Research Article Open Access

GAUSSIAN MIXTURE MODEL BASED CLASSIFICATION OF MICROCALCIFICATION IN MAMMOGRAMS USING DYADIC WAVELET TRANSFORM

Suman Mishra1 and Hariharan Ranganathan2
  • 1 Sathyabama University, India
  • 2 , India

Abstract

Breast cancer is a serious health related issue for women in the world. Cancer detected at premature stages has a higher probability of being cured, whereas at advanced stages chances of survival are bleak. Screening programs aid in detecting potential breast cancer at early stages of the disease. Among the various screening programs, mammography is the proven standard for screening breast cancer, because even small tumors can be detected on mammograms. In this study, a novel feature extraction technique based on dyadic wavelet transform for classification of microcalcification in digital mammograms is proposed. In the feature extraction module, the high frequency sub-bands obtained from the decomposition of dyadic wavelet transform is used to form innovative sub-bands. From the newly constructed sub-bands, the features such as energy and entropy are computed. In the classification module, the extracted features are fed into a Gaussian Mixture Model (GMM) classifier and the severity of given microcalcification; benign or malignant are given. A classification accuracy of 95.5% is obtained using the proposed approach on DDSM database.

Journal of Computer Science
Volume 9 No. 10, 2013, 1348-1355

DOI: https://doi.org/10.3844/jcssp.2013.1348.1355

Submitted On: 17 August 2013 Published On: 5 September 2013

How to Cite: Mishra, S. & Ranganathan, H. (2013). GAUSSIAN MIXTURE MODEL BASED CLASSIFICATION OF MICROCALCIFICATION IN MAMMOGRAMS USING DYADIC WAVELET TRANSFORM. Journal of Computer Science, 9(10), 1348-1355. https://doi.org/10.3844/jcssp.2013.1348.1355

  • 2,733 Views
  • 2,250 Downloads
  • 1 Citations

Download

Keywords

  • Dyadic Wavelet Transform
  • Gaussian Mixture Model
  • Digital Mammograms
  • Microcalcification
  • Benign and Malignant
  • DDSM Database