Knowledge?based radiation treatment planning: A data?driven method survey

This paper surveys the data-driven dose prediction methods investigated for knowledge-based planning (KBP) in last decade. These were classified into two major categories—traditional KBP and deep-learning (DL) methods—according to their techniques of utilizing previous knowledge. Traditional include studies that require geometric or anatomical features either find best-matched case(s) from a repository prior treatment plans build models. DL train neural networks make predictions. A comprehensive review each category is presented, highlighting key features, methods, advancements over years. We separated cited works according framework cancer site category. Finally, we briefly discuss performance both traditional then future trends prediction.