Analysis of Machine Learning Techniques Applied to the Classification of Masses and Microcalcification Clusters in Breast Cancer Computer-Aided Detection


Breast cancer is one of the most common and deadliest types of cancer among women and early detection is of major importance to decrease mortality rates. Microcalcification clusters and masses are two major indicators of malignancy in the early stages of this disease, when mammography is typically used as the screening technology. Computer-Aided Diagnosis (CAD) systems can support the radiologists’ work, by performing a double-reading process, which provides a second opinion that the physician can take into account in the detection process. This paper presents a CAD model based on computer vision procedures for locating suspicious regions that are later analyzed by artificial neural networks, support vector machines and linear discriminant analysis, to classify them into benign or malignant, based on a set of features that are extracted from lesions to characterize their visual content. A genetic algorithm is used to find the subset of features that provide the greatest discriminant power. Our results show that the SVM presented the highest overall accuracy and specificity for classifying microcalcification clusters, while the NN outperformed the rest for mass-classification in the same parameters. Overall accuracy, sensitivity and specificity were measured.

Share and Cite:

E. Alanís-Reyes, J. Hernández-Cruz, J. Cepeda, C. Castro, H. Terashima-Marín and S. Conant-Pablos, "Analysis of Machine Learning Techniques Applied to the Classification of Masses and Microcalcification Clusters in Breast Cancer Computer-Aided Detection," Journal of Cancer Therapy, Vol. 3 No. 6, 2012, pp. 1020-1028. doi: 10.4236/jct.2012.36132.

Conflicts of Interest

The authors declare no conflicts of interest.


[1] C. Tukington and K. Krag, “Encyclopedia of Breast Cancer,” Facts on File Library of Health and Living, 2005.
[2] American Cancer Society, “The Importance of Finding Breast Cancer Early,” 2012.
[3] National Cancer Institute. Breast Cancer Screening, 2012.
[4] S. Ciatto, M. Del Turco, G. Risso, S Catarzi, R. Bonardi, V. Viterbo, P. Gnutti, B. Guglielmoni, L. Ponelli, A. Pandiscia, F. Navarra, A. Lauria, R. Palmiero and P. Indovina, “Comparison of Standard Reading and Computer Aided Detection (cad) on a National Proficiency Test of Screening Mammography,” European Journal of Radiology, Vol. 45, No. 2, 2003, pp. 135-138. doi:10.1016/S0720-048X(02)00011-6
[5] S. N. Deepa and B. A. Devi, “A Survey on Artificial Intelligence Approaches for Medical Image Classification,” Indian Journal of Science and Technology, Vol. 4, No. 11, 2011, pp. 1583-1595.
[6] M. A. Kumar and H. S. Sheshadri, “On the Classification of Imbalanced Datasets,” International Journal of Computer Applications, Vol. 44, No. 8, 2012, pp. 1-7.
[7] M. Rizzi, M. D’Aloia and B. Castagnolo, “Health Care CAD Systems for Breast Microcalcification Cluster Detection,” Journal of Medical and Biological Engineering, Vol. 32, No. 3, 2012, pp. 147-156. doi:10.5405/jmbe.980
[8] X. S. Zhang, X. B. Gao and Y. Wang, “MCs Detection with Combined Image Features and Twin Support Vector Machines,” Journal of Computers, Vol. 4, No. 3, 2009, pp. 215-221. doi:10.4304/jcp.4.3.215-221
[9] I. Zyout, I. Abdel-Qader and C. Jacobs, “Embedded Feature Selection Using Pso-Knn: Shape-Based Diagnosis of Microcalcification Clusters in Mammography,” JUSPN, Vol. 3, No. 1, 2011, pp. 7-11. doi:10.5383/JUSPN.03.01.002
[10] H. D. Cheng, X. J. Shi, R. Min, L. M. Hu, X. P. Cai and H. N. Du, “Approaches for Automated Detection and Classification of Masses in Mammograms,” Pattern Recognition, Vol. 39, No. 4, 2006, pp. 646-668. doi:10.1016/j.patcog.2005.07.006
[11] A. R. Dominguez and A. F Nandi, “Enhanced Multi-Level Thresholding Segmentation and Rank Based Region Selection for Detection of Masses in Mammograms,” IEEE International Conference on Acoustics, Speech and Signal Processing, Vol. 1, 2007, pp. 449-452.
[12] S. Singh and K. Bovis, “A Weighted Gaussian Mixture Model with Markov Random Fields and Adaptive Expert Combination Strategy for Segmenting Masses in Mammograms,” Chapter 8, SPIE Press, Bellingham, 2006, pp. 263-289.
[13] S. Timp and N. Karssemeijer, “Interval Change Analysis to Improve Computer Aided Detection in Mammography,” Medical Image Analysis, Vol. 10, No. 1, 2006, pp. 82-95. doi:10.1016/
[14] B. Verma and J. Zakos, “A Computer-Aided Diagnosis System for Digital Mammograms Based on Fuzzy-Neural and Feature Extraction Techniques,” IEEE Transactions on Information Technology in Biomedicine, Vol. 5, No. 1, 2001, pp. 46-54. doi:10.1109/4233.908389
[15] S. E. Conant-Pablos, R. R. Hernández-Cisneros and H. Terashima-Marin, “Feature Selection for the Classification of Digital Mammograms using Genetic Algorithms, Sequential Search and Class Separability,” In: S. Smith and S. Cagnoni, Eds., Genetic and Evolutionary Computation: Medical Applications, Wiley, New York, 2010. doi:10.1002/9780470973134.ch5
[16] E. Cantú-Paz, “Feature Subset Selections, Class Separability and Genetic Algorithms,” Proceedings of the Genetic and Evolutionary Computation Conference, Springer-Verlag, Berlin, 2004, pp. 957-970.
[17] E. Cantú-Paz, S. Newsam and C. Kamath, “Feature Selection in Scientific Applications,” Proceedings of the 2004 ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, ACM, New York, 2004, pp. 788-793.
[18] L. Hadjiiski, B. Sahiner, H. P. Chan, N. Petrick, M. A. Helvie and M. Gurcan, “Analysis of Temporal Changes of Mammographic Features: Computer-Aided Classification of Malignant and Benign Breast Masses,” Medical Physics, Vol. 28, No. 11, 2001, pp. 2309-2317. doi:10.1118/1.1412242
[19] R. R. Hernández-Cisneros and H. Terashima-Marín, “Evolutionary Neural Networks Applied to the Classification of Microcalcification Clusters in Digital Mammograms,” Proceedings of the 2006 IEEE Congress on Evolutionary Computation, Vancouver, 16-21 July 2006, pp. 2459-2466.
[20] Y. Guo, L. S. Kang, F. J. Liu, H. S. Sun and L. L. Mei, “Evolutionary Neural Networks Applied to Land-Cover Classification in Zhaoyuan, China,” IEEE Symposium on Computational Intelligence and Data Mining, Honolulu, 1-5 April 2007, pp. 499-503. doi:10.1109/CIDM.2007.368916
[21] T. Deserno, “Biomedical Image Processing,” Springer Verlag, Berlin, 2011. doi:10.1007/978-3-642-15816-2
[22] J. Bozek, M. Mustra, K. Delac and M. Grgic, “A Survey of Image Processing Algorithms in Digital Mammography,” Recent Advances in Multimedia Signal Processing and Communications, Vol. 231, Springer, Berlin, 2009. doi:10.1007/978-3-642-02900-4_24
[23] S. Haykin, “Neural Networks: A Comprehensive Foundation,” 2nd Edition, Macmillan College Publishing Co., New York, 1999.
[24] V. Vapnik, “Statistical Learning Theory,” John Wiley & Sons, New York, 1998.
[25] T. Hastie, R. Tibshirani and A. Buja, “Flexible Discriminant Analysis by Optimal Scoring,” Journal of the American Statistical Association, Vol. 89, No. 428, 1994, pp. 1255-1270. doi:10.1080/01621459.1994.10476866
[26] T. Hastie, R. Tibshirani and J. Friedman, “The Elements of Statistical Learning. Data Mining, Inference, and Prediction,” 2nd Edition, Springer Series in Statistics, Springer, Berlin, 2008.
[27] J. Suckling, J. Parker and D. Dance, “The Mammographic Image Analysis Society Digital Mammogram Database,” Exerpta Medica, International Congress Series 1069, 1994, pp. 375-378.
[28] V. Kurkova, “Kolmogorov’s Theorem,” MIT Press, Cambridge, 1995.

Copyright © 2021 by authors and Scientific Research Publishing Inc.

Creative Commons License

This work and the related PDF file are licensed under a Creative Commons Attribution 4.0 International License.