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 Videos

A multi-scale probabilistic network model for detection, synthesis and compression in mammographic image analysis.

Paul Sajda1, Clay Spence, Lucas Parra

  • 1Department of Biomedical Engineering, Columbia University, 351 Engineering Terrace, MC 8904, New York, NY 10027, USA. sajda@columbia.edu

Medical Image Analysis
|July 19, 2003
PubMed
Summary

We developed a novel probabilistic network model for mammographic image analysis. This model enhances computer-aided diagnosis by accurately detecting masses and improving image compression.

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

Alpha Modulation of Spiking Activity Across Multiple Brain Regions in Mice Performing a Tactile Selective Detection Task.

The European journal of neuroscience·2025
Same author

Superficial Fluctuations in Functional Near-Infrared Spectroscopy during Concurrent Transcranial Magnetic Stimulation.

Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference·2025
Same author

TMS-induced modulation of brain networks and its associations to rTMS treatment for depression: a concurrent fMRI-EEG-TMS study.

Brain stimulation·2025
Same author

Brain2Model Transfer: Training sensory and decision models with human neural activity as a teacher.

ArXiv·2025
Same author

Alpha modulation of spiking activity across multiple brain regions in mice performing a tactile selective detection task.

bioRxiv : the preprint server for biology·2025
Same author

Phase synchrony between prefrontal noradrenergic and cholinergic signals indexes inhibitory control.

Nature communications·2025

Area of Science:

  • Medical Imaging
  • Artificial Intelligence
  • Statistical Modeling

Background:

  • Mammographic image analysis is crucial for early breast cancer detection.
  • Existing computer-aided diagnosis (CAD) systems require robust image analysis models.

Purpose of the Study:

  • To develop a probabilistic network model for mammographic image analysis.
  • To demonstrate the model's utility in computer-aided diagnosis (CAD).

Main Methods:

  • A multi-scale pyramid decomposition was used to factor images across scales.
  • A network of tree-structured hidden variables captured long-range spatial dependencies.
  • Maximum likelihood estimation with the expectation-maximization algorithm determined model parameters.

Related Experiment Videos

Main Results:

  • The model demonstrated utility in detecting mammographic masses for CAD.
  • Mammographic synthesis showed qualitative assessment of model structure.
  • Compression of mammographic regions of interest was achieved.

Conclusions:

  • The developed probabilistic network model is effective for mammographic image analysis.
  • The model shows significant potential for improving computer-aided diagnosis.
  • The model's hierarchical structure enables tractable computations and broad utility.