Classification of Liver Cancer Cell Based on Nano-features Using Decision Tree Algorithm

Abstract

Liver cancer is considered to be the main cause of death, and early detection and treatment can reduce the incidence. However, the diagnosis of cancer is not always accurate. In this paper, we use a decision tree machine learning algorithm to classify liver cancer cells based on their nano-features. This is done by extracting nano features to form a dataset after scanning a large number of living cell samples by AFM, including length, height, roughness, adhesion, elastic modulus. After randomly splitting the dataset, a decision tree algorithm was used to judge the nano-information features and classify the liver cancer cells. Finally, the classification performance was evaluated by parameters, such as ROC and AUC and confusion matrix.