The geometric and dosimetric effect of algorithm choice on propagated contours from CT to cone beam CTs

Adaptive radiotherapy relies of rapid re-contouring, online more so than offline. Intra-patient contour propagation via non-rigid registration offers a solution but can be of limited accuracy. However, the dosimetric significance of the inaccuracies is unknown. Here we evaluate the dosimetric reliability of contours generated by different commercially-available software packages.

Planning CT contours for ten head and neck cancer patients were propagated via five commercial packages to five CBCT scans acquired throughout treatment. The treatment plan was recalculated on each of the CBCTs for each set of propagated contours, and DVH parameters extracted for the spinal cord, brainstem, parotids and larynx. The propagated contours were compared to two gold standard contours: contours manually outlined and a consensus STAPLE contours generated from the propagated contours. Geometrical similarity was evaluated using mean distance to agreement (mDTA), Hausdorff distance, centroid agreement and Dice similarity coefficient. Dosimetric reliability was assessed against clinical constraints and comparing via the intraclass correlation coefficient (ICC).

All propagated contours were similar to the STAPLE (mDTA < 1.0 mm) whilst larger differences were seen for the manual contours (mDTA < 3.0 mm). The dosimetric comparison showed that the propagated contours gave excellent dose estimates for most organs. The spinal cord reliability was moderate (ICC > 0.66).

Large differences in geometric metrics rarely had a statistically significant impact on DVH parameters for the OARs studied. For that reason, propagated contours on treatment CBCT images are suitable for estimating dose to the OARs.