Analysis of components of variance determining probability of setup errors in CBCT-guided stereotactic radiotherapy of lung tumors

Abstract

Online tumor matching for SABR lung setup requires margins for inaccuracies due to intra-fraction variability of breathing-averaged tumor position (BATP) and CBCT image guidance. We studied intra-fraction variability during SABR delivery using VMAT, corrected these for measurement inaccuracies, and quantified the CBCT image-guidance uncertainties. For 193 fractions in 38 patients positioned without immobilization devices, CBCT scans were acquired before and after 2 arcs of a RapidArc treatment. A hidden marker test was performed to determine the accuracy of the CBCT system and an inter-observer test was performed to measure registration accuracy. Intra-fraction variability was calculated after correction for these components of variance, and the prediction interval for setup inaccuracies was determined. Correction for measurement inaccuracies reduced the intra-fraction variability of the BATP from 1.9 to 1.6 mm in AP, from 1.7 to 1.4 mm in SI and from 1.5 to 1.1 mm in LR direction (1 SD). Intra-fraction variability in bony anatomy after correction was ≤ 1 mm (1 SD). The 95% prediction interval to account for CBCT image-guidance uncertainties and intra-fraction variability was determined, and was found to be within our institutional PTV margins of 5 mm. Our findings show that it is essential to account for measurement and system inaccuracies when obtaining data for validating PTV margins from online CBCT image guidance.