Optimizing Breast Cancer Detection with Histopathological Images: A Machine Learning and Deep Learning Approach

The communicable disease known as cancer ranks second in the global burden of mortality. Cancer can arise in several locations of the body, and malignant cells have the ability to proliferate and metastasize to surrounding tissues. Breast cancer is a prevalent and grave disease that impacts millions globally. In Indian women, it is the most common cancer, with almost one in three women at risk of its occurrence. Timely and precise detection is essential for effective treatment and enhanced patient outcomes. Histopathological analysis of breast tissue samples remains the gold standard for breast cancer diagnosis. This work focuses on the advancement and implementation of advanced computational techniques for breast cancer screening utilizing histopathology images. This study employed various machine learning classification algorithms, including Random Forest, K-Nearest Neighbors, Support Vector Machines, Decision Trees, and Logistic Regression. The ResNet50 and VGG19 trained models were utilized for feature extraction, with ResNet50 achieving superior accuracy (95.00) compared to other deep learning models. The optimal classifier can be determined by evaluating the outcomes of the previously described classifiers against various performance metrics such as accuracy and precision.