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: May 23, 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

Pixel-based machine learning in medical imaging.

Kenji Suzuki1

  • 1Department of Radiology, The University of Chicago, 5841 South Maryland Avenue, MC 2026, Chicago, IL 60637, USA.

International Journal of Biomedical Imaging
|April 7, 2012
PubMed
Summary

Pixel/voxel-based machine learning (ML) offers a promising approach for medical image analysis by directly using pixel data. This method bypasses feature extraction and segmentation, potentially improving diagnostic accuracy for complex medical images.

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

Is lower zone mediastinal nodal dissection always mandatory for lung cancer in the lower lobe?

Surgery today·2015
Same author

Myocardial 14-3-3η protein protects against mitochondria mediated apoptosis.

Cellular signalling·2015
Same author

Midazolam inhibits the formation of amyloid fibrils and GM1 ganglioside-rich microdomains in presynaptic membranes through the gamma-aminobutyric acid A receptor.

Biochemical and biophysical research communications·2015
Same author

Development of MRI-powered modular robotic system.

Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference·2015
Same author

Clinical Outcomes of SMART Versus Luminexx Nitinol Stent Implantation for Aortoiliac Artery Disease: A Propensity Score-Matched Multicenter Study.

Angiology·2014
Same author

Two-year life expectancy in patients with critical limb ischemia.

JACC. Cardiovascular interventions·2014

Area of Science:

  • Medical Imaging
  • Machine Learning
  • Computer-Aided Diagnosis

Background:

  • Machine learning (ML) is crucial for medical image analysis and computer-aided diagnosis.
  • Traditional ML methods rely on extracted features from segmented objects, which can introduce errors.
  • Accurate representation of lesions and organs often requires learning from examples rather than simple equations.

Purpose of the Study:

  • To survey pixel/voxel-based machine learning (PML) methods in medical imaging.
  • To clarify the classes, similarities, differences, advantages, and limitations of PMLs.
  • To compare PMLs with traditional feature-based ML approaches.

Main Methods:

  • Review and analysis of existing literature on pixel/voxel-based machine learning in medical imaging.

Related Experiment Videos

Last Updated: May 23, 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

  • Categorization of different PML approaches.
  • Comparative analysis of PMLs against feature-based ML methods.

    • Main Results:

    • PML utilizes raw pixel/voxel values directly, eliminating the need for feature calculation and segmentation.
    • This direct approach can mitigate errors associated with segmentation and feature extraction, especially for subtle or complex objects.
    • PML shows potential for higher performance compared to traditional ML classifiers in specific medical imaging applications.

    Conclusions:

    • PML represents a significant advancement in medical image analysis, offering a more direct and potentially more accurate approach.
    • The method's ability to bypass segmentation and feature engineering makes it advantageous for complex medical patterns.
    • Further research into PML classes, applications, and comparative performance is warranted.