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
. 2022 Jun;6(2):110-118.
doi: 10.1002/pro6.1163. Epub 2022 Jun 11.

Patient-specific synthetic magnetic resonance imaging generation from cone beam computed tomography for image guidance in liver stereotactic body radiation therapy

Zeyu Zhang  1 , Zhuoran Jiang  1 , Hualiang Zhong  2 , Ke Lu  1 , Fang-Fang Yin  1 , Lei Ren  3
Affiliations

Patient-specific synthetic magnetic resonance imaging generation from cone beam computed tomography for image guidance in liver stereotactic body radiation therapy

Zeyu Zhang et al. Precis Radiat Oncol. 2022 Jun.

Abstract

Objective: Despite its prevalence, cone beam computed tomography (CBCT) has poor soft-tissue contrast, making it challenging to localize liver tumors. We propose a patient-specific deep learning model to generate synthetic magnetic resonance imaging (MRI) from CBCT to improve tumor localization.

Methods: A key innovation is using patient-specific CBCT-MRI image pairs to train a deep learning model to generate synthetic MRI from CBCT. Specifically, patient planning CT was deformably registered to prior MRI, and then used to simulate CBCT with simulated projections and Feldkamp, Davis, and Kress reconstruction. These CBCT-MRI images were augmented using translations and rotations to generate enough patient-specific training data. A U-Net-based deep learning model was developed and trained to generate synthetic MRI from CBCT in the liver, and then tested on a different CBCT dataset. Synthetic MRIs were quantitatively evaluated against ground-truth MRI.

Results: The synthetic MRI demonstrated superb soft-tissue contrast with clear tumor visualization. On average, the synthetic MRI achieved 28.01, 0.025, and 0.929 for peak signal-to-noise ratio, mean square error, and structural similarity index, respectively, outperforming CBCT images. The model performance was consistent across all three patients tested.

Conclusion: Our study demonstrated the feasibility of a patient-specific model to generate synthetic MRI from CBCT for liver tumor localization, opening up a potential to democratize MRI guidance in clinics with conventional LINACs.

PubMed Disclaimer

Conflict of interest statement

CONFLICT OF INTEREST The authors declares that they have no conflicts of interest.

Figures

FIGURE 1
FIGURE 1
Overall workflow of this study. CBCT, cone beam computed tomography; CT, computed tomography; MRI, magnetic resonance imaging
FIGURE 2
FIGURE 2
Architecture of UNet. The orange block is the input and the green block is the output
FIGURE 3
FIGURE 3
Representative slices of (A) onboard cone beam computed tomography (CBCT), (B) synthetic magnetic resonance imaging (MRI), and (C) ground truth MRI. The red circle highlights the region that contains the tumor
FIGURE 4
FIGURE 4
Representative difference images of the patient study. (A) Image showing the difference image between cone beam computed tomography (CBCT), and ground truth magnetic resonance imaging (MRI). (B) Image presents the difference between synthetic MRI and ground truth MRI
FIGURE 5
FIGURE 5
Line profiles of onboard cone beam computed tomography (CBCT), synthetic magnetic resonance imaging (MRI), and ground truth MRI for the liver. The red line illustrates the position of line profiles on the image
FIGURE 6
FIGURE 6
Line profiles of onboard cone beam computed tomography (CBCT), synthetic MRI and ground truth magnetic resonance imaging (MRI) for the tumor. The red line illustrates the position of line profiles on the image. GTV, gross tumor volume
FIGURE 7
FIGURE 7
Representative slices of hybrid magnetic resonance imaging (MRI)/cone beam computed tomography (CBCT) images from two patients
FIGURE 8
FIGURE 8
Representative slices of XCAT, synthetic MR-XCAT, and ground truth MR-XCAT
See this image and copyright information in PMC

Similar articles

See all similar articles

Cited by

References

    1. Siegel RL, Miller KD, Jemal A. Cancer statistics, 2019. CA Cancer J Clin. 2019;69(1):7–34. - PubMed
    1. Anwanwan D, Singh SK, Singh S, Saikam V, Singh R. Challenges in liver cancer and possible treatment approaches. Biochim Biophys Acta Rev Cancer. 2020;1873(1):188314. - PMC - PubMed
    1. Liu E, Stenmark MH, Schipper MJ, et al. Stereotactic body radiation therapy for primary and metastatic liver tumors. Transl Oncol. 2013;6(4):442–446. - PMC - PubMed
    1. Scorsetti M, Comito T, Clerici E, et al. Phase II trial on SBRT for unresectable liver metastases: long-term outcome and prognostic factors of survival after 5 years of follow-up. Radiat Oncol. 2018;13(1):1–10. - PMC - PubMed
    1. Zelefsky MJ, Kollmeier M, Cox B, et al. Improved clinical outcomes with high-dose image guided radiotherapy compared with non-IGRT for the treatment of clinically localized prostate cancer. Int J Radiat Oncol Biol Phys. 2012;84(1):125–129. - PubMed

LinkOut - more resources