Document Detail


Comparison of feature extraction and selection methods in mammogram recognition.
MedLine Citation:
PMID:  12594085     Owner:  NLM     Status:  MEDLINE    
Abstract/OtherAbstract:
This paper presents a comparison of feature extraction and selection methods in the design of mammogram recognition systems. Mammographic images were classified into two categories, normal and cancerous. The following methods of feature extraction were investigated: two-dimensional Haar wavelets, histograms, and singular value decomposition. The feature patterns were reduced and selected using principal component analysis (PCA) and rough sets. The rough sets methods were applied to the final selection of the pattern features. Classification of mammograms was realized using an error backpropagation neural network.
Authors:
R Swiniarski; A Swiniarska
Related Documents :
19366645 - Rough neuro-fuzzy structures for classification with missing data.
11699115 - Why do we slip to the basic level? computational constraints and their implementation.
16328675 - Synergistic techniques for better understanding and classifying the environmental struc...
18997275 - Real-time odor discrimination using a bioelectronic sensor array based on the insect el...
9631335 - Quantitative risk assessment for escherichia coli o157:h7 in ground beef hamburgers.
20442195 - Statistical models for the control phase of clinical monitoring.
Publication Detail:
Type:  Journal Article; Research Support, Non-U.S. Gov't    
Journal Detail:
Title:  Annals of the New York Academy of Sciences     Volume:  980     ISSN:  0077-8923     ISO Abbreviation:  Ann. N. Y. Acad. Sci.     Publication Date:  2002 Dec 
Date Detail:
Created Date:  2003-02-20     Completed Date:  2003-03-20     Revised Date:  2006-11-15    
Medline Journal Info:
Nlm Unique ID:  7506858     Medline TA:  Ann N Y Acad Sci     Country:  United States    
Other Details:
Languages:  eng     Pagination:  116-24     Citation Subset:  IM    
Affiliation:
Department of Computer Science, San Diego State University, California 92182, USA. rswiniar@sciences.sdsu.edu
Export Citation:
APA/MLA Format     Download EndNote     Download BibTex
MeSH Terms
Descriptor/Qualifier:
Breast / cytology
Breast Neoplasms / radiography
Female
Humans
Mammography / methods*
Pattern Recognition, Automated
Reference Values

From MEDLINE®/PubMed®, a database of the U.S. National Library of Medicine


Previous Document:  Functional magnetic resonance of human breast tumors: diffusion and perfusion imaging.
Next Document:  Tumor hypoxia and blood vessel detection: an image analysis technique for simultaneous tumor hypoxia...