Summary
Objectives
: This paper proposes an efficient method for the discrimination and classification of mammograms with benign, malignant and normal tissues.
Methods
: The proposed method consists of selection of tissues, feature extraction using independent component analysis, feature selection by the foiward- selection technique and classification of the tissue by the multilayer perceptron.
Results
: The method is tested for a mammogram set of the MIAS database, resulting in a 97.83% success rate, with 98.0% specificity and 97.5% sensitivity.
Conclusion
: The proposed method showed a good classification rate. The method will be useful for early cancer diagnosis.
Keywords
Mammogram - breast cancer - independent component analysis - computer-aided diagnosis - multilayer perceptron neural networks
