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

LNODE: latent dynamics reveal the shared spatiotemporal structure of amyloid-$β$ progression.

ArXiv·2026

Same author

LNODE: Uncovering the Latent Dynamics of <math><mi>A</mi> <mi>β</mi></math> in Alzheimer's Disease.

Medical image computing and computer-assisted intervention : MICCAI ... International Conference on Medical Image Computing and Computer-Assisted Intervention·2026

Same author

A boundary integral method for simulating the dynamics of inextensible vesicles suspended in a viscous fluid in 2D.

Journal of computational physics·2025

Same author

Aligning personalized biomarker trajectories onto a common time axis: a connectome-based ODE model for Tau-Amyloid beta dynamics.

Medical image analysis·2025

Same author

Inverse Problem Regularization for 3D Multi-Species Tumor Growth Models.

International journal for numerical methods in biomedical engineering·2025

Same author

A single-snapshot inverse solver for two-species graph model of tau pathology spreading in human Alzheimer's disease.

Brain informatics·2025

Same journal

Cloud Computing to Enable Wearable-Driven Longitudinal Hemodynamic Maps.

International Conference for High Performance Computing, Networking, Storage and Analysis : [proceedings]. SC (Conference : Supercomputing)·2024

Same journal

Enhancing Adaptive Physics Refinement Simulations Through the Addition of Realistic Red Blood Cell Counts.

International Conference for High Performance Computing, Networking, Storage and Analysis : [proceedings]. SC (Conference : Supercomputing)·2023

See all related articles

Search research articles

Related Experiment Video

Updated: Sep 30, 2025

Author Spotlight: An Efficient and Robust Software for Automated Fusion of Multiple Preclinical Imaging Modalities

Author Spotlight: An Efficient and Robust Software for Automated Fusion of Multiple Preclinical Imaging Modalities

Published on: October 27, 2023

Multi-Node Multi-GPU Diffeomorphic Image Registration for Large-Scale Imaging Problems.

Malte Brunn¹, Naveen Himthani², George Biros²

¹Computer Science, University of Stuttgart, Stuttgart, DE.

International Conference for High Performance Computing, Networking, Storage and Analysis : [Proceedings]. SC (Conference : Supercomputing)

|March 17, 2022

Summary

This summary is machine-generated.

We developed a faster Gauss-Newton-Krylov solver for large deformation diffeomorphic image registration using multi-GPU systems. This advanced solver significantly accelerates medical image analysis and large-scale computational tasks.

Keywords:

Gauss–Newton–Krylov solver PDE-constrained optimization diffeomorphic image registration multi-node multi-GPU preconditioning

More Related Videos

Multi-modal Pulmonary Imaging: Using Complementary Information from CT and Hyperpolarized 129Xe MRI to Evaluate Lung Structure-Function

Multi-modal Pulmonary Imaging: Using Complementary Information from CT and Hyperpolarized 129Xe MRI to Evaluate Lung Structure-Function

Published on: April 12, 2024

A Pipeline for 3D Multimodality Image Integration and Computer-assisted Planning in Epilepsy Surgery

A Pipeline for 3D Multimodality Image Integration and Computer-assisted Planning in Epilepsy Surgery

Published on: May 20, 2016

Related Experiment Videos

Last Updated: Sep 30, 2025

Author Spotlight: An Efficient and Robust Software for Automated Fusion of Multiple Preclinical Imaging Modalities

Author Spotlight: An Efficient and Robust Software for Automated Fusion of Multiple Preclinical Imaging Modalities

Published on: October 27, 2023

Multi-modal Pulmonary Imaging: Using Complementary Information from CT and Hyperpolarized 129Xe MRI to Evaluate Lung Structure-Function

Multi-modal Pulmonary Imaging: Using Complementary Information from CT and Hyperpolarized 129Xe MRI to Evaluate Lung Structure-Function

Published on: April 12, 2024

A Pipeline for 3D Multimodality Image Integration and Computer-assisted Planning in Epilepsy Surgery

A Pipeline for 3D Multimodality Image Integration and Computer-assisted Planning in Epilepsy Surgery

Published on: May 20, 2016

Area of Science:

Medical image analysis
Computational science
Scientific computing

Background:

Large deformation diffeomorphic image registration is crucial for medical image analysis.
Existing methods face computational challenges with high-resolution images.

Purpose of the Study:

To develop a high-performance solver for large deformation diffeomorphic image registration.
To optimize the solver for multi-node, multi-GPU systems.

Main Methods:

Extended the CLAIRE library for multi-node, multi-GPU systems.
Introduced a novel preconditioner for the Gauss-Newton Hessian system.
Implemented optimized computational kernels using device direct communication.

Main Results:

Achieved a 70% performance speedup compared to state-of-the-art methods.
Solved a 256^3 resolution image registration problem in five seconds on a single GPU.
Successfully registered 2048^3 resolution images on a large-scale GPU cluster.

Conclusions:

The developed Gauss-Newton-Krylov solver offers significant performance improvements for large deformation image registration.
The multi-GPU implementation enables registration of unprecedentedly large image datasets.
This work advances the capabilities of medical image analysis and scientific computing.