Get 20M+ Full-Text Papers For Less Than $1.50/day. Start a 7-Day Trial for You or Your Team.

Learn More →

Characterization and classification of tumor lesions using computerized fractal-based texture analysis and support vector machines in digital mammograms

Characterization and classification of tumor lesions using computerized fractal-based texture... Int J CARS (2009) 4:11–25 DOI 10.1007/s11548-008-0276-8 ORIGINAL ARTICLE Characterization and classification of tumor lesions using computerized fractal-based texture analysis and support vector machines in digital mammograms Qi Guo · Jiaqing Shao · Virginie F. Ruiz Received: 13 June 2008 / Accepted: 23 September 2008 / Published online: 28 October 2008 © CARS 2008 Abstract highest area under ROC curve ( A = 0.839 for dataset1, Objective This paper presents a detailed study of fractal- 0.828 for dataset2, respectively) among five methods for both based methods for texture characterization of mammogra- datasets. Lacunarity analysis showed that the ROIs depicting phic mass lesions and architectural distortion. The purpose mass lesions and architectural distortion had higher lacunari- of this study is to explore the use of fractal and lacunarity ana- ties than those of ROIs depicting normal breast parenchyma. lysis for the characterization and classification of both tumor The combination of FBM fractal dimension and lacunarity lesions and normal breast parenchyma in mammography. yielded the highest A value (0.903 and 0.875, respectively) Materials and methods We conducted comparative evalua- than those based on single feature alone for both given data- tions of five popular fractal dimension estimation methods sets. The application http://www.deepdyve.com/assets/images/DeepDyve-Logo-lg.png International Journal of Computer Assisted Radiology and Surgery Springer Journals

Characterization and classification of tumor lesions using computerized fractal-based texture analysis and support vector machines in digital mammograms

Download PDF
15 pages

Loading next page...
 
/lp/springer-journals/characterization-and-classification-of-tumor-lesions-using-Xg6dUGZpjV

References (51)

Publisher
Springer Journals
Copyright
Copyright © 2008 by CARS
Subject
Medicine & Public Health; Computer Science, general ; Computer Imaging, Vision, Pattern Recognition and Graphics; Health Informatics; Surgery ; Imaging / Radiology
ISSN
1861-6410
eISSN
1861-6429
DOI
10.1007/s11548-008-0276-8
pmid
20033598
Publisher site
See Article on Publisher Site

Abstract

Int J CARS (2009) 4:11–25 DOI 10.1007/s11548-008-0276-8 ORIGINAL ARTICLE Characterization and classification of tumor lesions using computerized fractal-based texture analysis and support vector machines in digital mammograms Qi Guo · Jiaqing Shao · Virginie F. Ruiz Received: 13 June 2008 / Accepted: 23 September 2008 / Published online: 28 October 2008 © CARS 2008 Abstract highest area under ROC curve ( A = 0.839 for dataset1, Objective This paper presents a detailed study of fractal- 0.828 for dataset2, respectively) among five methods for both based methods for texture characterization of mammogra- datasets. Lacunarity analysis showed that the ROIs depicting phic mass lesions and architectural distortion. The purpose mass lesions and architectural distortion had higher lacunari- of this study is to explore the use of fractal and lacunarity ana- ties than those of ROIs depicting normal breast parenchyma. lysis for the characterization and classification of both tumor The combination of FBM fractal dimension and lacunarity lesions and normal breast parenchyma in mammography. yielded the highest A value (0.903 and 0.875, respectively) Materials and methods We conducted comparative evalua- than those based on single feature alone for both given data- tions of five popular fractal dimension estimation methods sets. The application

Journal

International Journal of Computer Assisted Radiology and Surgery – Springer Journals

Published: Oct 28, 2008

There are no references for this article.