Leveraging Deep Learning for Breast Cancer Detection : An Comprehensive study

Abstract Breast cancer is a significant health concern globally, emphasizing the need for accurate diagnostic tools for early detection and treatment. In this research, we propose a novel methodology leveraging deep learning techniques for classifying breast histopathology images as benign or malignant. We employ state of the art convolutional neural networks (CNNs), including VGG16, VGG19, ResNet50, ResNet101, and a custom CNN architecture, to extract discriminative features from histopathology images. One of the key contributions of this work is the incorporation of class weights into the training process, aiming to address class imbalance in the da-taset and enhance model performance. We evaluate the efficacy of our approach using various performance metrics, including accuracy, precision, recall, and F1-score, on the publicly available BreaKHis dataset.