Harnessing Deep Convolutional Neural Networks for Enhanced Breast Cancer Diagnosis

Abstract

Breast cancer continues to be a major cause of cancer-related mortality among women globally, highlighting the critical need for effective detection and prognosis models. This study focuses on evaluating the performance of deep convolutional neural networks (DCNNs) in comparison to other machine learning techniques, including support vector machines (SVM) and logistic regression, for predicting breast cancer outcomes. Utilizing the Wisconsin Breast Cancer Dataset, we apply various preprocessing methods such as feature scaling, normalization, and dimensionality reduction to enhance model effectiveness. We develop and assess multiple machine learning models using key performance metrics including accuracy, precision, recall, and F1-score. Furthermore, a user-friendly website is created to incorporate the top-performing model, facilitating preliminary breast cancer diagnoses for healthcare professionals. The anticipated results include a DCNN model demonstrating accuracy above 95%, a detailed comparative analysis of the machine learning algorithms, and a dependable tool for early breast cancer detection. This research aims to advance the application of machine learning in healthcare, providing valuable insights for future medical diagnosis projects and showcasing the capabilities of mobile health applications. The outcomes of this study have the potential to improve patient care by assisting healthcare providers in making timely and accurate decisions in breast cancer diagnosis and treatment.