A Novel Score Fusion Approach for Breast Cancer Diagnosis

Early diagnosis of breast cancer disease is critical for patients to recover from this disease entirely as it is a common disease all over the world. In order to facilitate the diagnosis of the disease, medical doctors can benefit from computer-aided expert systems. In this paper, a score fusion method based on generalized regression neural network (GRNN) and feed forward neural network (FFNN) has been proposed so as to split breast cancer data samples into benign or malignant classes. The proposed method is tested on the Wisconsin Diagnostic Breast Cancer (WDBC) dataset. The utilities of these basic neural networks and the proposed method are examined and comparative performance results are presented. The experimental results show that the proposed method is promising for the diagnosis of breast cancer and may be used as an assisting tool in the decision-making of medical professionals