Knowledge-based deep residual U-Net (DRU) for synthetic CT generation using a single MR volume for frameless radiosurgery.

PURPOSE: To develop a knowledge-based deep model for sCT generation from a single MR volume in LINAC-based frameless SRS, enabling the MR-only workflow without extra CT simulation. METHODS: A total of 139 patients were included in the study, with 120 used for training and 19 for testing. A Deep Residual U-Net(DRU) was developed to generate sCT from patient-specific high-resolution T1 + Contrast MR volume, complemented by a healthy brain CT volume from the Visible Human Project that provides CT-specific anatomical knowledge. To simulate treatment conditions, a template immobilization mask was deformed to align with the patient-specific sCT anatomy, thereby creating a full sCTF volume. Four metrics, including PSNR, SSIM, RMSE, and MAE were derived to evaluate Hounsfield units(HU) accuracy of sCT compared to the ground-truth CT without immobilization masks. Single isocenter multi-target SRS plans developed with volumetric modulated arc therapy (VMAT) technique were recalculated within sCTF volumes to produce simulated dose distributions, which were compared with clinical plan dose distributions using the mean dose difference in the planning target volume(PTV) and gamma index evaluation. RESULTS: In the test set, the generated sCT (statistics are reported as mean ± standard deviation) achieved a PSNR(Peak Signal-to-Noise Ratio) of 75 ± 4 dB, Structural Similarity Index (SSIM) of 0.99 ± 0.01, root mean square error (RMSE) of 11.9 ± 5.8 HU, and mean average error (MAE) of 1.4 ± 0.8 HU for brain tissues. When comparing sCTF dose calculation results against the original plans, gamma index passing rates were 95.8 ± 4.2% for the entire volume and 84.4 ± 15.0% within PTVs, using 3%/1 mm/15% threshold criteria. The median/ interquartile range of PTV dose differences were -2.0% and 2.3%, with all discrepancies below -5.0%. CONCLUSION: This study successfully demonstrated the generation and validation of sCT images from single-modality MRI using a knowledge-based deep model. The results confirm that single-modality MRI without simulation CT scan effectively supports frameless SRS planning and integrates seamlessly into current clinical workflows.

Duke Scholars

Author John Stephen Ginn Radiation Oncology

Author Trey Carlton Mullikin Radiation Oncology

Author Chunhao Wang Radiation Oncology

Author Ke Lu Radiation Oncology

Author Justus D Adamson Radiation Oncology