Breast Cancer Risk Diagnosis based on Random Forest Classification
Li Li, Yuting Sun, Lei Xiao
Available Online November 2016.
- https://doi.org/10.2991/rac-16.2016.72How to use a DOI?
- Random Forest Classification; Breast Cancer; OOB Estimation
- In view of the good generalization performance of the random forest classifier, this paper uses the random forest classifier to analyze the risk of the 961 groups of breast tumor lesion tissue digital mammography image data. Empirical results show that the random forest classifier has better generalization performance than Decision Tree, Support Vector Machine and Recent Neighbor Method, and breast tumor severity of influential variable importance is as follows: Margin, Shape, Age and Density.
- Open Access
- This is an open access article distributed under the CC BY-NC license.
Cite this article
TY - CONF AU - Li Li AU - Yuting Sun AU - Lei Xiao PY - 2016/11 DA - 2016/11 TI - Breast Cancer Risk Diagnosis based on Random Forest Classification BT - 7th Annual Meeting of Risk Analysis Council of China Association for Disaster Prevention (RAC-2016) PB - Atlantis Press SP - 446 EP - 452 SN - 1951-6851 UR - https://doi.org/10.2991/rac-16.2016.72 DO - https://doi.org/10.2991/rac-16.2016.72 ID - Li2016/11 ER -