Deep learning versus classical neural approach to mammogram recognition

• Autorzy: Kurek J. , Świderski B. , Osowski S. , Kruk M. , Barhoumi W.

Identyfikatory

DOI

10.24425/bpas.2018.125930

• Języki publikacji: EN

Abstrakty

EN

Automatic recognition of mammographic images in breast cancer is a complex issue due to the confusing appearance of some perfectly normal tissues which look like masses. The existing computer-aided systems suffer from non-satisfactory accuracy of cancer detection. This paper addresses this problem and proposes two alternative techniques of mammogram recognition: the application of a variety of methods for definition of numerical image descriptors in combination with an efficient SVM classifier (so-called classical approach) and application of deep learning in the form of convolutional neural networks, enhanced with additional transformations of input mammographic images. The key point of the first approach is defining the proper numerical image descriptors and selecting the set which is the most class discriminative. To achieve better performance of the classifier, many image descriptors were defined by means of applying different characterization of the images: Hilbert curve representation, Kolmogorov-Smirnov statistics, the maximum subregion principle, percolation theory, fractal texture descriptors as well as application of wavelet and wavelet packets. Thanks to them, better description of the basic image properties has been obtained. In the case of deep learning, the features are automatically extracted as part of convolutional neural network learning. To get better quality of results, additional representations of mammograms, in the form of nonnegative matrix factorization and the self-similarity principle, have been proposed. The methods applied were evaluated based on a large database composed of 10,168 regions of interest in mammographic images taken from the DDSM database. Experimental results prove the advantage of deep learning over traditional approach to image recognition. Our best average accuracy in recognizing abnormal cases (malignant plus benign versus healthy) was 85.83%, with sensitivity of 82.82%, specificity of 86.59% and AUC = 0.919. These results are among the best for this massive database.

Słowa kluczowe

EN

convolutional neural networks; breast cancer diagnosis; mammogram recognition; diagnostic features

PL

splotowe sieci neuronowe; diagnostyka raka piersi; rozpoznawanie; mammografia; cechy diagnostyczne

• Wydawca: Polska Akademia Nauk, Wydział IV Nauk Technicznych
• Czasopismo: Bulletin of the Polish Academy of Sciences. Technical Sciences
• Rocznik: 2018
• Tom: Vol. 66, nr 6
• Strony: 831--840
• Opis fizyczny: Bibliogr. 33 poz., rys., wykr., tab.

Twórcy

autor

Kurek J.

• Faculty of Applied Informatics and Mathematics, Warsaw University of Life Sciences,166 Nowoursynowska St., 02-787 Warsaw, Poland

autor

Świderski B.

• Faculty of Applied Informatics and Mathematics, Warsaw University of Life Sciences,166 Nowoursynowska St., 02-787 Warsaw, Poland

autor

Osowski S.

• aculty of Electrical Engineering, Warsaw University of Technology and Faculty of Electronic Engineering, Military University of Technology, Warsaw, 75 Koszykowa St., 00-662 Warsaw, Poland

autor

Kruk M.

• Faculty of Applied Informatics and Mathematics, Warsaw University of Life Sciences,166 Nowoursynowska St., 02-787 Warsaw, Poland

autor

Barhoumi W.

• Research Team on Intelligent Systems in Imaging and Artificial Vision (SIIVA) – LimTic Laboratory, ISI, University of Tunis El Manar, Tunisia

Bibliografia

• [1] J. Ferlay, I. Soerjomataram, R. Dikshit, S. Eser, C. Mathers, M. Rebelo, and F. Bray, “Cancer incidence and mortality worldwide: sources, methods and major patterns in GLOBOCAN”. International Journal of Cancer 136(5), E359-E386 (2012).
• [2] H. Nelson, K. Tyne, A. Naik, C. Bougatsos, B. Chan, P. Nygren, and L. Humphrey L, “Screening for breast cancer: Systematic evidence review update for the U. S. preventive services task force”, Ann. Intern. Med. 151(10), 727-W242 (2009).
• [3] S. Hofvind, G. Ursin, S. Tretli, S. Sebuodegard, and B. Moller, “Breast cancer mortality in participants of the Norwegian breast cancer screening program”, Cancer 119(17), 3106‒12 (2013).
• [4] A. Jalalian, S.B. Mashohor, H.R. Mahmud, M.I. Saripan, A.R. Ramli, and B. Karasfi, “Computer-aided detection/diagnosis of breast cancer in mammography and ultrasound” Clinical Imaging 37, 420‒426 (2013).
• [5] Z. Wang, Q. Qu, and G. Yu, “Breast tumor detection in double views mammography based on extreme learning machine”, Neural Computing and Applications 27(1), 227‒240 (2016)
• [6] I. Christoyiani, A. Koutra, E. Dermata, and G. Kokkinakis, "Computer aided diagnosis of breast cancer in digital mammograms”, Computerized Medical Imaging and Graphics 26, 309‒319 (2002).
• [7] B.K. Elfarra and I.S. Abuhaiba, “New Feature Extraction Method for Mammogram Computer Aided Diagnosis”, Intern. Journal of Signal Processing, Image Processing and Pattern Recognition 6(1), 1‒81 2013.
• [8] M. Mazurowski, J. Zurada, and G. Tourassi, “Selection of examples in case-based computer-aided decision systems”, Physics in Medicine and Biology 53, 6079–6096 (2008).
• [9] M. Lobbes, M. Smidt, K. Keymeulen, R. Girometti, C. Zuiani, R. Beets-Tan, J. Wildberger, and C. Boetes, “Malignant lesions on mammography: accuracy of two different computer-aided detection systems”, Clinical Imaging 37, 283‒288 (2013).
• [10] S. Leon, L. Libby Brateman, J Honeyman-Buck, and J. Marshall, “Comparison of two commercial CAD systems for digital mammography”, Journal of Digital Imaging 22(4), 421–423 (2009) doi: 10.1007/s10278‒008‒9144-x.
• [11] S. Dhahbi, W. Barhoumi, and E. Zagrouba, “Breast cancer diagnosis in digitized mammograms using curvelet moments”, Computers in Biology and Medicine 64(1), 79‒90 (2015).
• [12] B. Swiderski, J. Kurek, S. Osowski, M. Kruk, and W. Barhoumi “Deep learning and non-negative matrix factorization in recognition of mammograms”, in Proc. SPIE 10225B, Eighth Int. Conf. Graphic and Image Processing, (2016) doi:10.1117/12.2266335.
• [13] M. Heath, K. Bowyer, D. Kopans, R. Moore, and P. Kegelmeyer, “The digital database for screening mammography”, in: Digital Mammography, Springer, Netherlands, 457‒460 (1998).
• [14] B. Swiderski, S. Osowski, J. Kurek, M. Kruk, I. Lugowska, P. Rutkowski, and W. Barhoumi, “Novel methods of image description and ensemble of classifiers in application to mammogram analysis”, Expert Systems with Applications 81, 67–78 (2017).
• [15] D. Stauffer, Introduction to percolation theory, Taylor & Francis, London, 1985.
• [16] R. Haralick and L. Shapiro, Image segmentation techniques. Computer Vision. Graphics and Image Processing 29, 100–132 (1985).
• [17] Matlab user manual, MathWorks, Inc. Natick, USA, 2017.
• [18] M. Schroeder, Fractals, Chaos, Power Laws. W.H. Freeman and Company, New York, 2006.
• [19] B. Moon, H.V. Jagadish, C. Faloutsos, and J.H. Saltz, “Analysis of the clustering properties of the Hilbert space-filling curve”, IEEE Transactions on Knowledge and Data Engineering 13(1):124–141 (2001) doi:10.1109/69.908985
• [20] A. Costa, G. Humpire-Mamani, and A. Traina, “An efficient algorithm for fractal analysis of textures”, in Proc. 25 SIBGRAPI Conference on Graphics, Patterns and Images, 39‒46 (2012).
• [21] M. Jiang, S. Zhang, H. Li, and N. Metaxas, “Computer-aided diagnosis of mammographic masses using scalable image retrieval”, IEEE Transactions on Biomedical Engineering 62(2), 783‒792 (2015).
• [22] I. Daubechies, Ten lectures on wavelets, SIAM, Philadelphia, 1992.
• [23] R.N. Khushaba, S. Kodagoa, S. Lal, and G. Dissanayake, “Driver drowsiness classification using fuzzy wavelet packet based feature extraction algorithm”, IEEE Transaction on Biomedical Engineering 58(1), 121‒131 (2011).
• [24] J. Kurek, M. Kruk, S. Osowski, P. Hoser, G. Wieczorek, A. Jegorowa, J. Górski, J. Wilkowski, K. Śmietańska, and J. Kossakowska, “Developing automatic recognition system of drill wear in standard laminated chipboard drilling process”, Bulletin of the Polish Academy of Sciences Technical Sciences, 64(3), 633‒640 (2016).
• [25] I. Goodfellow, Y. Bengio and A. Courville, Deep learning, MIT Press, Massachusetts, USA, 2016.
• [26] A. Krizhevsky, I. Sutskever, and G. Hinton, “Image net classification with deep convolutional neural networks”, Advances in Neural Information Processing Systems 25, 1‒9 (2012).
• [27] D. Lee and H. Seung, “Learning the parts of objects by non-negative matrix factorization”, Nature 401, 788‒791 (1999).
• [28] A. Cichocki, R. Zdunek, A.H. Phan, and S.I. Amari, Nonnegative matrix and tensor factorizations: applications to exploratory multi-way data analysis and blind source separation, Wiley, New York, 2009.
• [29] J.J. Fenton, S.H.Taplin, P.A. Carney, et al. “Influence of computer-aided detection on performance of screening mammography”, New England Journal of Medicine 356, 1399‒1409 (2007).
• [30] T. Kooi and G. Litjens, “Large scale deep learning for computer aided detection of mammographic lesions”, Medical Image Analysis, 35, 303‒312 (2017).
• [31] D. Yi, R.L. Sawyer, D. Cohn III, J. Dunnmon, and C. Lam, „Optimizing and visualizing deep learning for benign/malignant classification in breast tumors”, 29th Conf. NIPS 2016, arXiv preprint, arxiv.org (2017.
• [32] R.K. Samala, H.P. Chan, and L.M. Hadjiiski, „Multi-task transfer learning deep convolutional neural network: application to computer-aided diagnosis of breast cancer on mammograms”, Physics in Medicine & Biology 62, 8894‒8908 (2017). [33] P. Teare, M. Fishman, O. Benzaquen, and E. Toledano, “Malignancy Detection on Mammography Using Dual Deep Convolutional Neural Networks and Genetically Discovered False Color Input Enhancement”, Journal of Digital Imaging 30, 499-505 (2017)

Uwagi

PL

Opracowanie rekordu w ramach umowy 509/P-DUN/2018 ze środków MNiSW przeznaczonych na działalność upowszechniającą naukę (2019).