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

Digital mammography: hybrid four-channel wavelet transform for microcalcification segmentation

W Qian1, L P Clarke, D Song

  • 1Department of Radiology, College of Medicine, University of South Florida, Tampa, FL 33612, USA.

Academic Radiology
|May 23, 1998
PubMed
Summary

A four-channel wavelet transform improved microcalcification cluster detection sensitivity in digital mammography. This method also enhanced image detail preservation and reduced false positives, aiding in classification.

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

[Basic research and clinical applications progress of gastrointestinal developmental anatomy surgery].

Zhonghua wai ke za zhi [Chinese journal of surgery]·2026
Same author

B-Cell Landscape in Inflamed Dental Pulp Reveals Potential Autoimmune Involvement.

Journal of dental research·2026
Same author

MRI-based radiomics model for the preoperative prediction of classification in children with venous malformations.

Clinical radiology·2025
Same author

H<sub>2</sub>S signal enhances storage globulin hydrolysis, embryo supercooling and freezing tolerance of hydrated brassica (Brassica oleracea) seeds.

Cryo letters·2025
Same author

The optimal moisture content for cryopreservation of Longjing tea seeds.

Cryo letters·2025
Same author

[Diazepam alleviates pulmonary fibrosis in mice by inhibiting LPS-induced pyroptosis and inflammation <i>via</i> the let-7a-5p/MYD88 axis].

Nan fang yi ke da xue xue bao = Journal of Southern Medical University·2024

Area of Science:

  • Medical imaging analysis
  • Digital mammography
  • Image processing algorithms

Background:

  • Accurate segmentation of microcalcification clusters (MCCs) is crucial for breast cancer diagnosis in digital mammography.
  • Existing algorithms require optimization for improved sensitivity and detail preservation.

Purpose of the Study:

  • To evaluate a hybrid algorithm for automatic MCC segmentation using wavelet transforms.
  • To compare two- and four-channel wavelet transforms for MCC detection sensitivity and classification suitability.
  • To assess the impact of different filter bank structures on computational efficiency and reconstruction quality.

Main Methods:

  • A hybrid method combining nonlinear noise suppression, wavelet decomposition, and adaptive subimage reconstruction was employed.

Related Experiment Videos

  • Two- and four-channel wavelet transforms with polyphase QMF, tree, and lattice structures were implemented.
  • The algorithm was tested on a database of biopsy-proven microcalcification clusters.

    • Main Results:

    • Four-channel wavelet transforms achieved 94% sensitivity with a false-positive rate of 1.35 MCCs/image, outperforming two-channel transforms (93% sensitivity, 1.58 FP/image).
    • The lattice filter structure significantly improved computational speed, especially for higher-order channels.
    • Selective reconstruction of higher-order subimages aided in preserving segmented MCC details.

    Conclusions:

    • The four-channel wavelet transform offers superior performance for MCC segmentation in digital mammography.
    • This approach enhances diagnostic accuracy through improved sensitivity and better preservation of crucial image details.
    • Optimized filter structures contribute to computational efficiency without compromising reconstruction quality.