Pitfalls in Dose-Volume Histogram Computations
F Kaster1, M Aznar2, T Kadir1*, (1) Mirada Medical, Oxford, United Kingdom, (2) Rigshospitalet, University of Copenhagen, Copenhagen, DenmarkSU-E-T-681 Sunday 3:00PM - 6:00PM Room: Exhibit Hall
Purpose: To systematically study the effects of computation details on DVH accuracy for the first time in a teletherapy planning context, measure the effect sizes of different parameters and make recommendations for quality assurance in multicentric studies.
Methods: We defined two IMRT plans (maximum doses: 84/79 Gy) on a physical phantom (using a commercial TPS) and exported five dose volumes with different resolutions (1*1*0.83 mm^3, 2*2*2.5 mm^3, 3*3*2.5 mm^3, 4*4*5 mm^3, 5*5*5 mm^3) and contours for fifteen structures (volumes between 1 and 349 cm^3). We computed 7200 DVHs by independently varying dose bin number (2^7, 2^8, 2^9, 2^10), grid geometry (CT, dose volume), voxel counting scheme (completely inside, center inside, partial volume-weighted), interpolation method (nearest neighbor, linear, cubic). For each structure, the DVH with optimal simulation / computation parameters was interpreted as ground truth, and compared against the suboptimal DVHs using the percentage of failing gammas (PFG) distance (doi:10.1088/0031-9155/55/11/N04) [1 Gy dose tolerance, 2% volume tolerance]. The effect sizes of the various parameters were estimated via ANOVA.
Results: DVH accuracy (as measured by PFG) depended significantly on dose resolution (p<1e-15), grid geometry (p<1e-15) and voxel counting scheme (p=9e-4), with partial η² values of 0.408 / 0.104 / 0.002. Bin number and interpolation method were negligible. DVHs computed from a 4 mm grid had an almost three times higher average PFG than DVHs from a 2 mm grid (0.42 vs. 0.16).
Conclusion: For applications where DVH comparability between clinical sites with different TPS is imperative (e.g. multicentric studies), the dose resolution should be strictly identical, and researchers should ensure that DVHs are consistently computed either in the dose or CT grid geometry. Differences in the other computation parameters can be tolerated. Dose volumes with a resolution of >3 mm, whilst occasionally encountered in clinical routine, are unsuitable for accurate DVH computation.
Funding Support, Disclosures, and Conflict of Interest: FK and TK are employees of Mirada Medical. However, the contents of this abstract constitute strictly basic research, so that there is no conflict of interest.