A Proposed Convolutional Neural Network for Breast Cancer Diagnoses
Noor Kareem Kadhim, Belal Al Khateeb, Huda Wadah Ahmed
DOI: 10.15598/aeee.v21i1.4658
Abstract
Breast cancer is the second greatest cause of death in women worldwide, however, early detection may result in life prolongation or even complete recovery. Breast cancer can be classified by physicians into two types: benign tumors, and malignant tumors, all of which are fatal if not treated early. Several machine-learning algorithms have been developed to help physicians make diagnostic choices, concretely a convolutional neural network is presented in this paper. The proposed system is divided into several fundamental steps. The proposed classifier is trained to distinguish between incoming tumors using a dataset of 780 images. To evaluate the classifier's performance accuracy, precision, recall, and F1-score are used. In the testing stage, the proposed method achieved an overall classification accuracy of 93%, 93% precision, 93% recall, and 93% F1-score.