Auto-segmentation and dose accuracy evaluation of synthetic computed tomography generated from pelvis cone-beam computed tomography images using a cycle-generative adversarial network with a novel loss function

Background and Purpose: Synthetic CT (sCT) images generated from cone-beam (CB)CT images have shown improved image quality over CBCT images.This work evaluated a deep learning (DL)-based sCT model with the potential to facilitate accurate adaptive radiotherapy for pelvis patients.Materials and Methods: A DL-based cycle-Generative Adversarial Network (cycleGAN) model, incorporating a novel loss function to enhance structural image similarity, was used to generate sCT images from CBCT images acquired on a conventional c-arm Linac during intensity-modulated radiotherapy.Auto-segmentation accuracy for 10 pelvic structures was assessed compared to physiciandrawn contours using Dice similarity coefficients (DSC), Hausdorff distance (HD), and mean distance-toagreement (MDA).CT numbers for pelvic organs-at-risk were compared between sCT and planning CT (refCT).Dose, calculated using a Monte Carlo algorithm, was compared using relative dose differences to the gross tumor volume (GTV) for D 98%, D 50% , and D 2% between sCT and recalculated refCT, alongside 3Dglobal gamma analysis with 3%/3mm, 2%/2mm, and 1%/2mm criteria. Results:The sCTs demonstrated high auto-segmentation accuracy with DSC>0.8 and MDA<2 mm, except for the small bowel and colon.CT number differences were within published tolerances to achieve less than 1% dose difference excepting structures with substantial gas variations compared to the refCT.The mean dose difference to the GTV was 0.3%0.6across D 98% , D 50%, and D 2% .3D-gamma passing rates were 972% for the most restrictive criterion used, 1%/2mm.Conclusions: The cycleGAN-based CBCT-to-sCT model generated high-quality sCT images that may be directly utilized for image segmentation and dose calculation to advance adaptive radiotherapy on conventional Linacs.