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

Linearization and Approximation01:26

Linearization and Approximation

195
Linearization is a mathematical technique used to approximate complex, nonlinear functions with simpler linear models in the vicinity of a chosen reference point. The method is based on the idea that, although a function may be difficult to evaluate exactly, its behavior near a specific input value can often be closely approximated by the tangent line at that point. This approach is particularly useful when small deviations from a known value are involved.Consider the square root function, for...
195
Application of Linearization and Approximation01:29

Application of Linearization and Approximation

181
A drone flying through complex terrain often relies on more than one sensing method to estimate small changes in altitude. Along with direct measurements, air pressure provides a useful indirect indicator of vertical movement. Atmospheric pressure decreases as altitude increases, and this relationship is commonly described using an exponential model. Although accurate, converting pressure measurements into altitude values requires calculations that are too complex to perform repeatedly during...
181

You might also read

Related Articles

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

Sort by
Same author

A plug-and-play method for guided multi-contrast MRI reconstruction based on content/style modeling.

Medical image analysis·2026
Same author

Ex vivo T2*-weighted MRI and quantitative susceptibility mapping reflect spatial iron accumulation observed on histology in frontotemporal lobar degeneration.

Neurobiology of disease·2026
Same author

Neonatal brain MRI Atlas: Current and future.

Journal of neuroscience methods·2026
Same author

DEEP-DISORDER: Motion Correction in 3D MRI via Segment Reconstruction and Registration.

NMR in biomedicine·2026
Same author

JS-RegNeXt: A ConvNeXt-based few-shot JSR framework with correlation awareness and multi-scale prediction consistency.

IEEE journal of biomedical and health informatics·2026
Same author

Large language models for structured cardiovascular data extraction: a foundation for scalable research and clinical applications.

European heart journal. Digital health·2026

Related Experiment Video

Updated: Apr 4, 2026

Analyzing Dendritic Morphology in Columns and Layers
08:41

Analyzing Dendritic Morphology in Columns and Layers

Published on: March 23, 2017

9.9K

Fast Automatic Step Size Estimation for Gradient Descent Optimization of Image Registration.

Yuchuan Qiao, Baldur van Lew, Boudewijn P F Lelieveldt

    IEEE Transactions on Medical Imaging
    |September 10, 2015
    PubMed
    Summary

    A new fast adaptive stochastic gradient descent (ASGD) method significantly speeds up medical image registration. This computationally efficient approach automatically determines step size, reducing registration time by up to 7x while maintaining accuracy.

    More Related Videos

    Author Spotlight: Efficient Image Recognition Using Directional Gradient Histogram Technique and Support Vector Machines
    08:27

    Author Spotlight: Efficient Image Recognition Using Directional Gradient Histogram Technique and Support Vector Machines

    Published on: January 5, 2024

    1.8K
    Deep Neural Networks for Image-Based Dietary Assessment
    13:19

    Deep Neural Networks for Image-Based Dietary Assessment

    Published on: March 13, 2021

    10.2K

    Related Experiment Videos

    Last Updated: Apr 4, 2026

    Analyzing Dendritic Morphology in Columns and Layers
    08:41

    Analyzing Dendritic Morphology in Columns and Layers

    Published on: March 23, 2017

    9.9K
    Author Spotlight: Efficient Image Recognition Using Directional Gradient Histogram Technique and Support Vector Machines
    08:27

    Author Spotlight: Efficient Image Recognition Using Directional Gradient Histogram Technique and Support Vector Machines

    Published on: January 5, 2024

    1.8K
    Deep Neural Networks for Image-Based Dietary Assessment
    13:19

    Deep Neural Networks for Image-Based Dietary Assessment

    Published on: March 13, 2021

    10.2K

    Area of Science:

    • Medical Imaging
    • Computational Anatomy
    • Image Processing

    Background:

    • Fast automatic image registration is crucial for image-guided clinical procedures.
    • Current registration algorithms, like stochastic gradient descent, are often slow due to large datasets and complex computations.
    • Manual step size selection for gradient descent is data-dependent and difficult.

    Purpose of the Study:

    • To develop a computationally efficient method for automatic step size determination in gradient descent-based image registration.
    • To reduce the high computational cost associated with existing Adaptive Stochastic Gradient Descent (ASGD) methods.
    • To improve the speed of medical image registration without compromising accuracy.

    Main Methods:

    • Proposed a novel fast adaptive stochastic gradient descent (fast ASGD) method.
    • Determines step size by analyzing the distribution of voxel displacements between iterations.
    • Derived a relationship between step size and the expectation and variance of voxel displacements.

    Main Results:

    • Fast ASGD achieves similar accuracy to ASGD across diverse datasets and registration settings.
    • The computational complexity of fast ASGD is reduced from quadratic to linear with respect to transformation parameters.
    • Step size estimation time decreased from 40s to under 1s (a ~40x speedup for 105 parameters).
    • Total registration time was reduced by a factor of 2.5-7x.

    Conclusions:

    • Fast ASGD offers a computationally efficient and accurate solution for automatic step size selection in image registration.
    • This method significantly accelerates image-guided clinical procedures by reducing registration time.
    • The approach is validated across various modalities, subjects, and transformation models.