Abstract
Breast cancer is the most prevalent cancer in women, and its mortality numbers is rising globally. The reason for the increasing death rate is the finding of breast cancer in malignant stages (last stages). One of the finest methods for detecting breast cancer is mammography. As there are no symptoms at the early stages doctors feel difficult to identify breast cancer. Doctors feel very hard to identify the early stage of breast cancer in mammography films through their naked eye. To address these issues, a methodology for automatically detecting breast cancer in its preliminary stages has been developed. A system built using artificial intelligence has been designed to detect cancer in its early stages utilizing mammography films. Due to the monochromatic character of mammography images, salt and pepper noise as well as Gaussian noise was visible. The presence of the noise gives a grainy appearance to the mammography images. The median filter is used for pre-processing, and its accuracy is evaluated. The performance of the median filter is high, hence the mammography images are filtered using the median filter. To develop an automated method of breast cancer detection the pre-processed image is segmented and classified. Fuzzy C- Means Segmentation (FCM) is used to segment mammography images. Using an Attention Based Convolutional Neural Network (ABCNN), the classification of images is performed. The weights of the affected area are increased whereas the weights of other areas are decreased in an attention-based convolutional neural network. Hence it is easier to classify the affected area in earlier stages of cancer. This ABCNN enhances the classification performance without adding too many network parameters. So the computational cost is low when compared to other methods. The accuracy, specificity, and sensitivity of the classifier are evaluated in order to determine its performance. The combination of Fuzzy C-Means Segmentation and Attention Based Convolutional Neural Network produces high classification accuracy compared to other segmentation methods.