Computer-Aided Diagnosis of Malignant Mammograms using Zernike Moments and SVM

被引:81
作者
Sharma, Shubhi [1 ]
Khanna, Pritee [1 ]
机构
[1] Pandit Dwarka Prasad Mishra Indian Inst Informat, Jabalpur 482005, Madhya Pradesh, India
关键词
Computer-aided diagnosis (CAD); Mammograms; Preprocessing; Segmentation; Zernike moments; Support vector machine (SVM); BREAST-CANCER DETECTION; CLUSTERED MICROCALCIFICATIONS; AUTOMATIC DETECTION; CLASSIFICATION; MASSES; RECOGNITION; SYSTEM; IDENTIFICATION; SEGMENTATION;
D O I
10.1007/s10278-014-9719-7
中图分类号
R8 [特种医学]; R445 [影像诊断学];
学科分类号
1002 ; 100207 ; 1009 ;
摘要
This work is directed toward the development of a computer-aided diagnosis (CAD) system to detect abnormalities or suspicious areas in digital mammograms and classify them as malignant or nonmalignant. Original mammogram is preprocessed to separate the breast region from its background. To work on the suspicious area of the breast, region of interest (ROI) patches of a fixed size of 128x128 are extracted from the original large-sized digital mammograms. For training, patches are extracted manually from a preprocessed mammogram. For testing, patches are extracted from a highly dense area identified by clustering technique. For all extracted patches corresponding to a mammogram, Zernike moments of different orders are computed and stored as a feature vector. A support vector machine (SVM) is used to classify extracted ROI patches. The experimental study shows that the use of Zernike moments with order 20 and SVM classifier gives better results among other studies. The proposed system is tested on Image Retrieval In Medical Application (IRMA) reference dataset and Digital Database for Screening Mammography (DDSM) mammogram database. On IRMA reference dataset, it attains 99 % sensitivity and 99 % specificity, and on DDSM mammogram database, it obtained 97 % sensitivity and 96 % specificity. To verify the applicability of Zernike moments as a fitting texture descriptor, the performance of the proposed CAD system is compared with the other well-known texture descriptors namely gray-level co-occurrence matrix (GLCM) and discrete cosine transform (DCT).
引用
收藏
页码:77 / 90
页数:14
相关论文
共 53 条
[1]   COMPUTER AIDED DIAGNOSIS IN DIGITAL MAMMOGRAPHY USING COMBINED SUPPORT VECTOR MACHINE AND LINEAR DISCRIMINANT ANALYASIS CLASSIFICATION [J].
Alolfe, Mohammed A. ;
Mohamed, Wael A. ;
Youssef, Abou-Bakr M. ;
Mohamed, Ahmed S. ;
Kadah, Yasser M. .
2009 16TH IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING, VOLS 1-6, 2009, :2609-2612
[2]  
[Anonymous], 2009, ARXIV09122314, DOI DOI 10.7717/PEERJ.6201
[3]  
[Anonymous], 2008, 2008 NAT RAD SCI C, DOI DOI 10.1109/NRSC.2008.4542383
[4]  
[Anonymous], 2000, P 5 INT WORKSH DIG M
[5]  
Astley S., 1993, International Journal of Pattern Recognition and Artificial Intelligence, V7, P1313, DOI 10.1142/S0218001493000649
[6]   Breast cancer detection using rank nearest neighbor classification rules [J].
Bagui, SC ;
Bagui, S ;
Pal, K ;
Pal, NR .
PATTERN RECOGNITION, 2003, 36 (01) :25-34
[7]  
Balakumaran T., 2011, Proceedings of the 2011 World Congress on Information and Communication Technologies (WICT), P657, DOI 10.1109/WICT.2011.6141323
[8]  
Bovik AC., 2010, Handbook of Image and Video Processing
[9]   IMPROVEMENT IN RADIOLOGISTS DETECTION OF CLUSTERED MICROCALCIFICATIONS ON MAMMOGRAMS - THE POTENTIAL OF COMPUTER-AIDED DIAGNOSIS [J].
CHAN, HP ;
DOI, K ;
VYBORNY, CJ ;
SCHMIDT, RA ;
METZ, CE ;
LAM, KL ;
OGURA, T ;
WU, YZ ;
MACMAHON, H .
INVESTIGATIVE RADIOLOGY, 1990, 25 (10) :1102-1110
[10]   Approaches for automated detection and classification of masses in mammograms [J].
Cheng, HD ;
Shi, XJ ;
Min, R ;
Hu, LM ;
Cai, XR ;
Du, HN .
PATTERN RECOGNITION, 2006, 39 (04) :646-668