Automated Diagnosis of Mammogram Images of Breast Cancer Using Discrete Wavelet Transform and Spherical Wavelet Transform Features: A Comparative Study
Open accessResearch articleFirst published online December, 2014
Automated Diagnosis of Mammogram Images of Breast Cancer Using Discrete Wavelet Transform and Spherical Wavelet Transform Features: A Comparative Study
Mammograms are one of the most widely used techniques for preliminary screening of breast cancers. There is great demand for early detection and diagnosis of breast cancer using mammograms. Texture based feature extraction techniques are widely used for mammographic image analysis. In specific, wavelets are a popular choice for texture analysis of these images. Though discrete wavelets have been used extensively for this purpose, spherical wavelets have rarely been used for Computer-Aided Diagnosis (CAD) of breast cancer using mammograms. In this work, a comparison of the performance between the features of Discrete Wavelet Transform (DWT) and Spherical Wavelet Transform (SWT) based on the classification results of normal, benign and malignant stage was studied. Classification was performed using Linear Discriminant Classifier (LDC), Quadratic Discriminant Classifier (QDC), Nearest Mean Classifier (NMC), Support Vector Machines (SVM) and Parzen Classifier (ParzenC). We have obtained a maximum classification accuracy of 81.73% for DWT and 88.80% for SWT features using SVM classifier.
References
1.
ChristoyianniIKoutrasAADermatasE & KokkinakisG. Computer aided diagnosis of breast cancer in digitized mammograms. Computerized Medical Imaging and Graphics26 (5), 309–319 (2002). DOI: 10.1016/S0895-6111(02)00031-9.
2.
Heang-PingCSahinerBHelvieMAPetrickNRoubidouxMAWilsonTEAdlerDDParamagulCNewmanJS & Sanjay-GopalS. Improvement of radiologists' characterization of mammographic masses by using computer-aided diagnosis: An ROC study. Radiology212, 817–827, (1999).
3.
DoiKMacMahonHKatsuragawaSNishikawaRM & JiangY. Computer-aided diagnosis in radiology: Potential and pitfalls. European Journal of Radiology31, 97–109, (1999). DOI: 10.1016/S0720-048X(99)00016-9.
4.
BalleyguierCKinkelKFermanianJMalanSDjenGTaourelP & HelenonO. Computer-aided detection (CAD) in mammography: Does it help the junior or the senior radiologist?Euroean Journal of Radiology54, 90–96, (2005). DOI: 10.1016/j.ejrad.2004.11.021.
5.
FentonJJTaplinSHCarneyPAAbrahamLSicklesEAD'OrsiCBernsEACutterGHendrickREBarlowWE & ElmoreJG. Influence of computer-aided detection on performance of screening mammography. N Engl J Med356, 1399–1409, (2007). DOI: 10.1056/NEJMoa066099.
6.
SadafACrystalPScaraneloA & HelbichT. Performance of computer-aided detection applied to full-field digital mammography in detection of breast cancers. Eur J Radiol77, 457–461, (2009). DOI: 10.1016/j.ejrad.2009.08.024.
7.
SzekelyNTothN & PatakiB. A hybrid system for detecting masses in mammographic images. Instrumentation and Measurement. IEEE Transactions55, 944–952, (2006). DOI: 10.1109/TIM.2006.870104.
8.
GanesanKAcharyaURChuaCKLimCMAbrahamKT & NgK-H. Computer-aided breast cancer detection using mammograms: A review. Biomedical Engineering, IEEE Reviews6, 77–98, (2013). DOI: 10.1109/RBME.2012.2232289.
9.
StarckJLMouddenYAbrialP & NguyenM. Wavelets, ridgelets and curvelets on the sphere. Astronomy and Astrophysics4461191–1204 (2006). DOI: 10.1051/0004-6361:20053246.
10.
KezeleIDescoteauxMPouponCPouponF & ManginJF. Spherical wavelet transform for ODF sharpening. Med Image Anal14 (3), 332–342 (2010). DOI: 10.1016/j.media.2010.01.002; Epub 2010 Feb 1.
11.
Chih-ChinL & Cheng-ChihT. Digital image watermarking using discrete wavelet transform and singular value decomposition. IEEE Trans Instrum Meas59 (11), 3060–3063 (2010). DOI: 10.1109/TIM.2010.2066770.
12.
GanesanKAcharyaRUChuaCKLimCM & AbrahamTK. Decision support system for breast cancer detection using mammograms. Proceedings of the Institution of Mechanical Engineers, Part H: Journal of Engineering in Medicine (2013). DOI: 10.1177/0954411913480669.
13.
HuiYJieGHuaGZ & ChuanL. An efficient method to process the quantized acoustoelectric current: Wavelet transform. IEEE Trans Instrum Meas60 (3), 696–702 (2011). DOI: 10.1109/TIM.2010.2045549.
14.
DudaR & HartP. Pattern Classification and Scene Analysis. John Wiley & Sons, New York (1973).
15.
KimmeCO'LoughlinBJ & SklanskyJ. Automatic Detection of Suspicious Abnormalities in Breast Radiographs, in Data Structures. Computer Graphics, and Pattern Recognition, KlingerAFuKSKuniiTL (Eds.), New York: Academic Press, 427–447 (1977).
16.
PetrosianAChanHPHelvieMAGoodsittMM & AdlerDD. Computer-aided diagnosis in mammography: Classification of mass and normal tissue by texture analysis. Phys Med Biol39, 2273–2288, (1994). DOI: 10.1088/0031-9155/39/12/010.
17.
WeiLYangYNishikawaRM & JiangY. A study on several Machine-learning methods for classification of malignant and benign clustered microcalcifications. Medical Imaging, IEEE Transactions on24 (3), 371–380 (2005). DOI: 10.1109/TMI.2004.842457.
18.
MudigondaNRRangayyanRS & DesautelsJEL. Gradient and texture analysis for the classification of mammographic masses. Medical Imaging IEEE Transactions on19 (10), 1032–1043 (2000). DOI: 10.1109/42.887618.
19.
WeiLYangYNishikawaRM & JiangY. A study on several machine-learning methods for classification of malignant and benign clustered microcalcifications. Medical Imaging, IEEE Transactions on24 (3), 371–380 (2004). DOI: 10.1109/TMI.2004.842457.
20.
AlolfeMAMohamedWAYoussefABMMohamedAS & KadahYM. Computer aided diagnosis in digital mammography using support vector machine and linear discriminant analysis classification. Image Processing (ICIP), 2009 16th IEEE International Conference on, 2609–2612 (2009). DOI: 10.1109/ICIP.2009.5413992.
