Classification of breast regions as mass and non-mass based on digital mammograms using taxonomic indexes and SVM

被引:58
作者
Servulo de Oliveira, Fernando Soares [1 ]
de Carvalho Filho, Antonio Oseas [1 ]
Silva, Aristofanes Correa [1 ]
de Paiva, Anselmo Cardoso [1 ]
Gattass, Marcelo [2 ]
机构
[1] Fed Univ Maranhao UFMA, Appl Comp Grp NCA, BR-65085580 Sao Luis, MA, Brazil
[2] Pontifical Catholic Univ Rio de Janeiro PUC Rio, BR-22453900 Rio De Janeiro, RJ, Brazil
关键词
Medical image; Breast cancer; Phylogenetic trees; Taxonomic diversity index (Delta); Taxonomic distinctness (Delta*); FEATURES;
D O I
10.1016/j.compbiomed.2014.11.016
中图分类号
Q [生物科学];
学科分类号
07 ; 0710 ; 09 ;
摘要
Breast cancer is the second most common type of cancer in the world. Several computer-aided detection and diagnosis systems have been used to assist health experts identify suspicious areas that are difficult to perceive with the human eye, thus aiding in the detection and diagnosis of cancer. This work proposes a methodology for the discrimination and classification of regions extracted from mammograms as mass and non-mass. The Digital Database for Screening Mammography (DDSM) was used in this work for the acquisition of mammograms. The taxonomic diversity index (Delta) and the taxonomic distinctness (Delta*), which were originally used in ecology, were used to describe the texture of the regions of interest. These indexes were computed based on phylogenetic trees, which were applied to describe the patterns in regions of breast images. Two approaches were used for the analysis of texture: internal and external masks. A support vector machine was used to classify the regions as mass and non-mass. The proposed methodology successfully classified the masses and non-masses, with an average accuracy of 98.88%. (C) 2014 Elsevier Ltd. All rights reserved.
引用
收藏
页码:42 / 53
页数:12
相关论文
共 29 条
[1]  
[Anonymous], 2001, J. Am. Stat. Assoc.
[2]  
[Anonymous], 1992, R. woods digital image processing
[3]  
[Anonymous], INT J COMP APPL
[4]  
Baxevanis AD, 2004, METHODS BIOCH ANAL
[5]  
Berbar M.A., 2012, IV IEEE COMP SOC, VIV, P486
[6]   A mass classification using spatial diversity approaches in mammography images for false positive reduction [J].
Braz Junior, Geraldo ;
da Rocha, Simara Vieira ;
Gattass, Marcelo ;
Silva, Aristofanes Correa ;
de Paiva, Anselmo Cardoso .
EXPERT SYSTEMS WITH APPLICATIONS, 2013, 40 (18) :7534-7543
[7]  
Chang C.C., 2009, LIBSVM LIB SUPPORT V
[8]   A taxonomic distinctness index and its statistical properties [J].
Clarke, KR ;
Warwick, RM .
JOURNAL OF APPLIED ECOLOGY, 1998, 35 (04) :523-531
[9]   Classification of breast tissue in mammograms using efficient coding [J].
Costa, Daniel D. ;
Campos, Lucio F. ;
Barros, Allan K. .
BIOMEDICAL ENGINEERING ONLINE, 2011, 10
[10]   Taxonomic distinctness and diversity of a hyperseasonal savanna in central Brazil [J].
da Silva, Igor Aurelio ;
Batalha, Marco Antonio .
DIVERSITY AND DISTRIBUTIONS, 2006, 12 (06) :725-730