Machine Learning based Analysis of Histopathological Images of Breast Cancer Classification using Decision Tree Classifier

Abstract

Cancer is a significant public health problem that is experienced by people all around the world. This disease has already taken the lives of a significant number of people, and it will continue to do so in the years to come. Breast cancer has already surpassed cervical cancer as the largest frequent form of cancer detected in females in both developed and developing countries, making it the second leading cause of cancer death among women worldwide. This disease claims the lives of a significant number of women each and every year. If detected at an earlier stage, breast cancer is substantially easier to treat. In this study, a decision tree-based categorization of breast cancer in histological images is presented for the first time. Both benign and malignant breast growths can eventually develop into breast cancers. Researchers use classification as a tool to assess and classify the medical data they collect. Segmentation is a key factor in the identification of breast cancer. In order to train the model, the cancer specimens that can be found in the Kaggle archive are employed. The classification used by Decision Tree has an overall accuracy of 87.28 percent. These results provide evidence to support the utilization of the suggested machine learning-based Decision Tree classifier in the pre-evaluation of patients for the purposes of triage and decision-making prior to the provision of data.