Presenting a simplified assistant tool for breast cancer diagnosis in mammography to radiologists

摘要

This paper proposes a method to simplify a computational model from logistic regression for clinical use without computer. The model was built using human interpreted features including some BI-RADS standardized features for diagnosing the malignant masses. It was compared with the diagnosis using only assessment categorization from BI-RADS. The research aims at assisting radiologists to diagnose the malignancy of breast cancer in a way without using automated computer aided diagnosis system.