A Novel System for Early Detection of Breast Cancer using Area and Entropy Features of Malignant Tumor

Abstract

Computer aided detection and classification system has been developed to detect breast cancer at an early stage by predicting the area and texture of malignant tumours. Noise removal and image enhancement is carried out in the pre-processing stage by using adaptive median filter and contrast limited histogram equalisation techniques. Improved watershed segmentation technique with appropriate internal and external markers, have proved to be an efficient approach in detecting the region of interest. The detected tumours are classified using feedforward artificial neural network that are trained using textural features. Area and entropy features extracted from malignant tumours aids in early detection of breast cancer by categorising malignant tumours as belonging to stage I or stage II. The overall efficiency of the system, for identifying stages of malignant tumour is 92%, which has been identified to be high when compared to all existing systems. Mammogram images from Mammographic Image Analysis Society (MIAS) database was used for training the system and efficiency of the system was tested using real time hospital images.