Classification of Individual and Clustered Microcalcifications in Digital Mammograms Using Evolutionary Neural Networks
Breast cancer is one of the main causes of death in women and early diagnosis is an important means to reduce the mortality rate. The presence of microcalcification clusters are primary indicators of early stages of malignant types of breast cancer and its detection is important to prevent the disease. This paper proposes a procedure for the classification of microcalcification clusters in mammograms using sequential difference of gaussian filters (DoG) and three evolutionary artificial neural networks (EANNs) compared against a feedforward artificial neural network (ANN) trained with backpropagation. We found that the use of genetic algorithms (GAs) for finding the optimal weight set for an ANN, finding an adequate initial weight set before starting a backpropagation training algorithm and designing its architecture and tuning its parameters, results mainly in improvements in overall accuracy, sensitivity and specificity of an ANN, compared with other networks trained with simple backpropagation.
KeywordsHide Layer Digital Mammogram Feature Selection Process Evolutionary Neural Network Microcalcification Cluster
Unable to display preview. Download preview PDF.
- 1.Thurfjell, E.L., Lernevall, K.A., Taube, A.A.S.: Benefit of independent double reading in a population-based mammography screening program. Radiology 191, 241–244 (1994)Google Scholar
- 3.Balakrishnan, K., Honavar, V.: Evolutionary design of neural architectures. A preliminary taxonomy and guide to literature. Technical Report CS TR 95-01, Department of Computer Sciences, Iowa State University (1995)Google Scholar
- 4.Suckling, J., Parker, J., Dance, D., Astley, S., Hutt, I., Boggis, C., Ricketts, I., Stamatakis, E., Cerneaz, N., Kok, S., Taylor, P., Betal, D., Savage, J.: The Mammographic Images Analysis Society digital mammogram database. Exerpta Medica International Congress Series 1069, 375–378 (1994), http://www.wiau.man.ac.uk/services/MIAS/MIASweb.html Google Scholar
- 5.Gulsrud, T.O.: Analysis of mammographic microcalcifications using a computationally efficient filter bank. Technical Report, Department of Electrical and Computer Engineering, Stavanger University College (2001)Google Scholar
- 6.Hong, B.-W., Brady, M.: Segmentation of mammograms in topographic approach. In: IEE International Conference on Visual Information Engineering, Guildford, UK (2003)Google Scholar
- 8.Hu, M.-K.: Visual pattern recognition by moment invariants. IRE Trans. Information Theory IT-8, 179–187 (1962)Google Scholar
- 9.Kozlov, A., Koller, D.: Nonuniform dynamic discretization in hybrid networks. In: Proceedings of the 13th Annual Conference of Uncertainty in AI (UAI), Providence, Rhode Island, USA, pp. 314–325 (2003)Google Scholar
- 11.Cantú-Paz, E., Kamath, C.: Evolving neural networks for the classification of galaxies. In: Proceedings of the Genetic and Evolutionary Computation Conference, GECCO 2002, San Francisco, CA, USA, pp. 1019–1026 (2002)Google Scholar