Abstract
Mammography is the most widely used tool for the early detection of breast cancer. Computer-based algorithms can be developed to improve diagnostic information in mammograms and assist the radiologist to improve diagnostic accuracy. In this paper, we propose a novel computer aided technique to classify abnormalities in mammograms using fusion of local and global features. The objective of this work is to test the effectiveness of combined use of local and global features in detecting abnormalities in mammograms. Local features used in the system are Chebyshev moments and Haralick’s gray level co-occurrence matrix based texture features. Global features used are Laws texture energy measures, Gabor based texture energy measures and fractal dimension. All types of abnormalities namely clusters of microcalcifications, circumscribed masses, spiculated masses, architectural distortions and ill-defined masses are considered. A support vector machine classifier is designed to classify the samples into abnormal and normal classes. It is observed that combined use of local and global features has improved classification accuracy from 88.75% to 93.17%.
Similar content being viewed by others
References
Datta Karabi, Choudhary Maitrayee, Guha Subhas and Biswas Jaidip 2012 Breast cancer scenario in a Regional Cancer Centre in Eastern India over eight years- still a major public health problem. Asian Pacific J. Cancer Prevent. 13: 809–813
American College of Radiology (ACR) 1998 Illustrated breast imaging reporting and data system (BI-RADS), 3rd edition. American College of Radiology, Reston, VA
Eberl Margaret M, Fox Chester H, Edge Stephen B, Carter Cathleen A and Mahoney Martin C 2006 BI-RADS classification for management of abnormal mammograms. J. Am. Board Fam. Med. 19(219): 161–164
Vibha S V and Rege P P 2007 Malignancy texture classification in digital mammograms based on Chebyshev moments and log polar transformation. ICGST-BIME J. 7(1): 29–35
Rashed Essam A, Ismail A Ismail and Zaki Sherif I 2007 Multiresolution mammogram analysis in multilevel decomposition. Elsevier Pattern Recognit. Lett. 28: 286–292
Tirtajaya Andy and Santika Diaz D 2010 Classification of microcalcification using dual-tree complex wavelet transform and support vector machine. In: Second International Conference on Advances in Computing, Control, and Telecommunication Technologies, IEEE computer society, 164–166
Nithya R and Santhi B 2011 Mammogram classification using maximum difference feature selection method. J. Theoret. Appl. Inform. Technol. 33(2): 197–204
Phadke A C and Rege P P 2014 Comparison of SVM & ANN Classifier for Mammogram classification using ICA features. WIT Trans. Inform. Commun. Technol. 49: 497–504
Shanthi S and Murali Bhaskaran V 2014 A novel approach for classification of abnormalities in digitized mammograms. Sadhana, Indian Acad. Sci. 39(5): 1141–1150
Ted C Wang and Nicolaos B Karayiannis 1998 Detection of microcalcifications in digital mammograms using wavelets. IEEE Trans. Med. Imaging 17(4): 498–509
Karahaliou A, Skiadopoulos S, Boniatis I, Sakellaropoulos P, Likaki E, Panayiotakis G and Costaridou L 2007 Texture analysis of tissue surrounding microcalcifications on mammograms for breast cancer diagnosis. Br. J. Radiol. 80: 648–656
Alarcon-Aquino V, Starostenko O, Ramirez-Cortes J M, Rosas-Romero R, Rodriguez-Asomoza J, Paz-Luna O J and Vazquez-Muñoz K 2009 Detection of microcalcifications in digital mammograms using the dual-tree complex wavelet transform. Eng. Int. Syst., CRL Publishing Ltd, 49–63
Balakumaran T, Vennila L and Shankar Gowri 2010 Detection of microcalcification in mammograms using wavelet transform and fuzzy shell clustering. Int. J. Comput. Sci. Inform. Security 7(1): 657–660
Leena Jasmine J S, Govardhan A and Baskaran S 2010 Classification of microcalcification in mammograms using nonsubsampled contourlet transform and neural network. Eur. J. Sci. Res. 46(4): 531–539
Paradkar Sarvesh and Pande S S 2011 Intelligent detection of microcalcification from digitized mammograms. Sadhana, Indian Acad. Sci. 36(1): 125–139
Oliver Arnau, Torrent Albert, Xavier Llado, Meritxell Tortajada, Lidia Tortajada, Melcior Sentis, Jordi Freixenet and Reyer Zwiggelaar 2012 Automatic microcalcification and cluster detection for digital and digitized mammograms. Elsevier Knowl. Based Syst. 28: 68–75
Sampat Mehul P and Bovik Alan C 2003 Detection of spiculated lesions in mammograms. In: Proceedings of the 25 Annual International Conference of the IEEE EMBS Cancun, Mexico 17–21 September 2003, 810–813
Biswas Sujay and Mukherjee Dipti 2011 Recognizing architectural distortion in mammogram: A multiscale texture modeling approach with GMM. IEEE Trans. Biomed. Eng. 58(7): 2023–2030
Banik Shantanu, Rangayyan Rangaraj M and Leo J E 2011 Detection of architectural distortion in prior mammograms. IEEE Trans. Med. Imaging 30(2): 279–294
Phadke A C and Rege P P 2013 Classification of architectural distortion from other abnormalities in mammograms. Int. J. Appl. Innov. Eng. Manag. 2(2): 42–48
Rangayyan R M and Nguyen T M 2007 Fractal analysis of contours of breast masses in mammograms. J. Digit. Imaging 20(3): 223–237
Apffel Louis, Palma Giovanni, Muller Serge and Isabelle Bloch 2010 Fuzzy segmentation of masses in digital breast tomosynthesis images based on dynamic programming. IMAGAPP 2010 – International Conference on Imaging Theory and Applications, 7–13
Arianna Mencattini, Giulia Rabottino, Marcello Salmeri, Roberto Lojacono and Emanuele Colini 2011 Automatic breast masses boundary extraction in digital mammography using spatial fuzzy c-means clustering and active contour models. IEEE Conference on Medical Imaging, November 8, 2011, 978-1-4244-9338
Suckling J, Astley S, Betal D, Cerneaz N, Dance D R and Kok S L 1994 The mammographic image analysis society digital mammogram database. International Congress Series 1069. Excerpta Medica 375–378. Available at http://peipa.essex.ac.uk/info/mias.html
Khuzi Mohd, Besar R, Zaki W M D Wan and Ahmad N N 2009 Identification of masses in digital mammogram using gray level co-occurrence matrices. Biomed. Imaging Intervention J. 5(3): e17
Vibha S V and Rege P P 2009 Geometric transform invariant texture analysis with modified Chebyshev moments based algorithm. Int. J. Image Graphics, World Scientific Publishing Company 9(4): 1–16
Acknowledgements
This work was funded by Board of College and University Development, University of Pune. Authors are grateful to Board of College and University Development for funding the project. The authors are also thankful to oncologists Dr. Shekhar Kulkarni and Dr. Aparna Atre for their valuable inputs. Authors would like to thank the reviewers for giving guidelines for improvement in the quality of the manuscript.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Phadke, A.C., Rege, P.P. Fusion of local and global features for classification of abnormality in mammograms. Sādhanā 41, 385–395 (2016). https://doi.org/10.1007/s12046-016-0482-y
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s12046-016-0482-y