JBiSE  Vol.5 No.6 , June 2012
A computer aided detection framework for mammographic images using fisher linear discriminant and nearest neighbor classifier
ABSTRACT
Today, mammography is the best method for early detection of breast cancer. Radiologists failed to detect evident cancerous signs in approximately 20% of false negative mammograms. False negatives have been identified as the inability of the radiologist to detect the abnormalities due to several reasons such as poor image quality, image noise, or eye fatigue. This paper presents a framework for a computer aided detection system that integrates Principal Component Analysis (PCA), Fisher Linear Discriminant (FLD), and Nearest Neighbor Classifier (KNN) algorithms for the detection of abnormalities in mammograms. Using normal and abnormal mammograms from the MIAS database, the integrated algorithm achieved 93.06% classification accuracy. Also in this paper, we present an analysis of the integrated algorithm’s parameters and suggest selection criteria.

Cite this paper
Sarfraz, M. , Abu-Amara, F. and Abdel-Qader, I. (2012) A computer aided detection framework for mammographic images using fisher linear discriminant and nearest neighbor classifier. Journal of Biomedical Science and Engineering, 5, 323-329. doi: 10.4236/jbise.2012.56042.
References
[1]   National Cancer Institute (2011) The National Cancer Institute website. http://www.cancer.gov/cancertopics/types/breast

[2]   Senn, H.J. and Schrijvers, D. (2010) A lifestyle choice: Is cancer prevention the ultimate goal. Public Service Review, 20, 184-186.

[3]   Sonka, M. and Fitzpatrick, J.M. (2000) Handbook of medical imaging. Academic Press, Waltham. doi:/10.1117/3.831079

[4]   Ikeda, D. (2010) Breast Imaging. 2nd Edition, Elsevier Mosby, Maryland Heights.

[5]   Fiona, J.G., Susan, M.A., Maureen, G.C.G., Olonnsola, F.A., Matthew, G.W., Jonathan, J., Caroline, R.M.B. and Stephen, W.D. (2008) Single reading with computer-aided detection for screening mammography. The New England Journal of Medicine, 359, 1675-1684. doi:/10.1056/NEJMoa0803545

[6]   Abdel-Qader, I., Shen, L., Jacobs, C., Abu-Amara, F. and Pashaie-Rad, S. (2006) Unsupervised detection of suspicious tissue using data modeling and PCA. International Journal of Biomedical Imaging, 2006, Article ID: 57850.

[7]   Solka, J.L, Poston, W.L, Priebe, C.E, Rogers, G.W, Lorey, R.A, Marchette, D.J. and Woods, K. (1994) The detection of micro-calcifications in mammographic images using high dimensional features. IEEE Seventh Symposium on Computer-Based Medical Systems, Winston-Salem, 10-12 June 1994, 139-145.

[8]   Ryan, H, Lilien, H and Bruce, R. (2003) Probabilistic disease classification of expression-dependent proteomic data from mass spectrometry of human serum. Journal of Computational Biology, 10, 925-946. doi:/10.1089/106652703322756159

[9]   Sanja, F. and Leonardis, A. (2003) Robust LDA classifycation by subsampling. Computer Vision and Pattern Recognition Workshop, Madison, 16-22 June 2003, 97-97.

[10]   Beveridge, J. She, K., Bruce, A. and Geof, H. (2001) A Nonparametric statistical comparison of principal component and linear discriminant subspaces for face recognition. IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Colorado Springs, 8-14 December 2001, 535-542.

[11]   Giger, M.L., Krassemeijer, N. and Armato, S.G. (2001) Guest editorial computer-aided diagnosis in medical imaging. IEEE Transactions on Medical Imaging, 20, 1205- 1208. doi:/10.1109/TMI.2001.974915

[12]   Thomas, P., Michael, C. and Lewis, S. (2001) Comparison of the performance of different discriminant algorithms in analyze discrimination tasks using an array of carbon black-polymer composite vapor detectors. Analytical Chemistry, 73, 321-331. doi:/10.1021/ac000792f

 
 
Top