Classification of breast masses using selected shape, edge-sharpness, and texture features with linear and kernel-based classifiers

被引:64
作者
Mu, Tingting [1 ]
Nandi, Asoke K. [1 ]
Rangayyan, Rangaraj M. [2 ]
机构
[1] Univ Liverpool, Dept Elect Engn & Elect, Liverpool L69 3GJ, Merseyside, England
[2] Univ Calgary, Schulich Sch Engn, Dept Elect & Comp Engn, Calgary, AB T2N 1N4, Canada
基金
英国医学研究理事会;
关键词
breast masses; breast tumors; mammography; computer-aided diagnosis; feature selection; pattern classification; kernel-based classifiers; shape analysis; edge-sharpness analysis; texture analysis;
D O I
10.1007/s10278-007-9102-z
中图分类号
R8 [特种医学]; R445 [影像诊断学];
学科分类号
1002 [临床医学]; 100207 [影像医学与核医学]; 1009 [特种医学];
摘要
Breast masses due to benign disease and malignant tumors related to breast cancer differ in terms of shape, edge-sharpness, and texture characteristics. In this study, we evaluate a set of 22 features including 5 shape factors, 3 edge-sharpness measures, and 14 texture features computed from 111 regions in mammograms, with 46 regions related to malignant tumors and 65 to benign masses. Feature selection is performed by a genetic algorithm based on several criteria, such as alignment of the kernel with the target function, class separability, and normalized distance. Fisher's linear discriminant analysis, the support vector machine (SVM), and our strict two-surface proximal (S2SP) classifier, as well as their corresponding kernel-based nonlinear versions, are used in the classification task with the selected features. The nonlinear classification performance of kernel Fisher's discriminant analysis, SVM, and S2SP, with the Gaussian kernel, reached 0.95 in terms of the area under the receiver operating characteristics curve. The results indicate that improvement in classification accuracy may be gained by using selected combinations of shape, edge-sharpness, and texture features.
引用
收藏
页码:153 / 169
页数:17
相关论文
共 53 条
[1]
AIZERMAN MA, 1965, AUTOMAT REM CONTR+, V25, P821
[2]
*ALB CANC BOARD, 2001, ALB PROGR EARL DET B
[3]
Content-based retrieval and analysis of mammographic masses [J].
Alto, H ;
Rangayyan, RM ;
Desautels, JEL .
JOURNAL OF ELECTRONIC IMAGING, 2005, 14 (02) :1-17
[4]
Classification of breast masses in mammograms using neural networks with shape, edge sharpness, and texture features [J].
Andre, Tulio C. S. S. ;
Rangayyan, Rangaraj Mandayam .
JOURNAL OF ELECTRONIC IMAGING, 2006, 15 (01)
[5]
[Anonymous], 2004, KERNEL METHODS PATTE
[6]
[Anonymous], 1978, REMOTE SENSING QUANT
[7]
[Anonymous], 1992, GENETIC ALGORITHMS
[8]
Boser B. E., 1992, Proceedings of the Fifth Annual ACM Workshop on Computational Learning Theory, P144, DOI 10.1145/130385.130401
[9]
*BREAST EXP WORKGR, 2005, BREAST CANC DIAGN AL
[10]
Classifying mammographic mass shapes using the wavelet transform modulus-maxima method [J].
Bruce, LM ;
Adhami, RR .
IEEE TRANSACTIONS ON MEDICAL IMAGING, 1999, 18 (12) :1170-1177