A Novel CNN Approach for Accurate Breast Cancer Diagnosis

Breast cancer is a prevalent kind of cancer in women worldwide, and timely detection is crucial for effective treatment. Conventional methods for diagnosing breast cancer, such mammography and biopsy, mainly depend on human interpretation, which can be slow and prone to mistakes. Recently, deep learning methods, specifically Convolutional Neural Networks (CNNs), have demonstrated potential in enhancing the precision and effectiveness of breast cancer diagnosis. The study introduces an innovative Convolutional Neural Network (CNN) method for precise breast cancer identification based on histopathology images. 8,598 photos were gathered and split into training (6,860 images) and testing (1,738 images) datasets. The CNN structure was tailored for analyzing breast cancer images, incorporating Conv2d, Maxpooling2d, Dropout, Flatten, and Dense layers. The model underwent 25 training epochs and was assessed based on metrics including loss, accuracy, precision, recall, and F1-Score. A confusion matrix was created to evaluate the model's classification accuracy, and performance metrics were computed. The CNN model provided attained an 86% overall accuracy in diagnosing breast cancer, showcasing its efficacy in automated breast cancer diagnosis.