Generating synthetic computed tomography for radiotherapy: SynthRAD2025 challenge report
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866909040343252992 |
|---|---|
| author | Rogowski, Viktor Terpstra, Maarten L. Wahl, Niklas Kamp, Florian van der Bijl, Erik Galapon, Arthur Jr. Kurz, Christopher Xin, Bowen Sun, Zhengxiang Min, Hollie Belous, Gregg Dowling, Jason Xia, Yan Mei, Siyuan Fan, Fuxin Longuefosse, Arthur Gonzalez, Javier Sequeiro Benito, Miguel Diaz Martin, Alvaro Garcia Baldacci, Fabien Boussot, Valentin Hémon, Cédric Nunes, Jean-Claude Dillenseger, Jean-Louis Zhang, Zhiyuan Cai, Jinghua Bing, Han Zuopeng, Tan Brioso, Ricardo Loiacono, Daniele Landry, Guillaume Thummerer, Adrian Maspero, Matteo |
| author_facet | Rogowski, Viktor Terpstra, Maarten L. Wahl, Niklas Kamp, Florian van der Bijl, Erik Galapon, Arthur Jr. Kurz, Christopher Xin, Bowen Sun, Zhengxiang Min, Hollie Belous, Gregg Dowling, Jason Xia, Yan Mei, Siyuan Fan, Fuxin Longuefosse, Arthur Gonzalez, Javier Sequeiro Benito, Miguel Diaz Martin, Alvaro Garcia Baldacci, Fabien Boussot, Valentin Hémon, Cédric Nunes, Jean-Claude Dillenseger, Jean-Louis Zhang, Zhiyuan Cai, Jinghua Bing, Han Zuopeng, Tan Brioso, Ricardo Loiacono, Daniele Landry, Guillaume Thummerer, Adrian Maspero, Matteo |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_13555 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Generating synthetic computed tomography for radiotherapy: SynthRAD2025 challenge report Rogowski, Viktor Terpstra, Maarten L. Wahl, Niklas Kamp, Florian van der Bijl, Erik Galapon, Arthur Jr. Kurz, Christopher Xin, Bowen Sun, Zhengxiang Min, Hollie Belous, Gregg Dowling, Jason Xia, Yan Mei, Siyuan Fan, Fuxin Longuefosse, Arthur Gonzalez, Javier Sequeiro Benito, Miguel Diaz Martin, Alvaro Garcia Baldacci, Fabien Boussot, Valentin Hémon, Cédric Nunes, Jean-Claude Dillenseger, Jean-Louis Zhang, Zhiyuan Cai, Jinghua Bing, Han Zuopeng, Tan Brioso, Ricardo Loiacono, Daniele Landry, Guillaume Thummerer, Adrian Maspero, Matteo Medical Physics Artificial Intelligence 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. |
| title | Generating synthetic computed tomography for radiotherapy: SynthRAD2025 challenge report |
| topic | Medical Physics Artificial Intelligence |
| url | https://arxiv.org/abs/2605.13555 |