Search

Proffered Papers: Proffered papers 12: Artificial Intelligence and automation OC-0225: Highly-individualized dose reconstruction for pediatric abdominal radiotherapy with machine learning M. Virgolin, Z. Wang, B.V. Balgobind, I.W.E.M. Van Dijk, J. Wiersma, D.C. Hodgson, A. Bryce-Atkinson, M. Van Herk, C.R.N. Rasch, L. Zadravec Zaletel, P.S. Kroon, G.O. Janssens, A. Bel, P.A.N. Bosman, T. Alderliesten. [Extracted from the article]

For adequate radiotherapy in thoracic-abdominal tumors, organ motion needs to be considered in treatment planning. Although margin definitions for children have been reported, comprehensive analyses on applicable margins for treatment planning remain scarce. We aimed to quantify interfractional organ motion in a large multicenter patient cohort, and to investigate correlations with age and with general anesthesia (GA). Interfractional motion of both diaphragm domes, spleen, liver and kidneys relative to bony anatomy was quantified in 189 children (mean age 8.2; range 0.4–17.9 years), using 271 reference CT and 2052 cone beam CT scans. We calculated the distributions of systematic and random errors (standard deviations Σ and σ, respectively) in cranio-caudal (CC), left-right and anterior-posterior directions. Besides correlations between organ motion and age we investigated motion differences in a subcohort of patients <7 years treated with and without GA. For all organs (all directions) interfractional group mean motion was not significantly different compared to the CT (Bonferroni's adjusted p=0.008). Calculated Σ and σ were larger for diaphragm domes, liver and spleen compared to values for the kidneys (Table). We found no correlations between organ motion and age (r<0.1; p>0.05). Motion of both diaphragm domes, liver and spleen in CC direction for patients (<7 years) treated with GA was significantly smaller compared to those treated without GA (p<0.008), resulting in smaller Σ and σ for both diaphragm domes and three organs (Table). Motion quantification in a large cohort resulted in good estimations of interfractional Σ and σ values. There were no correlations between motion and age, but the use of GA in young patients showed significantly less motion, with subsequently small differences in Σ and σ values between groups. [ABSTRACT FROM AUTHOR]