Feasibility of artificial-intelligence-based synthetic computed tomography in a magnetic resonance-only radiotherapy workflow for brain radiotherapy: Two-way dose validation and 2D/2D kV-image-based positioning

Magnetic Resonance Imaging (MRI)-only workflow eliminates the MRI-computed tomography (CT) registration inaccuracy, which degrades radiotherapy (RT) treatment accuracy. For an MRI-only workflow MRI sequences need to be converted to synthetic-CT (sCT). The purpose of this study was to evaluate a commercially available artificial intelligence (AI)-based sCT generation for dose calculation and 2D/2D kV-image daily positioning for brain RT workflow. T1-VIBE DIXON was acquired at the 1.5 T MRI for 26 patients in RT setup for sCTs generation. For each patient, a volumetric modulated arc therapy (VMAT) plan was optimized on the CT, then recalculated on the sCT; and vice versa. sCT-based digitally reconstructed radiographs (DRRs) were fused with stereoscopic X-ray images recorded as image guidance for clinical treatments. Dosimetric differences between planned/recalculated doses and the differences between the calculated and recorded clinical couch shift/rotation were evaluated. Mean ΔD50 between planned/recalculated doses for target volumes ranged between −0.2 % and 0.2 %; mean ΔD50 and ΔD0.01ccm were −0.6 % and 1.6 % and −1.4 % and 1.0 % for organ-at-risks, respectively. Differences were tested for clinical equivalence using intervals ±2 % (dose), ±1mm (translation), and ±1° (rotation). Dose equivalence was found using ±2 % interval (p