EUVIMEDOpdag EUVIMED
Crossref

Megavoltage CT enhancement for cervical cancer tomotherapy using a generative adversarial network with deformable convolution and self‐attention

Wanwei Jian, Lin Zhu, Bailin Zhang, Qiang He, Geng Yang, Huaizhi Jin, Fei Li, Haoyu Meng, Xuetao Wang

Medical Physics · 2026

DOI: 10.1002/mp.70416 ↗

At a glance

Journal article in Medical Physics, 2026. Written by Wanwei Jian and 8 co-authors. Institution: Department of Radiation Therapy, The Second Affiliated Hospital of Guangzhou University of Chinese Medicine, Guangzhou, Guangdong, China. Major MEDLINE topics: Generative Adversarial Networks, Uterine Cervical Neoplasms, Image Processing, Computer-Assisted, Tomography, X-Ray Computed. Cited 1 times so far (Crossref); 37 references. Funded by: State Key Laboratory of Traditional Chinese Medicine Syndrome, Municipal University (Institute) Enterprise Joint Funding Project, Guangdong Provincial Hospital of Traditional Chinese Medicine Science and Technology Research Project.

AbstractSubjectsBibliografiske oplysningerCiteRelated studies

Abstract (original language)

Background

Megavoltage computed tomography (MVCT) is an essential imaging modality for verifying patient positioning in helical tomotherapy. However, its clinical application in daily anatomical monitoring and adaptive radiotherapy is hindered by inherent image artifacts and poor soft‐tissue contrast. This issue is particularly pronounced in pelvic radiotherapy, where the intra‐ and interfraction anatomical variations necessitate high‐quality image guidance to ensure precise dose delivery.

Purpose

We developed a deep‐learning‐based framework for MVCT enhancement to improve anatomical visualization and facilitate accurate adaptive treatment planning for cervical cancer.

Methods

This study analyzed a retrospective cohort of 170 patients with cervical cancer who underwent helical tomotherapy. The proposed deep‐learning‐based algorithm employed a generative adversarial network (GAN) that integrated deformable convolution and a self‐attention mechanism (SADC‐EGAN) to improve MVCT image quality. Comparative analyses were conducted against representative baseline methods, including U‐Net, Attention U‐Net, U‐Net++, Swin‐UNet, CycleGAN, and Pix2Pix. Model performance was assessed using quantitative metrics, including mean absolute error (MAE), peak signal‐to‐noise ratio (PSNR), structural similarity index measure (SSIM), and Fréchet inception distance (FID).

Results

The synthetic computed tomography (sCT) images generated by the proposed SADC‐EGAN method demonstrated superior Hounsfield unit (HU) accuracy and structural similarity compared to the original MVCT. Specifically, the MAE between the sCT and kilovoltage computed tomography (kVCT) was reduced to 36.32 ± 6.69 HU, compared with 56.72 ± 9.09 HU for MVCT. In terms of image quality, the sCT images exhibited notable enhancements over MVCT images, with higher PSNR (32.54 ± 2.31 vs. 29.40 ± 1.56 dB), improved SSIM (0.93 ± 0.01 vs. 0.89 ± 0.02), and substantially lower FID (66.68 ± 22.31 vs. 153.52 ± 28.77).

Conclusions

The proposed SADC‐EGAN framework, integrating deformable convolutions and self‐attention, effectively generated high‐quality kVCT‐like images from MVCT, improving both HU accuracy and image quality. This approach has clinical potential to enable online adaptive helical tomotherapy for cervical cancer.

Subjects

MeSH terms (MEDLINE)

Generative Adversarial NetworksUterine Cervical NeoplasmsImage Processing, Computer-AssistedTomography, X-Ray ComputedRadiotherapy, Intensity-ModulatedHumansFemaleRetrospective StudiesGenerative Artificial Intelligence

Author keywords

adaptive radiation therapycervical cancerdeformable convolutiongenerative adversarial network (GAN)megavoltage CT enhancement

Authors and institutions

  • Department of Radiation Therapy, The Second Affiliated Hospital of Guangzhou University of Chinese Medicine, Guangzhou, Guangdong, China.
  • State Key Laboratory of Traditional Chinese Medicine Syndrome, The Second Affiliated Hospital of Guangzhou University of Chinese Medicine, Guangzhou, Guangdong, China.

Funding

  • State Key Laboratory of Traditional Chinese Medicine Syndrome
  • Municipal University (Institute) Enterprise Joint Funding Project
  • Guangdong Provincial Hospital of Traditional Chinese Medicine Science and Technology Research Project

Cite

APA

Jian, W., Zhu, L., Zhang, B., He, Q., Yang, G., Jin, H., Li, F., Meng, H., & Wang, X. (2026). Megavoltage CT enhancement for cervical cancer tomotherapy using a generative adversarial network with deformable convolution and self‐attention. Medical Physics. https://doi.org/10.1002/mp.70416

Vancouver

Jian W, Zhu L, Zhang B, He Q, Yang G, Jin H, et al. Megavoltage CT enhancement for cervical cancer tomotherapy using a generative adversarial network with deformable convolution and self‐attention. Medical Physics. 2026. doi:10.1002/mp.70416

BibTeX
@article{Jian2026,
  author = {Jian, Wanwei and Zhu, Lin and Zhang, Bailin and He, Qiang and Yang, Geng and Jin, Huaizhi and Li, Fei and Meng, Haoyu and Wang, Xuetao},
  title = {Megavoltage CT enhancement for cervical cancer tomotherapy using a generative adversarial network with deformable convolution and self‐attention},
  journal = {Medical Physics},
  year = {2026},
  doi = {10.1002/mp.70416}
}
Start for free →