Mammogram Images Classification Using Linear Discriminant Analysis Technique and K-Nearest Neighbor Technique: A Comparative Study
DOI:
https://doi.org/10.54388/jkues.v4i2.299Keywords:
Breast cancer, image processing, data mining, classification, linear discriminant analysis, Machine Learning, K-Nearest Neighbor, Linear Discriminant Analysis techniqueAbstract
Cancer is an ordinary disease of today’s world, as one in three people is diagnosed with it at some stage in their lives. Of all the diseases categorized under cancer, the best chance at early diagnosis and detection is given to breast cancer. It has been noted that early detection increases the likelihood of a successful treatment Classification of mammographic images is critical to early diagnosis of the disease. Two classifiers were used in this study; LDA and KNN and the six statistical features were extracted from the MIAS dataset. When using 85% for training and 15% for testing our method got an accuracy of 81% with LDA classifier. But the KNN classifier was able to classify the test data with the same ratio of the training to the testing data to a 76% accuracy.
References
Hejmadi, M. (2010). Introduction to cancer biology. Momna Hejmadi & Ventus Publishing ApS.
Eaton, L. (2003). World cancer rates set to double by 2020.BMJ?: British Medical Journal, 326(7392), 728.
https://doi.org/10.1136/bmj.326.7392.728/a.
Sharma, G. N., Dave, R., Sanadya, J., Sharma, P., & Sharma,K. K. (2010). Various Types and Management of Breast Cancer: An Overview.Journal of Advanced PharmaceuticalTechnology &Research, 1(2), 109-126.
Laronga, C., Chagpar, A. B., & Vora, S. R. (2016). Patient education: breast cancer guide to diagnosis and treatment (beyond the basics). UpToDate. Waltham. https://www.uptodate.com/contents/breast-cancer-guide-todiagnosis-and-treatment-beyond-the-basics. Accessed, 7-1-2017.
Scharl, A., Kühn, T., Papathemelis, T., & Salterberg, A.(2015). The Right Treatment for the Right Patient –Personalised Treatment of Breast Cancer. Geburtshilfe Und Frauenheilkunde, 75(7), 683-691. https://doi.org/10.1055/s-0035-1546270
Fuller, M. S., Lee, C. I., & Elmore, J. G. (2015). Breast Cancer Screening: An Evidence-Based Update. The Medical Clinics of North America, 99(3), 451-468. https://doi.org/10.1016/j.mcna.2015.01.002
Nilavalan, R., Craddock, I., Preece, A., Leendertz, J., & Benjamin, R. (2007). Wideband microstrip patch antenna design for breast cancer tumour detection. IET Microwaves, Antennas & Propagation, 1(2), 277. https://doi.org/10.1049/iet-map:20050189
Gefen, S., Tretiak, O., Piccoli, C., Donohue, K., Petropulu, A., Shankar, P., et al. (2003). ROC analysis of ultrasound tissue characterization classifiers for breast cancer diagnosis. IEEE Transactions on Medical Imaging, 22(2), 170-177. https://doi.org/10.1109/tmi.2002.808361
Hassan, A. M. & El-Shenawee, M. (2011). Review of electromagnetic techniques for breast cancer detection. IEEE Reviews in Biomedical Engineering, 4, 103-118. https://doi.org/10.1109/RBME.2011.2169780
Cheng, Y. & Fu, M. (2018). Dielectric Properties for Differentiating Normal and Malignant Thyroid Tissues. Medical Science Monitor?: International Medical Journal of Experimental and Clinical Research, 24, 1276-1281. https://doi.org/10.12659/MSM.908204
S. Balakrishnama, A. Ganapathiraju ''LINEAR DISCRIMINAN ANALYSIS –A BRIEF TUTORIAL'' Department of Electrical and Computer Engineering Mississippi State University'' ,year,isnb
S. Sharma, J. Agrawal, and S. Sharma, "Classification through machine learning technique: C4. 5 algorithm based on various entropies,"International.
A. Kharrat, K. Gasmi, M. B. Messaoud, N. Benamrane, and M. Abid, "A hybrid approach for automatic classification of brain MRI using genetic algorithm and support vector machine," Leonardo Journal of Sciences, vol. 17, pp. 71-82, 2010.
Suckling, J., Parker, J., Dance, D., Astley, S., Hutt, I., Boggis, C., Ricketts, I., et al. (2015). Mammographic Image Analysis Society (MIAS)
database v1.21 . [Dataset].https://www.repository.cam.ac.uk/handle/1810/250394 .
