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

Optimal filter-based detection of microcalcifications.

T O Gulsrud1, J H Husøy

  • 1Department of Electircal and Computer Engineering, Stavanger University College, Norway. thor.gulsrud@th.his.no

IEEE Transactions on Bio-Medical Engineering
|November 1, 2001
PubMed
Summary
This summary is machine-generated.

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

Texture segmentation using filters with optimized energy separation.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2008
Same author

"Probability of successful defibrillation" as a monitor during CPR in out-of-hospital cardiac arrested patients.

Resuscitation·2001
Same author

CPR artifact removal from human ECG using optimal multichannel filtering.

IEEE transactions on bio-medical engineering·2000
Same author

Predicting outcome of defibrillation by spectral characterization and nonparametric classification of ventricular fibrillation in patients with out-of-hospital cardiac arrest.

Circulation·2000
Same author

Optimisation algorithms for ECG data compression.

Medical & biological engineering & computing·1997
Same author

Computationally efficient sub-band coding of ECG signals.

Medical engineering & physics·1996

This study introduces a novel texture feature extraction method for digital mammograms to detect microcalcifications. The method effectively identifies clustered microcalcifications in both uncompressed and compressed images, maintaining high accuracy.

Area of Science:

  • Medical Imaging
  • Biomedical Engineering
  • Digital Signal Processing

Background:

  • Accurate detection of microcalcifications in digital mammograms is crucial for early breast cancer diagnosis.
  • Texture analysis plays a vital role in differentiating between pathological and normal tissue patterns.
  • Image compression is essential for efficient storage and transmission of mammographic data.

Purpose of the Study:

  • To develop and evaluate a texture feature extraction method for discriminating microcalcifications from normal tissue in digital mammograms.
  • To assess the impact of Joint Photographic Experts Group (JPEG) compression on the performance of the proposed detection scheme.

Main Methods:

  • A texture feature extraction method utilizing a single filter optimized with the Fisher criterion was proposed.

Related Experiment Videos

  • The Fisher criterion was employed to maximize feature separation by considering both mean and variance.
  • Mammograms were compressed using JPEG at various ratios to evaluate performance under compression.

    • Main Results:

    • The proposed method achieved a high true positive rate of approximately 95% for uncompressed mammograms at 1.5 false positive clusters/image.
    • Detection performance remained robust even when mammograms were compressed by a factor of approximately four.
    • The method demonstrated suitability for detecting clustered microcalcifications in both uncompressed and compressed digital mammograms.

    Conclusions:

    • The developed texture feature extraction method is effective for detecting clustered microcalcifications in digital mammograms.
    • The proposed scheme exhibits resilience to JPEG compression, making it practical for clinical applications involving electronic data handling.
    • This approach offers a promising tool for improving the accuracy and efficiency of mammographic analysis.