DIAGNOSIS OF BREAST LESIONS USING THE LOCAL CHAN-VESE MODEL, HIERARCHICAL FUZZY PARTITIONING AND FUZZY DECISION TREE INDUCTION

Document Type: Research Paper

Authors

1 laboraoire SIMPA, Departement d'informatique, Faculte des mathematiques et d'informatique, Universite des sciences et de la technologie d'Oran "Mohamed BOUDIAF", USTO-MB; BP 1505 El M'naouer 31000, Oran, Algerie

2 laboratoire SIMPA, Departement d'informatique, Faculte des mathematiques et d'informatique, Universite des sciences et de la technologie d'Oran "Mohamed BOUDIAF", USTO-MB; BP 1505 El M'naouer 31000, Oran, Algerie

Abstract

Breast cancer is one of the leading causes of death among women. Mammography remains today the best technology to detect breast cancer, early and efficiently, to distinguish between benign and malignant diseases. Several techniques in image processing and analysis have been developed to address this problem. In this paper, we propose a new solution to the problem of computer aided detection and interpretation for breast cancer. In the proposed approach, a Local Chan-Vese (LCV) model is used for the mass lesion segmentation step to isolate a suspected abnormality in a mammogram. In the classification step, we propose a two-step process: firstly, we use the hierarchical fuzzy partitioning (HFP) to construct fuzzy partitions from data, instead of using the only human information, available from expert knowledge, which are not sufficiently accurate and confronted to errors or inconsistencies. Secondly,fuzzy decision tree induction are proposed to extract classification knowledge from a set of  feature-based examples. Fuzzy decision trees are first used to determine the class of the abnormality detected (well-defined mass, ill-defined mass, architectural distortion, or speculated masses), then, to identify the Severity of the abnormality, which can be benign or malignant. The proposed system is tested by using the images from Mammographic Image Analysis Society[MIAS] database. Experimental results show the efficiency of the proposed approach, resulting in an accuracy rate of 87, a sensitivity of 82.14\%, and good specificity of 91.42

Keywords


[1] S. N. Acho and W. I. D. Rae, Dependence of shape-based descriptors and mass segmentation
areas on initial contour placement using the chan-vese method on digital mammograms,
Computational and Mathematical Methods in Medicine, 2015 (2015), 1-16.
[2] American Cancer Society, Cancer facts and figures, Atlanta, Ga: American Cancer Society,
(2013), 1-60.
[3] R. Bellotti, A completely automated CAD system for mass detection in a large mammographic
database, Medical Physics, 33(8) (2006), 3066–3075.
[4] L. Breslo and D. Aha, Simplifying decision trees: a survey, The Knowledge Engineering
Review, 12(1) (1997), 1-40.
[5] L. F. A. Campos, A. C Silva and A. K. Barros, Diagnosis of breast cancer in digital mammograms
using independent component analysis and neural networks, X Iberoamerican, Conference
on Pattern Recognition, Havana, Lecture notes in computer science, 3773 (2005),
460–469.

[6] T. F. Chan and L. A. Vese, Active contours without edges, IEEE Trans. Image Process, 10(2)
(2001), 266-277.
[7] R. Crandall, Image segmentation using Chan Vese algorithm, ECE532 Project fall, 2009.
[8] A. Keles and Y. Ugur,Expert system based on neuro-fuzzy rules for diagnosis breast cancer,
Expert Syst Appl., 38(5)(2011), 5719–5726.
[9] U. Khan, H. Shin, J. P. Choi and M. Kim, Weighted fuzzy decision trees for prognosis of
breast cancer survivability, Proc of the Australasian Data Mining Conferenre, Glenelg, South
Australia, 7(3) (2008), 141-152.
[10] Z. Lei and K. Ardrew Chan, An artificial intelligent algorithm for tumor detection in screening
mammogram, IEEE Trans. on Medical Imaging, 20(7) (2009), 559-567.
[11] M. Leonardo de Oliveira, G. Braz Junior, C. S. .Aristofanes, A. Cardoso de Paiva and M.
Gattass, Detection of masses in digital mammograms using K-means and support vector
machine, Electronic Letters on Computer Vision and Image Analysis, 8(2) (2009), 39-50.
[12] A. M.Maciej. Y.J.Lo, P.B.Harrawood and D. G Tourassc, Mutual information-based template
matching scheme for detection of breast masses: From mammography to digital breast
tomosynthesis, Journal of Biomedical Informatics 44(5) (2011), 815-823.
[13] C. Marsala, Apprentissage inductif en pr´esence de donn´ees impr´ecises : construction et
utilisation d’arbres de d´ecision flous, Th`ese de doctorat, Universit´e de Paris 6, (1988).
[14] C. Marsala, Fuzzy decision trees to help flexible querying, KYBERNETICA, 36 (2006), 689–
705.
[15] L. Martins, A. Dos Santos, A. Silva and A. Paiva,Classification of normal, benign and malignant
tissues using co-occurrence matrix and bayesian neural network in mammographic
images, Proceedings of the Ninth Brazilian Symposium on Neural Networks, (2006), 479–486.
[16] A. Materka and M. Strzelecki, Texture analysis methods, A review, COST B11 Technical
Report, Lodz-Brussels: Technical University of Lodz, (1998), 9-11.
[17] G. H. B. Miranda and J. C Felipe,Computer-aided diagnosis system based on fuzzy logic for
breast cancer categorization, Computers in Biology and Medicine, 64(1) (2015), 334-34.
[18] J. I. Mohamed, M. Ahmadi and A. S. A. Maher, An efficient automatic mass classification
method in digitized mammograms using artificial neural network, International Journal of
Artificial Intelligence and Application (IJAIA), 1(3) (2010), 1-13.
[19] E. Molins, F. Macia and F. Ferrer, Association between radiologists’ experience and accuracy
in interpreting screening mammograms, BMC Health Serv Res., 8(91) (2008), 1-10.
[20] S. K. Murthy, Automatic construction of decision trees from data: a multi-disciplinary survey,
Data Min Knowl Disc, 2(4) (1998), 345-389.
[21] C. Olaru anf L. Wehenkel, A complete fuzzy decision tree technique, Fuzzy Sets and Systems,
138(2) (2003), 221-254.
[22] A. Oliver, J. Freixenet, R Mart´ı et al., A novel breast tissue density classification methodology,
IEEE Transactions on Information Technology in Biomedicine, 12(1) (2008), 55–65.
[23] S. Osher and N. Paragios, Geometric level set methods in imaging, vision and Graphics,
Springer-Verlag, 2003.
[24] G. Palma, G. Peters, S. Muller and I. Bloch, Masses classification using fuzzy active contours
and fuzzy decision tree, SPIE Symposium on Medical Imaging, San Diego, CA, USA,
6915(2008), 691509.1-691509.11.
[25] o. Pitchumani Angayarkanni and N. Banu Kamal, Association rule mining based decision tree
induction for efficient detection of cancerous masses in mammogram, International Journal
of Computer Applications, 31(6) (2011), 1-5.
[26] P. Rahmati, A. Adler and G. Hamarneh, Mammography segmentation with maximum likelihood
active contours, Medical Image Analysis, 16(6) (2012), 1167–1186.
[27] R. Ramani and N. Suthanthira Vanitha, Computer aided detection of tumours in mammograms,
international .Journal of Image, Graphics and Signal Processing, 6(4) (2014), 54-59.
[28] M. Ramdani, Syst`eme d’induction formelle `a base de connaissances impr´ecises, Th`ese de
doctorat, Paris 6, LIP6, 1994.
[29] R. S. Safavian and D. Landgrebe, A survey of decision tree classifier methodology, IEEE
Transactions on Systems, Man, and Cybernetics, 3(21) (1991), 660–674.

[30] G. Saborta, Probabilit´es, Analyse des donn´ees et Statistique, Ed. Technip, 1990.
[31] M. S. Salve and A. Chakkarwar, Classification of mammographic images using Gabor Wavelet
and discrete wavelet transform, International Journal of Advanced Research in Electronics
and Communication Engineering (IJARECE), 2(5) (2013).
[32] G. Serge and B. Charnomordic, Generating an interpretable family Of fuzzy partitions, IEEE
Transactions on Fuzzy Systems, 12(3) (2004), 324– 335.
[33] G. Serge, Induction de r`egles floues interpr´etables, Th`ese de Doctorat, INSA Toulouse,
France, 2001.
[34] S. Shanthi and M. BhaskaraR, Intuistionistic fuzzy C-means and decision tree approach for
breast cancer detection and classification, European Journal of Scientific research, 66(I3)
(2011), 345-351.
[35] J. Suckling, J. Parker, D. R. Dance et al., The mammographic image analysis society digital
mammogram database, Excerpta Medica International Congress Series, (1069) (1994), 375-
378.
[36] T. Takagi and M. Sugeno, Fuzzy identification of systems and its applications to modeling
and control, IEEE Trans. Syst. Man Cybern, 15 (1985), 116–132.
[37] H. D. Thanh, Mesures de discrimination et leurs applications en apprentissage inductif,
Th`ese de doctorat, Universit´e de Paris 6, 2007.
[38] X. F. Wang, D. S. Huang and H. Xu, An efficient local Chan–vese model for image segmentation,
Pattern Recognition, 43(3) (2010), 603-618.
[39] Y. Wu, O. Alagoz, M. U. S. Ayvaci, A. Munoz del Rio, A. D. J. Vanness, R. Woods and E. S.
Burnsise, A comprehensive methodology for determining the most informative mammographic
features, Journal of digital imaging, 26(5) (2013), 941-947.
[40] L. A. Zadeh, Fuzzy sets, Information and Control, 8(3) (1965), 338-353.