Generating synthetic computed tomography for radiotherapy: SynthRAD2025 challenge report

2026-05-13

AI Summary

This study addresses the challenges of radiation burden from repeated CT scans in radiotherapy and the lack of electron density information in MRI, while also acknowledging that cone-beam CT (CBCT) requires correction for accurate dose calculation. To overcome these limitations, the authors propose a deep learning approach to generate high-fidelity synthetic CT (sCT) images from either MRI or CBCT, enabling MRI-only radiotherapy workflows and CBCT-based adaptive replanning. Validated across five European centers with 2,362 patients, the method demonstrates excellent CBCT-to-CT performance (mean absolute error: 48.3 HU; photon gamma pass rate >99%, proton ≈89%) and superior MRI-to-CT accuracy in head-and-neck regions. Notably, this work is the first to systematically show that image quality correlates only weakly with dosimetric accuracy, underscoring the necessity of dedicated dosimetric validation for clinical deployment of sCT.

Abstract

Radiation therapy (RT) requires precise dose delivery over multiple fractions, with CT fundamental for treatment planning due to its electron density information. Repeated CT acquisitions impose radiation exposure and logistical burdens, MRI lacks electron density, and cone-beam CT (CBCT) requires correction for dose calculation. Synthetic CT (sCT) generation addresses these by converting MRI or CBCT into CT-equivalent images with accurate Hounsfield Unit (HU) values, enabling MRI-only RT and CBCT-based adaptive workflows. Building on SynthRAD2023, SynthRAD2025 benchmarked sCT methods on 2,362 patients from five European centers across head and neck, thorax, and abdomen. Two tasks: MRI-to-CT (890 cases) and CBCT-to-CT (1,472 cases), evaluated via image similarity (MAE, PSNR, MS-SSIM), segmentation (Dice, HD95), and dosimetric metrics from photon and proton plans. With 803 participants and 12/13 valid submissions, Task 1 top performance reached MAE $64.8\pm21.3$ HU, PSNR $\sim$30 dB, MS-SSIM $\sim$0.936, Dice 0.79, photon $γ_{2\%/2\text{mm}}>98\%$, proton $γ\approx85\%$. Task 2 improved: MAE $48.3\pm13.4$ HU, PSNR 32.6 dB, MS-SSIM 0.968, Dice 0.86, photon $γ>99\%$, proton $γ\approx89\%$. Strong image--segmentation correlations ($ρ=0.78$--$0.79$) but moderate dose correlations confirmed image quality is insufficient as a dosimetric surrogate. Head-and-neck cases were most consistent; thoracic and abdominal cases showed greater variability. Residual errors at tissue interfaces propagate along beam paths, affecting proton dose more than photon. SynthRAD2025 demonstrates that deep learning yields clinically relevant sCTs, especially for CBCT-to-CT, while identifying persistent MRI-to-CT challenges and underscoring dose-based evaluation as essential for clinical validation.

Problem

• synthetic CT
• radiotherapy
• MRI-to-CT
• CBCT-to-CT
• electron density

Innovation

• synthetic CT
• deep learning
• dosimetric validation
• multi-center benchmark
• radiotherapy planning