MENU

Click here to

×

Are you sure ?

Yes, do it No, cancel

Quality Assurance for Precision Radiation Therapy

R Wiersma1*, J Moran2*, B Han3*, (1) The University of Chicago, Chicago, IL, (2) University Michigan Medical Center, Ann Arbor, MI, (3) Stanford University School of Medicine, Stanford, CA




Presentations

(Tuesday, 7/31/2018) 7:30 AM - 9:30 AM

Room: Karl Dean Ballroom A1

Through technological advances and clinical research over the past few decades, radiation therapy has been evolving from evidence�based medicine towards precision medicine. The aim of precision radiation therapy (PRT) is to select the best treatment option for each patient at the most appropriate time. Emphasizing biological outcomes, PRT substantially increases treatment complexity in both space and time using tools such as dose painting and orchestrated adaptive strategies. Therefore, quality assurance (QA) for PRT must evolve in order to address multiple decision-making steps and sophisticated human-machine interactions over the course of treatment. Due to this increasing complexity, current manual QA tests may adversely lead to suboptimal clinical outcomes as a result of human errors and technological failures, potentially leading to suboptimal clinical outcomes or even patient injuries. To avoid such incidences, it is therefore important to improve and automate current QA mechanisms in line with recent technological advances in digital LINAC, web-based data management, and artificial intelligence methods. This will allow QA procedures to be implemented in a streamlined and automated manner with improved accuracy, efficiency and comprehensiveness.

This session will cover recent advances in QA of PRT. Topics will include online QA collaborative systems, autonomous applications in QA and safety control, and QA with artificial intelligence.

Learning Objectives:
1. Understand that data standardization and online sharing and analysis methods are necessary for QA and patient safety.
2. Understand how to safely incorporate automation in the clinical care process to improve quality in clinical care.
3. Understand that artificial intelligence and machine learning methods can be useful to improve the efficiency and accuracy for machine QA, plan quality evaluations and patient-specific QA.

Handouts

Keywords

Not Applicable / None Entered.

Taxonomy

Not Applicable / None Entered.

Contact Email