Geometrical and dosimetric evaluation of breast target volume auto-contouring

Background and purpose: Automatic delineations are often used as a starting point in the radiotherapy contouring workflow, after which they are manually reviewed and adapted. The purpose of this work was to quantify the geometric differences between automatic and manually edited breast clinical target volume (CTV) contours and evaluate the dosimetric impact of such differences. Materials and methods: Eighty-seven automatically generated and manually edited contours of the left breast were retrieved from our clinical database. The automatic contours were obtained with a commercial auto-segmentation toolbox. The geometrical comparison was performed both locally and globally using the Dice score and the 95% Hausdorff distance (HD). Two treatment plans were generated for each patient and the obtained dosimetric differences were quantified using dose-volume histogram (DVH) parameters in the lungs, heart and planning target volume (PTV). An inter-observer variability study with four observers was performed on a subset of ten patients. Results: A median Dice score of 0.95 and a median 95% HD of 9.7 mm were obtained. Larger breasts were consistently under-contoured. Cranial under-contouring resulted in more than 5% relative decrease in PTV coverage in 15% of the patients while lateroposterior over-contouring increased the lung V-20Gy by a maximum of 2%. The inter-observer variability of the PTV coverage was smaller than the difference between PTV coverage achieved by the automatic and the consensus contours. Conclusions: Cranial under-contouring resulted in under-treatment, while lateroposterior over-contouring resulted in an increased lung dosage that is clinically irrelevant, showing the need to consider dose distributions to assess the clinical impact of local geometrical differences.