MammoSys: A content-based image retrieval system using breast density patterns

Abstract In this paper, we present a content-based image retrieval system designed to retrieve mammographies from large medical image database. The system is developed based on breast density, according to the four categories defined by the American College of Radiology, and is integrated to the dat...

Full description

Saved in:
Bibliographic Details
Published inComputer methods and programs in biomedicine Vol. 99; no. 3; pp. 289 - 297
Main Authors de Oliveira, Júlia E.E, Machado, Alexei M.C, Chavez, Guillermo C, Lopes, Ana Paula B, Deserno, Thomas M, Araújo, Arnaldo de A
Format Journal Article
LanguageEnglish
Published Ireland Elsevier Ireland Ltd 01.09.2010
Subjects
Access to Information
Algorithms
Artificial Intelligence
Breast - pathology
Breast density
Breast Neoplasms - diagnosis
Breast Neoplasms - pathology
Content-based image retrieval
Databases, Factual
Feasibility Studies
Female
Humans
Image Processing, Computer-Assisted - instrumentation
Image Processing, Computer-Assisted - methods
Information Storage and Retrieval - methods
Internal Medicine
Mammography - instrumentation
Medical images
Models, Theoretical
Other
Principal Component Analysis
Support vector machine
Two-dimensional principal component analysis
Medical images
Breast density
Content-based image retrieval
Support vector machine
Two-dimensional principal component analysis
Online AccessGet full text

Cover

More Information
Summary:Abstract In this paper, we present a content-based image retrieval system designed to retrieve mammographies from large medical image database. The system is developed based on breast density, according to the four categories defined by the American College of Radiology, and is integrated to the database of the Image Retrieval in Medical Applications (IRMA) project, that provides images with classification ground truth. Two-dimensional principal component analysis is used in breast density texture characterization, in order to effectively represent texture and allow for dimensionality reduction. A support vector machine is used to perform the retrieval process. Average precision rates are in the range from 83% to 97% considering a data set of 5024 images. The results indicate the potential of the system as the first stage of a computer-aided diagnosis framework.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
ISSN:0169-2607
1872-7565
DOI:10.1016/j.cmpb.2010.01.005