Program Information

Collaborative Knowledge Modeling and Integration for Radiation Therapy Planning

C Mayo

W Verbakel

Q Wu

Y Xiao

y Ge

C Mayo¹*, W Verbakel²*, Q Wu³*, Y Xiao⁴*, y Ge⁵*, (1) Mayo Clinic, Rochester, MN, (2) VU University Medical Center, Amsterdam, The Netherlands, (3) Duke University Medical Center, Durham, NC, (4) Thomas Jefferson University Hospital, Philadelphia, PA, (5) University of North Carolina at Charlotte, Charlotte, NC

TH-C-500-1 Thursday 10:30AM - 12:30PM Room: 500 Ballroom

Experience, knowledge, and guidelines about intensity modulated radiation therapy (IMRT) have been accumulated over the past decade, but they have largely not been formally extracted or modeled to support more efficient and optimal treatment planning. Therefore in routine clinic practice, IMRT/VMAT treatment planning for each individual case is still managed in a time-consuming iterative process, where planner and physician attempt to create the clinically optimal plan. Each patient presents a unique set of anatomic constraints on how much the dose can be “sculpted” to spare normal tissue, which is quantitatively unknown to the planner. Balancing the competing goals; i.e. target coverage and organs at risk (OARs) sparing, is a trial-and-error process guided largely by the planner’s and physician’s personal experience, skill, and knowledge. Further, for any given dose distribution, likely clinical outcomes (e.g. tumor control rate and normal tissue toxicity) are not readily apparent to physicians. The limited knowledge available in this area (e.g. QUANTEC guidelines, population-based data) is not integrated into treatment planning systems, and physicians are usually left to their intuition and experience. Thus, there is a strong need to explicitly organize, model and integrate the available knowledge from various sources into the planning process. In this session, we will present and discuss some of the early efforts in knowledge development, modeling, and application in treatment planning. These efforts are managed at different levels, from disease sites to institution. We will present clinical examples demonstrating how ready-access and integration of such knowledge into the planning process will improve the efficiency of IMRT/VMAT planning and the overall quality of resulting plans. We will also discuss the potentials and challenges to collaboratively extract, represent, integrate, and apply these various sources of knowledge in the radiation therapy via proper infrastructure management. Finally, we would also discuss the potential of such knowledge integration and sharing in helping small, independent clinics where physicians and physicists often provide services for a broad spectrum of disease sites, and where peer review with in depth specialty knowledge input can be limited.

Learning Objectives:
1. Extracting and organizing knowledge at different levels, by different disease site, and in institutional and multi-institutional settings
2. Infrastructure for collaborative knowledge building, modeling and sharing
3. Modeling and representation of knowledge for treatment planning, leading to cost and quality effective standardization of plan optimization


Funding Support, Disclosures, and Conflict of Interest: Q-R Jackie Wu: Research grant from Varian Medical Systems and NIH Ying Xiao: Research grants from NIH/ACR and Pennsylvania State Dept of Health Charles Mayo: Research grant from Varian Medical Systems Wilko Verbakel: The department of radiation oncology of VUmc has a research agreement with Varian Medical Systems. Verbakel and Dahele have received honorarium / travel expenses from Varian Medical Systems. Yaorong Ge: Research grant from NIH

Contact Email: