MENU

Click here to

×

Are you sure ?

Yes, do it No, cancel

Automated Planning and Data-Driven Plan Quality Control

K Moore1*, T Purdie2*, J Lowenstein3*, (1) UC San Diego, La Jolla, CA, (2) The Princess Margaret Cancer Centre - UHN, Toronto, ON, CA, (3) UT MD Anderson Cancer Center, Houston, TX




Presentations

(Tuesday, 7/14/2020) 2:00 PM - 3:00 PM [Eastern Time (GMT-4)]

Room: Track 5

Data-driven approaches to treatment planning are powerful techniques to increase both the efficiency and quality of radiotherapy. This session will focus on the training, validation, ongoing maintenance, and quality control of data-driven quality control and automated planning systems, including the following topics:
1. General principles behind patient-specific dose prediction
2. Data requirements for knowledge-based modeling training sets and planning libraries. 3. Techniques for analyzing knowledge-based dose prediction accuracy and quantifying model error.
4. Recommendations for quality assurance of the training sets, including quality filtering prior to modeling and validation on an independent validation set.
5. Clinically implementing dose predictions for treatment plan quality control.
6. Conversion of dose predictions into optimization objectives and priorities, i.e. final automated planning routines.
7. Pre-clinical validation of automated planning routines.
8. Testing, validating, and assessing benefits/risks of externally sourced knowledge-based planning routines.
9. Recommendations for ongoing post-clinical maintenance of knowledge-based planning systems.
10. Use of data-driven quality control for multi-institutional clinical trials.

Learning Objectives:
1. Understand the current framework around clinical implementation data-driven plan quality control
2. Understand the testing and validation of data-driven automated planning
3. Understand how to safely implement automated planning systems
4. Understand the role of data-driven quality control on multi-institutional clinical trials

Funding Support, Disclosures, and Conflict of Interest: K. Moore reports income for personal consulting and speaker honoraria from Varian Medical Systems. This work was supported in part by the Agency for Healthcare Research and Quality (AHRQ R01HS025440).

Handouts

Keywords

Not Applicable / None Entered.

Taxonomy

Not Applicable / None Entered.

Contact Email