Interpretation of Mammographic Using Fuzzy Logic for Early Diagnosis of Breast Cancer

Accuracy and interpretability are two important objectives in the design of Fuzzy Logic model. In many real-world applications, expert experiences usually have good interpretability, but their accuracy is not always the best. Applying expert experiences to Fuzzy Logic model can improve accuracy and preserve interpretability. In this study we propose an accessible tool that helps medical interpretation of suspect zones or tumors in mammographics. This paper describes a methodology to locate precisely different kind of lesions in breast cancer patients. The use of Fuzzy Logic model improves the diagnostic efficiency in tumor progression. After applying an image segmentation method to extract regions of interest (ROIs), the values obtained feed the system. The Fuzzy Logic model processes them to achieve Breast Imagine Reporting And Data System (BI-RADSreg). Some experimental results on breast images show the feasibility of the propose methodology.

[1]  Nacéra Benamrane,et al.  Fuzzy Neural Networks and Genetic Algorithms for Medical Images Interpretation , 2006, Geometric Modeling and Imaging--New Trends (GMAI'06).

[2]  Anselmo Cardoso de Paiva,et al.  Classification of Normal, Benign and Malignant Tissues Using Co-occurrence Matrix and Bayesian Neural Network in Mammographic Images , 2006, 2006 Ninth Brazilian Symposium on Neural Networks (SBRN'06).

[3]  José L. Verdegay.  Fuzzy sets and operations research for decision support: Key selected papers by Hans-Jürgen Zimmermann , 2003 .

[4]  Atam P. Dhawan,et al.  Analysis of mammographic microcalcifications using gray-level image structure features , 1996, IEEE Trans. Medical Imaging.

[5]  Lei Yang,et al.  A dynamic fuzzy classifier for detecting abnormalities in mammograms , 2004, First Canadian Conference on Computer and Robot Vision, 2004. Proceedings..

[6]  Bart Kosko,et al.  Neural networks and fuzzy systems , 1998 .

[7]  Bart Kosko,et al.  Neural networks and fuzzy systems: a dynamical systems approach to machine intelligence , 1991 .

[8]  David Levy,et al.  Book review: Neural Networks and Fuzzy Systems: A Dynamical Systems Approach to Machine Intelligence by Bart Kosko (Prentice Hall 1992) , 1992, CARN.

[9]  Richard H. Moore,et al.  THE DIGITAL DATABASE FOR SCREENING MAMMOGRAPHY , 2007 .

[10]  Gabriela Martins,et al.  Breast Imaging Reporting and Data System - BI-RADS®: valor preditivo positivo das categorias 3, 4 e 5. revisão sistemática da literatura , 2007 .

[11]  Adel Said Elmaghraby,et al.  Error investigation of models for improved detection of masses in screening mammography , 2005, Proceedings of the Fifth IEEE International Symposium on Signal Processing and Information Technology, 2005..

[12]  Ellyete de Oliveira Canella,et al.  BREAST IMAGING REPORTING AND DATA SYSTEM – BI-RADS ® : POSITIVE PREDICTIVE VALUE OF CATEGORIES 3 , 4 AND 5 , 2007 .

[13]  Stamatios V. Kartalopoulos,et al.  Understanding neural networks and fuzzy logic , 1995 .

[14]  Nico Karssemeijer,et al.  A Stochastic Model for Automated Detction of Calculations in Digital Mammograms , 1991, IPMI.

[15]  Matthew T. Freedman,et al.  Automatic segmentation of mammographic masses using fuzzy shadow and maximum-likelihood analysis , 2002, Proceedings IEEE International Symposium on Biomedical Imaging.

[16]  Jerry M. Mendel,et al.  Generating fuzzy rules by learning from examples , 1992, IEEE Trans. Syst. Man Cybern..

[17]  Nico Karssemeijer,et al.  Stochastic model for automated detection of calcifications in digital mammograms , 1992, Image Vis. Comput..

[18]  Jianchao Zeng,et al.  Performance assessment of mammography image segmentation algorithms , 2005, 34th Applied Imagery and Pattern Recognition Workshop (AIPR'05).