Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2025 Jul 22.
doi: 10.1007/s13246-025-01606-1. Online ahead of print.

Supervised versus unsupervised GAN for pseudo-CT synthesis in brain MR-guided radiotherapy

Milad Zeinali Kermani  1 , Mohamad Bagher Tavakoli  2 , Amir Khorasani  3 , Iraj Abedi  1 , Vahid Sadeghi  4 , Alireza Amouheidari  5
Affiliations

Supervised versus unsupervised GAN for pseudo-CT synthesis in brain MR-guided radiotherapy

Milad Zeinali Kermani et al. Phys Eng Sci Med. .

Abstract

Radiotherapy is a crucial treatment for brain tumor malignancies. To address the limitations of CT-based treatment planning, recent research has explored MR-only radiotherapy, requiring precise MR-to-CT synthesis. This study compares two deep learning approaches, supervised (Pix2Pix) and unsupervised (CycleGAN), for generating pseudo-CT (pCT) images from T1- and T2-weighted MR sequences. 3270 paired T1- and T2-weighted MRI images were collected and registered with corresponding CT images. After preprocessing, a supervised pCT generative model was trained using the Pix2Pix framework, and an unsupervised generative network (CycleGAN) was also trained to enable a comparative assessment of pCT quality relative to the Pix2Pix model. To assess differences between pCT and reference CT images, three key metrics (SSIM, PSNR, and MAE) were used. Additionally, a dosimetric evaluation was performed on selected cases to assess clinical relevance. The average SSIM, PSNR, and MAE for Pix2Pix on T1 images were 0.964 ± 0.03, 32.812 ± 5.21, and 79.681 ± 9.52 HU, respectively. Statistical analysis revealed that Pix2Pix significantly outperformed CycleGAN in generating high-fidelity pCT images (p < 0.05). There was no notable difference in the effectiveness of T1-weighted versus T2-weighted MR images for generating pCT (p > 0.05). Dosimetric evaluation confirmed comparable dose distributions between pCT and reference CT, supporting clinical feasibility. Both supervised and unsupervised methods demonstrated the capability to generate accurate pCT images from conventional T1- and T2-weighted MR sequences. While supervised methods like Pix2Pix achieve higher accuracy, unsupervised approaches such as CycleGAN offer greater flexibility by eliminating the need for paired training data, making them suitable for applications where paired data is unavailable.

Keywords: Deep learning; Generative adversarial networks; Radiotherapy; Synthetic CT; Treatment planning.

PubMed Disclaimer

Conflict of interest statement

Declarations. Conflict of interest: The authors declare no conflicts of interest related to this study. This research was conducted independently, without any financial or commercial influences that could be perceived as potential conflicts. Ethics approval: This study was conducted in accordance with the ethical standards of the institutional and/or national research committee and with the principles of the Declaration of Helsinki. Ethical approval was obtained from [Isfahan university of medical sciences] (Approval Number: [IR.MUI.MED.REC.1401.362.]). Consent to participate: Not applicable. This study did not involve human participants or animals requiring informed consent. Consent to publish: Not applicable. This study did not involve human participants or personal data requiring consent for publication.

Similar articles

See all similar articles

References

    1. Ilic I, Ilic M (2023) International patterns and trends in the brain cancer incidence and mortality: an observational study based on the global burden of disease. Heliyon 9(7):e18222 - PubMed - PMC
    1. Rees J (2011) Diagnosis and treatment in neuro-oncology: an oncological perspective. Br J Radiol 84(special_issue_2):S82–S89 - PubMed
    1. Mason JH, Perelli A, Nailon WH, Davies ME (eds) (2017) Quantitative electron density CT imaging for radiotherapy planning. In: Medical image understanding and analysis: 21st annual conference, MIUA 2017, Edinburgh, UK, July 11–13, 2017, Proceedings 21. Springer, Berlin
    1. Wang Y, Liu C, Zhang X, Deng W (2019) Synthetic CT generation based on T2 weighted MRI of nasopharyngeal carcinoma (NPC) using a deep convolutional neural network (DCNN). Front Oncol 9:1333 - PubMed - PMC
    1. Ulin K, Urie MM, Cherlow JM (2010) Results of a multi-institutional benchmark test for cranial CT/MR image registration. Int J Radiat Oncol Biol Phys 77(5):1584–1589 - PubMed - PMC