RLBP Metodu ile Mamografi Görüntülerinin İncelenmesi ve Sınıflandırılması
Göğüs kanseri dünya genelinde kadınlarda en çok karşılaşılan kanser türüdür. Günümüzde her kadının başına gelebilecek olan göğüs kanseri, erkeklerde de görülebilmektedir. Göğüs kanserinde insanların fiziksel ve zihinsel halleri çok etkilidir. Göğüs kanserine karşın tedbirli olabilmek için belirli aralıklarla göğüs dokularının incelenmesi gerekmektedir. Bu dokular, uzmanlar tarafından incelenmektedir. Ancak inceleme esnasında yapılan yanlış teşhisler tedavi sürecini olumsuz etkilemektedir. Bu sebeple, bu dokuların sayısal ortamda işlenip incelenmesi daha faydalı olmaktadır. Bu çalışmada, YSA ile göğüs kanserinin sınıflandırması yapılmıştır. Mamografi görüntüleri üzerinde Döndürülmüş Yerel İkili Örüntü (RLBP) metodu kullanılarak öznitelikler çıkarılmıştır. Bu öznitelikler, parametreleri belirlenmiş olan YSA aracılığı ile eğitilmiştir. Eğitim sonucunda iyi ve kötü huylu olarak sınıflandırılan ikili sınıflandırmada %87,82 ve Yağlı, Yağlı-Glandüler ve Yoğun-Glandüler olarak sınıflandırılan üçlü arka plan doku sınıflandırmasında %80,95 başarı oranı elde edilmiştir.
Examination and Classification of Mammography Images with the RLBP Method
Breast cancer is the most common type of cancer in women worldwide. Breast cancer, which can happen to every woman, can also be seen in men. The physical and mental state of people is very important in breast cancer. The breast tissues should be examined at intervals in order to be cautious against breast cancer. The breast tissues should be examined periodically in order to be cautious against breast cancer. These tissues are examined by experts. However, misdiagnoses made during the examination adversely affect the treatment process. For this reason, it is more beneficial to process and examine these tissues in digital environment. In this study, classification of breast cancer was made with ANN. Features were extracted using the Rotated Local Binary Pattern (RLBP) method on mammography images. These features were trained by ANN whose parameters have been determined. As a result of the training, a success rate of 87.82% was achieved in the binary classification classified as benign and malignant, and 80.95% in the triple background tissue classification classified as Fatty, Fatty-Glandüler and Dense-Glandüler.
___
- Hossfeld, DK. Manual of Clinical Oncology, 5th ed. Springer- Verlag, UICC, 1992.
- Topuz, E. Aydıner, A. Dincer, M. Meme Kanseri, Nobel Tıp Kitabevi, 2003.
- Baldi, V. Cicalese, A. Coppala, G. Scarano, M. Gatto, E. Results of Mammographic Screening, 2003.
- Humprey, LL. Helfand, M. Chang, BK. Woolf, SH. "Breast cancer screening: a summary of the evidence for the U.S Preventive Services Task Force", 2009.
- Kopans, D.B. Feig, S.A. The Canadian National Breast Cancer Screening Study,1993.
- Howlader, N. Noone, AM. Krapcho, M. et. al. (eds). SEER Cancer Statistics Review, 1975–2009 National Cancer Institute. Bethesda. 2012.
- American Cancer Society Guidelines for The Early Detection of Cancer, 2001.orientation estimation in hidden markov random fields." Biomedical Imaging: From Nano to Macro, 2011 IEEE International Symposium on. IEEE, 2011.
- D. Brzakovic and M. Neskovic, "Mammogram screening using multiresolution- based image segmentation," in State of the Art in Digital Mammographic Image Analysis,K.W. Bowyer and S. Astley, Eds, Singapore: World Scientific, 1994, pp. 103–127.
- Houssein, E. H., Emam, M. M., Ali, A. A., and Suganthan, P. N., "Deep and machine learning techniques for medical imaging-based breast cancer: A comprehensive review", Expert Systems with Applications, 114161,2020
- Society, A. C. (2019). Breast cancer facts and figures 2019-2020. Atlanta: American Cancer Society, Inc..
- L. Miller and N. Ramsey, "The detection of malignant masses by nonlinear multiscale analysis," in Proc. 3rd Int.Workshop Digital Mammography, K. Doi, M. L. Giger, R. M. Nishikawa, and R. A. Schmidt, Eds., Chicago, IL, June 9–12, 1996, pp. 335–340.
- C. M. Chang and A. Laine, "Coherence of multiscale features for enhancement of digital mammograms," IEEE Trans. Inform. Technol. Biomed., vol. 3, pp. 32–46, Mar. 1999.
- N. Petrick, H. P. Chan, B. Sahiner, and D. Wei, "An adaptive densityweighted contrast enhancement filter for mammographic breast mass detection," IEEE Trans. Med. Imag., vol. 15, pp. 59–67, Jan. 1996.
- University of Essec. Mamographic Image Analysis Society. http://peipa.essex.ac.uk/ipa/pix/mias/ Last accessed: 7th September 2010.
- Ergene, Mehmet Celalettin, Akif Durdu, and Halil Cetin. "Imitation and learning of human hand gesture tasks of the 3D printed robotic hand by using artificial neural networks."
Electronics, Computers and Artificial Intelligence (ECAI), 2016 8th International Conference on. IEEE, 2016.
- Ojala, T., Pietikinen, M., and Harwood,D., "A comparative study of texture measures with classification based on featured distrubition", Pattern Recognition, vol. 29, no. 1, 1996.
- Maaenpaaa,T., Pietikaainen M., “Texture Analysis with Local Binary Patterns”, University of Oulu, 2004.
- Marcano-Cedeño, A., Quintanilla-Domínguez, J., and Andina, D. (2011). WBCD breast cancer database classification applying artificial metaplasticity neural network. Expert Systems with Applications, 38(8), 9573–9579.
- Bhardwaj, A., and Tiwari, A. (2015). Breast cancer diagnosis using genetically optimized neural network model. Expert Systems with Applications, 42(10), 4611–4620.
- Mahersia, H., Boulehmi, H., and Hamrouni, K. (2016). Development of intelligent systems based on Bayesian regularization network and neuro-fuzzy models for mass detection in mammograms: An comparative analysis. Computer Methods and Programs in Biomedicine, 126, 46–62.
- Singh, S. P., and Urooj, S. (2016). An improved CAD system for breast cancer diagnosis based on generalized pseudo-Zernike moment and Ada-DEWNN classifier. Journal of Medical Systems, 40(4), 105.
- Xie, W., Li, Y., and Ma, Y. (2016). Breast mass classification in digital mammography based on extreme learning machine. Neurocomputing, 173, 930–941.