DocumentCode :
2728849
Title :
A Comparison of Different Gabor Features for Mass Classification in Mammography
Author :
Hussain, Mutawarra ; Khan, Sharifullah ; Muhammad, Ghulam ; Bebis, G.
Author_Institution :
Dept. of Comput. Sci., King Saud Univ., Riyadh, Saudi Arabia
fYear :
2012
fDate :
25-29 Nov. 2012
Firstpage :
142
Lastpage :
148
Abstract :
Masses are among the early signs of breast cancer, which is the second major cause of death in women. For mass detection, a mammogram is segmented into regions of interest (ROIs) that contain masses as well as suspicious normal tissues, which lead to false positives. The problem is to reduce the false positives by classifying ROIs as masses and normal tissues. Further, the detected masses are needed to be discriminated as benign and malignant. We investigate the performance of six different Gabor feature extraction approaches for these mass classification problems. These techniques employ Gabor filter banks for extracting multiscale and multiorientation texture features which represent structural properties of masses and normal dense tissues in mammograms. The feature extraction approaches are evaluated over the ROIs extracted from MIAS database. Successive Enhancement Learning based weighted Support Vector Machine (SELwSVM) is used to efficiently classify the generated unbalanced datasets. The best performance in terms of area under ROC curve (Az = 1.0) is obtained by the Gabor features extracted using first order statistics of the Gabor responses and LDA.
Keywords :
Gabor filters; biological tissues; cancer; channel bank filters; feature extraction; image texture; mammography; medical image processing; object detection; signal classification; support vector machines; Gabor feature extraction approach; Gabor filter banks; LDA; MIAS database; ROC curve; ROI; SELwSVM; breast cancer; false positive reduction; first order statistics; mammography; mass classification problems; mass detection; multiorientation texture feature technique; multiscale texture feature extraction; region of interest; structural property; successive enhancement learning based weighted support vector machine; suspicious normal tissues; Cancer; Feature extraction; Filter banks; Gabor filters; Kernel; Support vector machines; Training; Directional features; Gabor Filter Bank; LDA; Mammography; Mass Classification; PCA; SEL weighted SVM;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Signal Image Technology and Internet Based Systems (SITIS), 2012 Eighth International Conference on
Conference_Location :
Naples
Print_ISBN :
978-1-4673-5152-2
Type :
conf
DOI :
10.1109/SITIS.2012.31
Filename :
6395087
Link To Document :
بازگشت