Clinical application of MR-Only in cyberknife stereotactic radiotherapy for brain metastases: a feasibility study

Abstract

Due to the limited number of studies on MR-only stereotactic radiotherapy (SRT) for brain metastases using CyberKnife in the literature, this study systematically evaluates the dose calculations and image guidance accuracy of synthetic CT (sCT) and sCT-derived digital reconstructed radiographs (sDRRs), to assess the feasibility of clinical MR-only workflow implementation in CyberKnife SRT for brain metastases. We developed a machine learning model trained on T1-weighted MR and corresponding CT images from 50 patients with brain metastases who had previously undergone CyberKnife treatment, with images from an additional 18 patients used to test the feasibility of the MR-only workflow. The Mean Absolute Error (MAE), Structural Similarity Index (SSIM), Peak Signal-to-Noise Ratio (PSNR) and the Dice Similarity Coefficient (DSC) were used to evaluate the image quality of sCT and sDRR. For dosimetric evaluation, the sCT-based and transferred plans (namely, the original planning parameters were transferred to the sCT images for dose recalculation) was compared with the plans based on the real CT images (rCT) using DVH metrics. For image-guided positioning accuracy, the 2D errors generated by registering DRR with the digital radiography images (DRs) were converted into translational and rotational couch shifts using a geometric back-projection method, thereby assessing the consistency of positioning accuracy between the sDRRs with the rCT-derived DRRs (rDRRs). The sCT images had a mean MAE of 10.08 ± 2.14 HU, a SSIM of 0.98 ± 0.01, and a PSNR of 34.73 ± 1.27 dB, and the overall sDRRs maintained high image quality (MAE: 37.36 ± 9.31 HU; SSIM: 0.95 ± 0.03; PSNR: 31.41 ± 7.14 dB). Large OARs (brainstem/eyeballs) had high DSC (> 0.80), while small OARs (lenses/optic pathway) had lower DSC. The dosimetric parameters of PTV and OARs under both planning strategies showed no statistically significant difference from the rCT-based plans ( p > 0.05). When using sDRRs for image guidance, the translational errors were submillimeter, and the rotational errors had a wider distribution but mean values within robotic correction range, there was no statistical difference compared with that of the rDRRs ( p > 0.05). The proposed model can generate accurate sCT for brain metastases, and the feasibility of the MR-only in CyberKnife SRT has been verified. This study is retrospectively registered in the Clinical trial Center of Zhejiang Cancer Hospital in Jan 1th, 2024 (No. MR-33-24-003134).