Computer-aided Detection of Breast Cancer on the Wisconsin Dataset: an Artificial Neural Networks Approach

The early detection of breast cancer (BC) has a significant impact on reducing the disease's mortality rate. As an effective cost- and time-saving tool, computer-aided diagnosis (CAD) systems have been developed in this research field, aiding clinicians and radiologists' decision-making process by offering highly accurate information. In this study, a shallow artificial neural network (ANN) model with one hidden layer is used to diagnose and predict BC using the Wisconsin breast cancer dataset (WBCD) and the Wisconsin diagnostic breast cancer (WDBC) dataset without employing feature optimization or selection algorithms. The datasets are divided into 80% for training and 20% for testing using five-fold cross-validation. The model's effectiveness and efficiency are evaluated based on sensitivity, specificity, precision, accuracy, and F1 score, along with the area under the receiver-operating characteristic curve (AUC). In the task of classifying benign and malignant tumours using the WBCD, the shallow ANN model showed promising performance with an average accuracy of 99.85%, specificity of 99.72%, sensitivity of 100%, precision of 99.69%, and F1 score of 99.84%. For BC detection using WDBC, it achieved an average accuracy of 99.47%, specificity of 99.53%, sensitivity of 99.59%, precision of 98.71%, and F1 score of 99.13%. The AUC of the proposed model was 99.86% and 99.56% for the WBCD and the WDBC dataset, respectively, illustrating the model's discrimination capacity. Moreover, the ANN model outperformed state-of-the-art models that integrate feature optimization and selection algorithms to classify BC tumours using WBCD and WDBC. Hence, the shallow ANN model presented here demonstrates significant potential for diagnosing BC using WBCD and WDBC without the need for feature optimization or selection algorithms.