EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

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

Xiwen Shu iD, Ke Lu iD, Jingtong Zhao, John Ginn, Yongbok Kim iD, Zhenyu Yang, Justus Adamson iD, Trey Mullikin, Chunhao Wang

Journal of Applied Clinical Medical Physics · 2026

DOI: 10.1002/acm2.70343 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Applied Clinical Medical Physics, 2026. Verfasst von Xiwen Shu und 8 weiteren Autor:innen. Beteiligte Einrichtung: Department of Radiation Oncology, Duke University, Durham, North Carolina, USA. Hauptthemen laut MEDLINE: Radiotherapy Planning, Computer-Assisted, Radiosurgery, Tomography, X-Ray Computed, Magnetic Resonance Imaging. Die Arbeit nennt 40 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: NCI NIH HHS.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

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 sCT F 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 sCT F 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 sCT F 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.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Radiotherapy Planning, Computer-AssistedRadiosurgeryTomography, X-Ray ComputedMagnetic Resonance ImagingBrain NeoplasmsImage Processing, Computer-AssistedDeep LearningKnowledge BasesHumansRadiotherapy, Intensity-ModulatedRadiotherapy DosageOrgans at RiskMaleAlgorithmsFemale

Stichwörter der Autor:innen

MRI‐only radiotherapyResidual U‐Netdeep learningframeless SRStreatment planning

Autor:innen und Institutionen

  • Department of Radiation Oncology, Duke University, Durham, North Carolina, USA.
  • Medical Physics Graduate Program, Duke Kunshan University, Kunshan, Jiangsu, China.

ORCID-Profile: Xiwen Shu, Ke Lu, Yongbok Kim, Justus Adamson

Förderung

  • NCI NIH HHS

Zitieren

APA

Shu, X., Lu, K., Zhao, J., Ginn, J., Kim, Y., Yang, Z., Adamson, J., Mullikin, T., & Wang, C. (2026). Knowledge‐based deep residual U‐Net (DRU) for synthetic CT generation using a single MR volume for frameless radiosurgery. Journal of Applied Clinical Medical Physics. https://doi.org/10.1002/acm2.70343

Vancouver

Shu X, Lu K, Zhao J, Ginn J, Kim Y, Yang Z, et al. Knowledge‐based deep residual U‐Net (DRU) for synthetic CT generation using a single MR volume for frameless radiosurgery. Journal of Applied Clinical Medical Physics. 2026. doi:10.1002/acm2.70343

BibTeX
@article{Shu2026,
  author = {Shu, Xiwen and Lu, Ke and Zhao, Jingtong and Ginn, John and Kim, Yongbok and Yang, Zhenyu and Adamson, Justus and Mullikin, Trey and Wang, Chunhao},
  title = {Knowledge‐based deep residual U‐Net (DRU) for synthetic CT generation using a single MR volume for frameless radiosurgery},
  journal = {Journal of Applied Clinical Medical Physics},
  year = {2026},
  doi = {10.1002/acm2.70343}
}
Kostenlos starten →