DeepBreast: Building Optimized Framework for Prognosis of Breast Cancer Classification Based on Computational Intelligence

Breast cancer is a significant issue for women worldwide and a leading cause of death. So automated detection of tumors is required. Numerous research studies have attempted to classify breast cancer using machine learning algorithms, and numerous researchers have stated that machine learning algorithms are preferable in the Prognosis process. An optimized framework based on Seven machine-learning algorithms was used in this paper. The machine learning algorithms are optimized using Grid Search. The performance of the framework was compared to determine which classifier performs the best on the Wisconsin dataset. The results indicated a significant increase in predicted accuracy, with the highest value being 78.6% of accuracy in the Wisconsin Prognosis Breast Cancer dataset (WPBC). These results demonstrate significant improvement in the area of breast cancer detection as compared to the existing state of art results of baseline machine learning models.