A Genuine GLCM-based Feature Extraction for Breast Tissue Classification on Mammograms

Yıl 2016, , 124 - 129, 25.12.2016

Semih Ergin , İdil Işıklı Esener , Tolga Yüksel

https://doi.org/10.18201/ijisae.269453

Cited By: 4

Öz

A breast tissue type detection system is designed, and verified on a
publicly available mammogram dataset constructed by the Mammographic Image
Analysis Society (MIAS) in this paper. This database consists of three
fundamental breast tissue types that are fatty, fatty-glandular, and
dense-glandular. At the pre-processing stage of the designed detection system,
median filtering and morphological operations are applied for noise reduction
and artifact suppression, respectively; then a pectoral muscle removal
operation follows by using a region growing algorithm. Then, 88-dimensional
texture features are computed from the GLCMs (Gray-Level Co-Occurrence
Matrices) of mammogram images. Besides, a formerly introduced 108-dimensional
feature ensemble is also computed and cascaded with the 88-dimensional texture
features. Finally, a classification process is realized using Fisher’s Linear
Discriminant Analysis (FLDA) classifier in four different classification cases:
one-stage classification, first fatty – then others, first fatty-glandular –
then others, and first dense-glandular – then others. A maximum of 72.93%
classification accuracy is achieved using only texture features whereas it is
increased to 82.48% when cascade features are utilized. This consequence
clearly exposes that the cascade features are more representative than texture
features. The maximum classification accuracy is attained when “first fatty-glandular
– then others” classification case is implemented, that is consistent with the
fact that fatty-glandular tissue type is easily confused with fatty and
dense-glandular tissue types.

Anahtar Kelimeler

Breast tissue, Digital mammography, Feature extraction, Computer-aided detection

Kaynakça

• [1] A. Jemal, F. Bray, M. M. Center, J. Ferlay, E. Ward and D. Forman (2011). Global cancer statistics. CA: A Cancer Journal for Clinicians. Vol. 61. No.2. Pages. 69-90.
• [2] L. M. Mina and N. A. M. Isa (2014). Preprocessing technique for mammographic images. International Journal of Computer Science and Information Technology Research. Vol. 2. Pages. 226-231.
• [3] M. Saha, M. K. Naskar and B. N. Chatterji (2015). Mammogram denoising by curvelet transform based on the information of neighbouring coefficients. Third IEEE International Conference on Computer, Communication, Control and Information Technology (C3IT), Hooghly, Inda. Pages. 1-6.
• [4] H. C. Rodigues de Oliveira, L. Rodrigues Borges, P. Ferreira Nunes, P. R. Bakic, A. D. A. Maidment and M. A. C. Vieira (2015). Use of wavelet multiresolution analysis to reduce radiation dose in digital mammography. 28th IEEE International Symposium on Computer-Based Medical Systems (CBMS), São Carlos and Ribeirão Preto, Brazil. Pages. 33-37.
• [5] C. Oral and H. Sezgin (2013). Effects of dimension reduction in mammograms classification. Eighth International Conference on Electrical and Electronics Engineering (ELECO), Bursa, Turkey. Pages. 630-633.
• [6] U. Bick, M.L. Giger, R. A. Schmidt, R. M. Nishikawa, D. E. Wolvertan and K. Doi (1995). Automated segmentation of digitized mammograms. Academic Radiology, Vol. 2. No. 2. Pages. 1-9.
• [7] A. J. Mendez, P. J. Tahaces, M. J. Lado, M. Souto, J. L. Correa and J. J. Vidal (1996). Automatic detection of breast border and nipple in digital mammograms. Computer Methods and Programs in Biomedicine. Vol. 49. Pages. 253-262.
• [8] M. A. Wirth and A. Stapinski (2003). Segmentation of the breast region in mammograms using active contours. Viusal Communications and Image Processing (VCIP), Lugano, Switzerland. Pages. 1995-2006.
• [9] K. Ganesan, U. R. Acharya, K. C. Chua, L. C. Min and K. T. Abraham (2013). Pectoral muscle segmentation: A review. Computer Methods and Programs in Biomedicine. Vol. 110. Pages. 48-57.
• [10] M. Saltanat, M. A. Hossain and M. S. Alam (2010). An efficient pixel value based mapping scheme to delineate pectoral muscle from mammograms. Fifth IEEE International Conference on Bio-Inspired Computing: Theories and Applications (BIC-TA), Changsha, China. Pages. 1510-1517.
• [11] D. Y. Roshann and K. Harada (2007). A connected component labelling algorithm for grayscale images and application of the algorithm on mammograms. The 22nd Annual ACM Symposium on Applied Computing (SAC), Seoul, Korea. Pages. 146-152.
• [12] J. Nagi, S. A. Kareem, F. Nagi and S. K. Ahmed (2010). Automated breast profile segmentation for ROI detection using digital mammograms. IEEE EMBS Conference on Biomedical Engineering & Sciences (IECBES), Kuala Lumpur, Malaysia. Pages. 87-92.
• [13] L. Liu, J. Wang, and K. He, “Breast density classification using histogram moments of multiple resolution histograms”, In: 3rd International Conference on Biomedical Engineering and Informatics, pp. 146-149, 2010.
• [14] C. C. Liu, C. Y. Tsai, J. Liu, C. Y. Yu, and S. S. Yu, “A pectoral muscle segmentation algorithm for digital mammograms using Otsu thresholding and multiple regression analysis”, Computers & Mathematics with Applications, vol. 64, no. 5, pp. 1100-1107, 2012.
• [15] K. Thangavel and M. Karnan, “Computer aided diagnosis in digital mammograms: Detection of microcalcifications by meta heuristic algorithms”, International Journal on Artificial Intelligence and Machine Learning, vol. 5, pp. 29-40, 2005.
• [16] R. David, O. Arnau, M. Joan, P. Marta and E. Joan (2005). Breast segmentation with pectoral muscle suppression on digital mammograms. Lecture Notes in Computer Science. Pages. 153-158.
• [17] T. S. Subashini, V. Ramalingam and S. Palanivel (2010). Pectoral muscle remocal and detection of masses in digital mammogram using CCL. International Journal of Computer Applications. Vol.1. No. 6. Pages. 71-76.
• [18] J. Chakraborty and S. Mukhopadhyay (2012). Automatic detection of pectoral muscle using average gradient and shape based feature. Journal of Digital Imaging. Vol. 25. Pages. 387-399.
• [19] K. S. Camilus, V. K. Govindan and P. S. Sathidevi (2011). Pectoral muscle identification in mammograms”, Journal of Applied Clinical Medical Physics. Vol. 12. No. 3. Pages. 215-230.
• [20] G. Liasis, C. Pattichis and S. Petroudi (2012). Combination of different texture features for mammographic breast density classification. 12th IEEE International Conference on Bioinformatics & Engineering (BIBE), Nicosia, Cyprus, Pages. 732-737.
• [21] S. Kutluk and B. Günsel (2013). Tissue density classification in mammographic images using local features. 21st Signal Processing and Communications Applications Conference (SIU), Haspolat-Nikosia, North Cyprus. Pages. 1-4.
• [22] J. Wang, Y. Li, Y. Zhang, H. Xie and C. Wang (2011). Bag-of-features based classification of breast parenchymal tissue in the mammogram via jointly selecting and weighting visual words. 6th IEEE International Conference on Image and Graphics (ICGIP), Tokyo, Japan. Pages: 622-627.
• [23] A. Bosch, X. Munoz, A. Oliver and J. Marti (2006). Modeling and classifying breast tissue density in mammograms. IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, Nevada. Pages. 1552-1558.
• [24] Z. Chen, E. Denton and R. Zwiggelaar (2011). Local feature based mammographic tissue pattern modelling and breast density classification. 4th IEEE International Conference on Biomedical Engineering and Informatics (BMEI), Shanghai, China, Pages. 351-355.
• [25] K. Vaidehi and T.S. Subashini (2015). Automatic classification and retrieval of mammographic tissue density using texture features. 9th IEEE International Conference on Intelligent Systems and Control (ISCO), Coimbatore, India, Pages. 1-6.
• [26] M. Mustra, M. Grgic and K. Delac (2010). Feature selection for automatic breast density classification. 52nd IEEE International Symposium ELMAR (ELMAR), Zadar, Crotia. Pages. 9-16.
• [27] I. Diamant, H. Greenspan and J. Goldberger (2012). Breast tissue classification in mammograms using visual words. 27th IEEE Convention of Electrical & Electrronics Engineers in Israel (IEEEI), Eilat, Israel. Pages. 1-4.
• [28] L. Liu, J. Wang and K. He (2010). Breast density classification using histogram moments of multiple resolution mammograms. Third IEEE International Conference on Biomedical Engineering and Informatics (BMEI), Yantai, China. Pages. 146-149.
• [29] Q. Liu, L. Liu, Y. Jan, J. Wang, X. Ma and H. Ni (2011). Mammogram density estimation using sub-region classification. Fourth IEEE International Conference on Biomedical Engineering and Informatics (BMEI), Shanghai, China. Pages. 356-359.
• [30] C. Neal, Jr. Gallagher and G.L. Wise (1981). A theoretical analysis of the properties of median filters: IEEE Transactions on Acoustics, Speech, and Signal Processing. Vol. ASSP-29. No. 6. Pages. 1136-1141.
• [31] R. C. Gonzalez and R. E. Woods (2007). Digital Image Processing. 3. Ed.
• [32] A. Eleyan and H. Demirel (2011). Co-occurrence matrix and its statistical features as a new approach for face recognition. Turkish Journal of Electrical Engineering & Computer Sciences. Vol. 19. No. 1. Pages. 97-107.
• [33] A. Çalışkan and B. Ergen (2014). Palmprint Recognition System based on Gray Level Co-Occurrence Matrix. 22nd Signal Processing and Communications Applications Conference (SIU), Trabzon, Turkey. Pages. 826-829.
• [34] R. M. Haralick, K. Shanmugam and I. Dinstein (1973). Textural features of image classification. IEEE Transactions on Systems, Man and Cybernetics. Vol. SMC-3, No. 6.
• [35] L. Soh and C. Tsatsaulis (1999). Texture analysis of SAR sea ice imagery using gray level co-occurrence matrices. IEEE Transactions on Geoscience and Remote Sensing. Vol. 37. No. 2.
• [36] D. A. Clausi (2002). An analysis of co-occurrence texture statistics as a function of grey level quantization. Can. J. Remote Sensing. Vol. 28. No. 1. Pages. 45-62.
• [37] J Suckling et al. (1994). The Mammographic Image Analysis Society Digital Mammogram Database. Exerpta Medica. International Congress Series 1069. Pages. 375-378.
• [38] I. I. Esener, S. Ergin and T. Yüksel (2015). A new ensemble of features for breast cancer diagnosis. 38th IEEE International Convention on Information and Communication Technology, Electronics and Microelectronics (MIPRO), Opatija, Crotia. Pages. 1168-1173.