Method, system and computer program product for breast density classification using fisher discrimination
AssigneesKing Fahd University of Petroleum and Minerals, King Abdulaziz City for Science and Technology
InventorLahouari Ghouti
Life of this patent
Estimating the term…
Abstract
A method for content-based image retrieval for the classification of breast density from mammographic imagery is described. The breast density is characterized through the Fisher linear discriminants (FLD) extracted from the Principal Component Analysis (PCA). Unlike PCA, the FLD provides a very discriminative representation of the mammographic images in terms of the breast density. Various exemplary methods, systems and computer program products are also disclosed.
Claims5
A system for classifying breast density from mammographic imagery using content-based image retrieval, the system comprising:
- circuitry configured to
- store a mammogram image database;
- pre-process one or more digital mammogram images of a patient to remove noise and enhance contrast;
- segment the one or more digital mammogram images to produce one or more extracted regions of interest and save the one or more extracted regions of interest;
- group the one or more saved extracted regions of interest to produce a large mammogram image;
- decompose the large mammogram image by principal component analysis (PCA) in the mammogram image database;
- and
- classify the large mammogram image according to breast density with Fisher Linear Discriminant (FLD) in the mammogram image database.
Dependencies are inferred from the claim text.