Prediction of Breast Cancer Using Machine Learning and Deep Learning Models

Breast cancer is the most common problem in women caused due to the outgrowth of cells in breast. Due to the absence of specific data and lack of technology, doctors aren’t able to develop effective treatment plans that can increase patient lifeline. To increase the accuracy of breast cancer diagnosis, it is necessary to develop techniques that minimize errors. In this paper, the proposed approach compared the performance of random forest and decision tree, bagging algorithms, RESNET50, and VGG16 models in predicting breast cancer outcomes using different datasets. All experiments were performed in a simulation environment using the Collab platform. To compare benign and malignant breast cancers, the study also employed sequential prior selection based on feature selection and transfer learning VGG16 mode feature extraction analysis. The results showed that the random forest and ensemble classification models have the accuracy of 99.10 and 99.73% accuracy comparing the two widely used breast cancer associating datasets. The main goal of this project is to predict breast cancer accurately.