Probabilistic Neural Network for Breast Biopsy Classification
Ali Hussein Al-Timemy, Fawzi M. Al-Naima, Nebras H. Qaeeb · 2009
This paper presents the classification of benign and malignant breast tumor based on fine needle aspiration cytology (FNAC) and probabilistic neural network (PNN). Five hundred and sixty nine sets of cell nuclei characteristics obtained by applying image analysis techniques to microscopic slides of FNAC samples of breast biopsy have been used in this study. These data were obtained from the University of Wisconsin Hospitals, Madison. The dataset consist of thirty features which represent the input layer to the PNN. The PNN will classify the input features into benign and malignant. The sensitivity, specificity and accuracy were found to be equal 97.5%, 92.5% and 96.2% respectively. It can be concluded that PNN gives fast and accurate classification and it works as promising tool for classification of breast cell nuclei.