Key points are not available for this paper at this time.
BACKGROUND AND PURPOSE: To investigate the impact that loading contours into an internal representation and saving them back to DICOM format has on contour position within commercially available contouring systems. MATERIALS AND METHODS: Two DICOM RT Structure Sets (RTSS) were loaded into 12 different commercial contour editing systems. Small non-editing actions were taken to prompt the systems to convert the structures to their internal representation. Contours were exported again as DICOM RTSS. The exported contours were compared to the original contours. The impact on contour similarity measures was quantified by their calculation against a common reference set for both the original and the re-exported contours. RESULTS: Average distances up to 0.23 mm were observed between the original and re-exported contours on thoracic data for some systems, with maximum distances up to 37.7 mm resulting from topological changes. Contour boundary changes impacted contouring similarity measures up to 2.6%, 29%, 35% and 21% for volumetric Dice Similarity Coefficient, 2D Mean Surface Distance, 3D Mean Surface Distance, and Hausdorff Distance, respectively. Notably, Surface Dice Similarity Coefficient and Normalised Added Path Length varied up to 96% and 97% respectively at low tolerances. Other systems preserved the original contours. CONCLUSIONS: Caution should be employed when comparing contouring accuracy measures between studies or within multi-centre evaluations if different contouring systems have been used. For monitoring auto-contouring in clinical practice, differences between automatic and clinical contours smaller than one quarter of the in-plane voxel size can be disregarded, as possibly reflecting software-related effects rather than intentional editing.
Gooding et al. (Sun,) studied this question.