolution-agnostic Unsupervised deep learning

More Related Videos

Identification of Disease-related Spatial Covariance Patterns using Neuroimaging Data

Identification of Disease-related Spatial Covariance Patterns using Neuroimaging Data

Published on: June 26, 2013

Large-Scale Multi-Omics Genome-Wide Association Studies Mo-GWAS: Guidelines for Sample Preparation and Normalization

Large-Scale Multi-Omics Genome-Wide Association Studies Mo-GWAS: Guidelines for Sample Preparation and Normalization

Published on: July 27, 2021

Related Experiment Videos

Last Updated: Sep 22, 2025

Basics of Multivariate Analysis in Neuroimaging Data

Basics of Multivariate Analysis in Neuroimaging Data

Published on: July 24, 2010

Identification of Disease-related Spatial Covariance Patterns using Neuroimaging Data

Identification of Disease-related Spatial Covariance Patterns using Neuroimaging Data

Published on: June 26, 2013

Large-Scale Multi-Omics Genome-Wide Association Studies Mo-GWAS: Guidelines for Sample Preparation and Normalization

Large-Scale Multi-Omics Genome-Wide Association Studies Mo-GWAS: Guidelines for Sample Preparation and Normalization

Published on: July 27, 2021

Area of Science:

Medical Imaging
Computational Neuroscience
Biophysics

Background:

Quantitative susceptibility mapping (QSM) is a vital MRI technique for tissue magnetic susceptibility mapping.
Traditional QSM reconstruction faces challenges due to the ill-posed nature of dipole kernel deconvolution.
Existing deep learning methods often require supervised training with matched phase images and ground-truth maps, limiting their applicability and resolution adaptability.

Purpose of the Study:

To develop an unsupervised, resolution-agnostic deep learning method for QSM reconstruction.
To overcome the limitations of supervised learning and resolution dependency in current deep learning-based QSM.

Main Methods:

Proposed an unsupervised deep learning framework for QSM.
Utilized adaptive instance normalization to achieve resolution-agnostic reconstruction.
Trained the model without requiring ground-truth QSM labels.

Main Results:

The unsupervised method successfully reconstructed QSM across various resolutions.
Achieved accurate QSM comparable to classical methods and superior to other deep learning approaches.
Demonstrated ultra-fast reconstruction times.

Conclusions:

The proposed unsupervised, resolution-agnostic deep learning method offers an effective alternative for QSM reconstruction.
This approach eliminates the need for labeled data and adapts to different resolutions, enhancing QSM's clinical utility.
The method provides accurate and rapid QSM, outperforming existing deep learning techniques.