Study on Breast Tumor Detection Based on Lasso-BP Neural Network

Abstract

In recent years, breast cancer, as one of the most threatening tumors for women's health in China, affects women's health with a growth rate of 2% every year. The Lasso algorithm was used to screen the characteristics of breast cancer data, and then the BP neural network was used to classify the 9 breast cancer data determination factors in the UCI dataset and the remaining 8 determination factors after screening. The experimental results showed that: In the detection of breast cancer based on BP neural network, the remaining 8 breast cancer data features are used to classify benign and malignant tumors, and the classification accuracy rate is higher than that of the original 9 breast cancer data features.