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

Image segmentation feature selection and pattern classification for mammographic microcalcifications.

J C Fu1, S K Lee, S T C Wong

  • 1Automated Measurement and Diagnostic Systems Laboratory, Department of Industrial Engineering and Technology Management, Da-Yeh University, 112 Shan-Jeau Rd, Da-Tsuen 515, Chang-Hwa, Taiwan, ROC. jc0001@aries.dyu.edu.tw

Computerized Medical Imaging and Graphics : the Official Journal of the Computerized Medical Imaging Society
|July 9, 2005
PubMed
Summary

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

[A nested case-control study on factors affecting hepatitis B surface antigen natural clearance in community populations].

Zhonghua liu xing bing xue za zhi = Zhonghua liuxingbingxue zazhi·2026
Same author

[Evaluation of risk factors in diabetic foot infections with systemic inflammatory response syndrome].

Zhonghua yi xue za zhi·2024
Same author

[Effect of baseline LH/FSH ratio in PCOS on IVF-ET outcomes: a retrospective cohort study].

Zhonghua fu chan ke za zhi·2024
Same author

[Primary central nervous system ALK-positive anaplastic large cell lymphoma: a clinicopathological analysis of four cases].

Zhonghua bing li xue za zhi = Chinese journal of pathology·2023
Same author

[Investigation of serum surface active protein D and clara cell protein levels in workers exposed to silica dust in ferrous metal foundry].

Zhonghua lao dong wei sheng zhi ye bing za zhi = Zhonghua laodong weisheng zhiyebing zazhi = Chinese journal of industrial hygiene and occupational diseases·2023
Same author

[Radiographic diagnosis of distal fibula avulsion fractures: Comparison of ankle X-ray and three-dimensional reconstruction of CT].

Beijing da xue xue bao. Yi xue ban = Journal of Peking University. Health sciences·2023

This study introduces a two-stage method for detecting microcalcifications in mammograms. A novel mathematical model and feature selection significantly improved breast cancer detection accuracy using support vector machines.

Area of Science:

  • Medical Imaging
  • Biomedical Engineering
  • Computational Pathology

Background:

  • Microcalcifications in X-ray mammograms are critical indicators for early breast cancer detection.
  • Accurate detection systems are essential for effective breast cancer diagnostics.
  • Existing methods may require extensive system training and lack detailed feature information.

Purpose of the Study:

  • To develop and evaluate a two-stage microcalcification detection procedure for mammograms.
  • To assess the performance of a data-driven mathematical model and feature selection algorithms.
  • To compare the efficacy of Support Vector Machines (SVM) and General Regression Neural Networks (GRNN) for classification.

Main Methods:

  • A data-driven, closed-form mathematical model was employed for initial microcalcification localization and shape analysis.

Related Experiment Videos

  • Sixty-one features (texture, spatial, spectral) were extracted from suspected microcalcifications.
  • A Sequential Forward Search (SFS) algorithm was used for feature selection, followed by classification using SVM and GRNN.

    • Main Results:

    • The proposed mathematical model effectively detected microcalcifications without requiring system training.
    • The SVM achieved an Az value of 98.00% with SFS-selected features, outperforming the GRNN (97.80%).
    • SFS feature selection improved classification performance and significantly reduced feature vector dimensions (up to 82%).

    Conclusions:

    • The developed two-stage approach offers an effective and efficient method for microcalcification detection in mammography.
    • The combination of a mathematical model, SFS feature selection, and SVM classification demonstrates high diagnostic accuracy.
    • This method enhances breast cancer detection by providing accurate localization and classification of microcalcifications.