ABSTRACT
It is common for women to develop breast cancer. Early detection is essential for an effective course of treatment. Breast cells are the source of this cancer, which eventually results in death if not detected promptly. Thanks to machine learning techniques that identify cancerous cells, the detection and treatment process has become increasingly straightforward. One conventional technique for identifying breast cancer is mammography. As per the reports, mammography is only accurate in diagnosing 78% of cases of breast cancer. However, there are numerous instances in which a doctor's carelessness or a mammography mistake can also lead to a delayed or incorrect diagnosis, which can be fatal. When combined, MRI and CNNs can aid in the quick detection and prevention of breast cancer. However, their imaging methods demand a certain amount of processing power. As a result, this study proposes an effective learning model that can recognize cancerous cells. We used a variety of models, such as CART, KNN (K nearest neighbor), Gaussian Naïve Bayes (NB), and SVM (support vector machine), to identify breast cancer.
