Classification of Breast Cancer and its Diagnosis Using Machine Learning

Breast cancer is the one of the most prevalent and deadly type of rare cancer among the women of all ages. Improving patient outcomes requires accurate diagnosis and timely detection. To enable the precise detection of breast cancer, several categorization approaches have been developed over time. This study offers an extensive examination of contemporary breast cancer classification techniques, including deep learning, machine learning, and image processing methodologies. The document delineates the merits and drawbacks of each method and provides avenues for subsequent investigation. Traditional/Conventional machine learning methods, like Support Vector Machines (SVM), Decision Trees, and Random Forests, are juxtaposed with contemporary deep learning models, such as Convolutional Neural Networks (CNNs), emphasizing their distinct advantages and drawbacks. The discussion encompasses the significance of feature selection, data preparation, and imaging methods. The paper closes by highlighting existing obstacles, including data imbalance and model interpretability, and proposes future research avenues to improve diagnostic accuracy and dependability.