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 Experiment Video

Updated: Jul 13, 2026

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
04:48

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

Automatic seed initialization for the expectation-maximization algorithm and its application in 3D medical imaging.

M Lynch1, D Ilea, K Robinson

  • 1Vision Systems Group, Dublin City University, Dublin 9, Ireland. lynchm@eeng.dcu.ie

Journal of Medical Engineering & Technology
|August 19, 2007
PubMed
Summary
This summary is machine-generated.

Related Concept Videos

Mechanistic Models: Compartment Models in Algorithms for Numerical Problem Solving01:29

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

Jejunal histopathology, metagenome, and mucosal transcriptome of broilers after an enteric challenge and fed diets with different fiber types and concentrations.

Poultry science·2026
Same author

Cecal metagenome and mucosal transcriptome of broilers after an enteric challenge and fed diets with different fiber types and concentrations<sup>1</sup>.

Poultry science·2026
Same author

Development of a Core Outcome Set for research studies with older adults in the Emergency Department-CREAT-ED: A multi-stage study protocol.

Trials·2026
Same author

Insights Into School-Based Physical Activity Implementation Strategies During the COVID-19 Pandemic: A Thematic Analysis.

Child: care, health and development·2025
Same author

Cell Cycle Arrest of a 'Zippering' Epithelial Cell Cluster Shapes the Face and is Disrupted in Craniofacial Disorders.

bioRxiv : the preprint server for biology·2025
Same author

Exploring the organisation and delivery of falls management in care homes for older people in England.

BMC geriatrics·2025

This study introduces an automatically initialized expectation-maximization algorithm for segmenting medical MRI images. This method improves image partitioning accuracy by eliminating the need for manual parameter initialization.

Area of Science:

  • Medical Imaging Analysis
  • Computer Vision
  • Machine Learning

Background:

  • Region-based segmentation algorithms aim to partition images into meaningful areas.
  • Optimization schemes commonly rely on minimizing/maximizing image intensity functions.
  • Parameter initialization significantly impacts the convergence and accuracy of these algorithms.

Purpose of the Study:

  • To develop and evaluate an automatically initialized expectation-maximization (EM) algorithm for medical MRI image segmentation.
  • To compare the performance of automatic initialization against manual initialization.
  • To apply the algorithm to standard medical image processing tasks.

Main Methods:

  • Implementation of an expectation-maximization (EM) algorithm.

Related Experiment Videos

Last Updated: Jul 13, 2026

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
04:48

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

  • Automatic initialization of algorithm parameters.
  • Statistical partitioning of medical MRI data.
  • Comparative analysis with manual initialization.

    • Main Results:

    • The automatically initialized EM algorithm effectively partitions medical MRI data.
    • Results demonstrate comparable or improved performance against manual initialization.
    • The algorithm shows applicability to common medical image processing tasks.

    Conclusions:

    • Automatic initialization provides a robust and efficient alternative to manual parameter setting in MRI segmentation.
    • The developed EM algorithm offers a valuable tool for medical image analysis.
    • Further applications in diverse medical imaging tasks are warranted.