2018 AAPM Annual Meeting
Back to session list

Session Title: Automation in Radiotherapy - Fasten Your Seatbelt!
Question 1: Which of the following methods can be used to validate the accuracy of automatic contour segmentation:
Reference:Sharp et al.: Perspectives on automated image segmentation for radiotherapy, Medical Physics, Vol. 41, No. 5, May 2014
Choice A:Moment method
Choice B:Dice similarity coefficient
Choice C:Maximum distance
Choice D:All of the above
Question 2: Which of the following methods performs the best for automatic segmentation of contours for cervical cancer radiotherapy treatment:
Reference:S. Ghose et al. A review of segmentation and deformable registration methods applied to adaptive cervical cancer radiation therapy treatment planning. Artificial Intelligence in Medicine 64 (2015) 75–87
Choice A:Landmark based registration
Choice B:B-spline registration
Choice C:B-spline registration with shape priors
Choice D:Rigid registration
Question 3: Which of the following statements about optical flow based registration is correct:
Reference:Brock et al. Use of image registration and fusion algorithms and techniques in radiotherapy: Report of the AAPM Radiation Therapy Committee Task Group No. 132. Med. Phys. 44 (7), July 2017
Choice A:It only allows translation in 3 directions
Choice B:The deformation is local
Choice C:The deformation is global
Choice D:It only allows translation and rotations
Question 4: One of the most effective methods of catching high severity errors that may reach the radiotherapy treatment unit is:
Reference:Ford EC, Terezakis S, Souranis A, Harris K, Gay H, Mutic S. Quality control quantification (QCQ): a tool to measure the value of quality control checks in radiation oncology. Int J Radiat Oncol Biol Phys. 2012;84(3):e263–e269
Choice A:IMRT QA
Choice B:Timeout by the therapist
Choice C:Physics chart review
Choice D:Chart rounds
Question 5: According to the hierarchy of effectiveness, the most effective method of reducing errors involves:
Reference:ASTRO. (2012). Safety is No Accident: A Framework for Quality Radiation Oncology and Care. Fairfax: ASTRO.
Choice A:Periodic retreating of staff members on relevant policies and procedures
Choice B:Implementing checklists and time-outs
Choice C:Improvements and updates to policies and procedure documents
Choice D:Hardwiring systems for success using automation and forced functions
Question 6: In order to get a new virtual QA model trained, how many plans needed for the training?
Reference:Valdes G, Scheuermann R, Hung CY, Olszanski A, Bellerive M, Solberg TD., “A mathematical framework for Virtual IMRT QA using machine learning,” Med Phys. 2016 Jul;43(7):4323. doi:10.1118/1.4953835.
Choice A:50
Choice B:100
Choice C:200
Choice D:400
Back to session list