An Enhancement of Breast Cancer Abnormalities Detection Using Deep CNN

Breast cancer is the leading cause of cancer-related mortality among women worldwide. Early detection and accurate classification of breast cancer abnormalities are crucial for enhancing patient outcomes and guiding effective treatment strategies. In recent years, deep learning techniques, especially Deep Convolutional Neural Networks (CNNs), have shown great promise for automated image classification tasks, including the classification of breast cancer abnormalities. In this research, we propose a model based on DenseNet201 for the image classification of breast cancer. The BreaKHis dataset, comprising 7,909 microscopic histopathological images categorized as benign or malignant, is utilized to train and evaluate the model. We evaluate and compare the performance of two optimizers, Stochastic Gradient Descent (SGD) and Adaptive Moment Estimation (ADAM), with an emphasis on accuracy metrics. The objective is to enhance breast cancer diagnosis and treatment by developing a model capable of accurately classifying tumor tissues. The findings of this study have the potential to significantly influence patient care and breast cancer detection methodologies.