Identification and Classification of Breast Cancer using Multilayer Perceptron Techniques for Histopathological Image
G. Sajiv, G. Ramkumar
Abstract
Among the many types of cancer that affect women, breast cancer (BC) is one of the most well-known. By analyzing and predicting BC, the condition can be effectively treated by preventing future medical issues. Machine learning (ML) is often regarded as the suitable approach for BC detection due to its effectiveness in analyzing complex BC datasets. Researchers rely on classification to make sense of the vast amounts of medical data they collect in their quest to identify breast cancer. To make the distinction between benign and malignant breast cancers without resorting to invasive surgery, a precise and consistent diagnostic approach is required for early detection. The model is trained using cancer data obtained from the Kaggle database. Multilayer Perceptron is able to classify data with an accuracy of 85%. Our anticipated algorithm’s primary function is illness categorization and diagnosis. When used in conjunction with other cancer detection methods, MLP improves the likelihood of a cancer diagnosis being made in time for the patient to receive treatment when it is most effective.