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

Mechanistic Models: Compartment Models in Algorithms for Numerical Problem Solving

Mechanistic Models: Compartment Models in Algorithms for Numerical Problem Solving

Mechanistic models play a crucial role in algorithms for numerical problem-solving, particularly in nonlinear mixed effects modeling (NMEM). These models aim to minimize specific objective functions by evaluating various parameter estimates, leading to the development of systematic algorithms. In some cases, linearization techniques approximate the model using linear equations.
In individual population analyses, different algorithms are employed, such as Cauchy's method, which uses a...

You might also read

Related Articles

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

Sort by

Same author

Enantioselective Radical Ring-Opening Cyanation of Oxime Esters by Dual Photoredox and Copper Catalysis.

Organic letters·2019

Same author

ACCELERATING MAGNETIC RESONANCE IMAGING VIA DEEP LEARNING.

Proceedings. IEEE International Symposium on Biomedical Imaging·2019

Same author

Technical note: Development and application of KASP assays for rapid screening of 8 genetic defects in Holstein cattle.

Journal of dairy science·2019

Same author

Sesquiterpenes and diterpenes from Euphorbia thymifolia.

Fitoterapia·2019

Same author

Glechomanamides A-C, Germacrane Sesquiterpenoids with an Unusual Δ<sup>8</sup>-7,12-Lactam Moiety from <i>Salvia scapiformis</i> and Their Antiangiogenic Activity.

Journal of natural products·2019

Same author

Parameter optimization framework on wave gradients of Wave-CAIPI imaging.

Magnetic resonance in medicine·2019

Search research articles

Related Experiment Video

Updated: May 16, 2025

Diffusion Tensor Magnetic Resonance Imaging in the Analysis of Neurodegenerative Diseases

Diffusion Tensor Magnetic Resonance Imaging in the Analysis of Neurodegenerative Diseases

Published on: July 28, 2013

MeMGB-Diff: Memory-Efficient Multivariate Gaussian Bias Diffusion Model for 3D bias field correction.

Xingyu Qiu¹, Dong Liang¹, Gongning Luo¹

¹School of Computer Science and Technology, Harbin Institute of Technology, Harbin, China.

Medical Image Analysis

|April 4, 2025

Summary

This summary is machine-generated.

We developed a Memory-Efficient Multivariate Gaussian Bias Diffusion Model (MeMGB-Diff) for 3D MRI bias field correction. This novel method improves efficiency and accuracy without clinical labels, outperforming existing techniques.

Keywords:

Bias field correction Diffusion model MRI

More Related Videos

Sample Drift Correction Following 4D Confocal Time-lapse Imaging

Sample Drift Correction Following 4D Confocal Time-lapse Imaging

Published on: April 12, 2014

Synthesis of Cyclic Polymers and Characterization of Their Diffusive Motion in the Melt State at the Single Molecule Level

Synthesis of Cyclic Polymers and Characterization of Their Diffusive Motion in the Melt State at the Single Molecule Level

Published on: September 26, 2016

Related Experiment Videos

Last Updated: May 16, 2025

Diffusion Tensor Magnetic Resonance Imaging in the Analysis of Neurodegenerative Diseases

Diffusion Tensor Magnetic Resonance Imaging in the Analysis of Neurodegenerative Diseases

Published on: July 28, 2013

Sample Drift Correction Following 4D Confocal Time-lapse Imaging

Sample Drift Correction Following 4D Confocal Time-lapse Imaging

Published on: April 12, 2014

Synthesis of Cyclic Polymers and Characterization of Their Diffusive Motion in the Melt State at the Single Molecule Level

Synthesis of Cyclic Polymers and Characterization of Their Diffusive Motion in the Melt State at the Single Molecule Level

Published on: September 26, 2016

Area of Science:

Medical Imaging
Artificial Intelligence
Image Processing

Background:

Bias fields in MRI degrade image quality, hindering accurate medical diagnosis.
Traditional bias field correction methods and generative adversarial networks (GANs) have limitations, including high annotation costs and training instability.
Diffusion models show promise but face challenges in 3D applications due to computational demands and sampling inefficiency.

Purpose of the Study:

To introduce a novel, efficient, and label-free 3D bias field correction method for MRI.
To address the limitations of existing diffusion-based models in terms of memory usage and computational cost for 3D data.
To improve the accuracy and fidelity of bias field correction in MRI.

Main Methods:

Proposed a Memory-Efficient Multivariate Gaussian Bias Diffusion Model (MeMGB-Diff) for explicit and efficient 3D bias field correction.
Extended diffusion models to a multivariate Gaussian framework, modeling bias fields as multivariate Gaussian variables.
Implemented memory efficiency by performing diffusion in a smaller image domain, leveraging voxel correlation, and introduced a specialized loss function for intensity trends.

Main Results:

MeMGB-Diff demonstrated significant memory reduction (64x) and improved sampling efficiency (over 10x) compared to other diffusion methods.
Achieved state-of-the-art performance with optimal metrics (SSIM, PSNR, COCO, CV) across various tissues.
Quantitative and qualitative assessments on synthetic and clinical data confirmed high fidelity and uniform intensity in corrected MRI scans.

Conclusions:

MeMGB-Diff offers a highly efficient and accurate solution for 3D MRI bias field correction.
The proposed method overcomes key limitations of previous diffusion-based approaches.
This work presents a state-of-the-art method for improving MRI diagnostic accuracy through effective bias field removal.