A mathematical and dosimetric approach to validate auto‐contouring by Varian Smart segmentation for prostate cancer patients

Purpose The aim of this study was to quantify the discrepancies in geometrical and dosimetric impacts (in volumetric modulated arc therapy) between manually segmented (MS) contours smart segmentation (SS) auto-contours (by Varian Eclipse Treatment Planning System SS v13.5) for prostate cancer patients. Methods automated carried out by (Varian, version 13.5) Smart Segmentation workspace 10 patients four regions interest; such as, bladder, rectum, femoral head left, right. geometric deviation MS have been quantified form different parameters. organ-wise correlation validation parameters addressed. Results analysis showed good consistent bladder. hypothesis test checking compliance with AAPM 132 tolerance addressed validated bladder p-value = 0.01 0.05. There no significant difference dose–volume histogram (DVH) estimated standard DVH constraints protocol (as per TMH PRIME trial) also not significant, Conclusion This shows that “well correlated infer correctly about matching or coincidence auto contours,” contouring plan optimization can achieve acceptable constraints.