Knowledge-Based Treatment Planning
Intensity-modulated radiation therapy (IMRT), including its variations (e.g., IMRT, volumetric arc therapy (VMAT), and tomotherapy), is a widely used and critically important technology for cancer treatment. IMRT treatments rely heavily on planning expertise due to its technical complexity and the conflicting nature of maximizing tumor control while minimizing normal organ damage. As treatment planning experience and especially the carefully designed clinical plan data being accumulated during the past two decades, a new set of technologies commonly termed knowledge-based planning (KBP) have been developed that aim to improve the quality and efficiency of IMRT planning by learning from the database of past clinical plans. In this chapter, we will first provide an overview of the concept of KBP—the problems it aims to address, the approaches that are effective, and the challenges it faces. Then we will present several KBP models, including a DVH prediction model, a whole breast radiation therapy (WBRT) fluence prediction model, and a beam angle bouquet model. These are a few samples from the vast amount of KBP literature published in the last years and represent some of the most recognized uses of KBP in clinical treatment planning practice.
